SlideShare a Scribd company logo
1 of 71

Deep Learning for Food Analysis
Petia Radeva
www.cvc.uab.es/~petia
Computer Vision at UB (CVUB), Universitat de Barcelona &
Medical Imaging Laboratory, Computer Vision Center
Index
 Motivation
 Learning and Deep learning
 Deep learning for food analysis
 Lifelogging
2
22:55AMiTANS’16, Albena, 26 of June, 2016
Metabolic diseases and health
3
22:55AMiTANS’16, Albena, 26 of June, 2016
 4.2 million die of chronic diseases
in Europe (diabetes or cancer)
linked to lack of physical activities
and unhealthy diet.
 Physical activities can increase
lifespan by 1.5-3.7 years.
 Obesity is a chronic disease
associated with huge economic,
social and personal costs.
 Risk factors for cancers,
cardiovascular and metabolic
disorders and leading causes of
premature mortality worldwide.
Health and medical care
 Today, 88% of U.S. healthcare dollars are
spent on medical care – access to
physicians, hospitals, procedures, drugs,
etc.
 However, medical care only accounts for
approximately 10% of a person’s health.
 Approximately half the decline in U.S.
Deaths from coronary heart disease from
1980 through 2000 may be attributable
to reductions in major risk factors
(systolic blood pressure, smoking,
physical inactivity).
4
22:55AMiTANS’16, Albena, 26 of June, 2016
Health and medical care
Recent data shows evidence of stagnation that may be explained by the increases in obesity and
diabetes prevalence.
Healthcare resources and dollars must now be dedicated to improving lifestyle and behavior.
5
22:55AMiTANS’16, Albena, 26 of June, 2016
Why food analysis?
 Today, measuring physical activities is not a problem.
 But what about food and nutrition?
 Nutritional health apps are based on food diaries
6
22:55AMiTANS’16, Albena, 26 of June, 2016
Two main questions?
 What we eat?
 Automatic food recognition vs. Food diaries
 And how we eat?
 Automatic eating pattern extraction – when, where, how, how
long, with whom, in which context?
 Lifelogging
7
22:55AMiTANS’16, Albena, 26 of June, 2016
Index
 Motivation
 Learning and Deep learning
 Deep learning for food analysis
 Lifelogging
8
22:55AMiTANS’16, Albena, 26 of June, 2016
Why “Learn”?
 Machine learning consists of:
 Developing models, methods and algorithms to make computers learn i.e. take decision.
 Training from big amount of example data.
 Learning is used when:
 Humans are unable to explain their expertise (speech recognition)
 Human expertise does not exist (navigating on Mars),
 Solution changes in time (routing on a computer network)
 Solution needs to be adapted to particular cases (user biometrics)
 Data is cheap and abundant (data warehouses, data marts); knowledge is expensive
and scarce.
 Example in retail: Customer transactions to consumer behavior:
People who bought “Da Vinci Code” also bought “The Five People You Meet in Heaven” (www.amazon.com)
 Build a model that is a good and useful approximation to the data.
9
22:55AMiTANS’16, Albena, 26 of June, 2016
Growth of Machine Learning
 This trend is accelerating due to:
 Big data and data science today are a reality
 Improved data capture, networking, faster computers
 New sensors / IO devices / Internet of Things
 Software too complex to write by hand
 Demand for self-customization to user
 It turns out to be difficult to extract knowledge from human
expertsfailure of expert systems in the 1980’s.
 Improved machine learning algorithms
AMiTANS’16, Albena, 26 of June, 2016
10
22:55
22:55AMiTANS’16, Albena, 26 of June, 2016
11
Deep leearning everywhere
12
22:55AMiTANS’16, Albena, 26 of June, 2016
Deep learning applications
13
22:55AMiTANS’16, Albena, 26 of June, 2016
Formalization of learning
 Consider:
 training examples: D= {z1, z2, .., zn} with the zi being examples sampled from an unknown
process P(Z);
 a model f and a loss functional L(f,Z) that returns a real-valued scalar.
Minimize the expected value of L(f,Z) under the unknown generating process P(Z).
 Supervised Learning: each example is an (input,target) pair: Z=(X,Y)
 classification: Y is a finite integer (e.g. a symbol) corresponding to a class index, and we
often take as loss function the negative conditional log-likelihood, with the interpretation
that fi(X) estimates P(Y=i|X):
L(f,(X,Y)) = -log fi(X), where fi(X)>=0, Σi fi(X) = 1.
14
22:55AMiTANS’16, Albena, 26 of June, 2016
Classification/Recognition
Is this an urban or rural area?
Input: x
Output: y  {-1,+1}
From: M. Pawan Kumar
Which city is this?
Output: y  {1,2,…,C}
Binary classification Multi-class classification
22:55AMiTANS’16, Albena, 26 of June, 2016
15
Object Detection and segmentation
Where is the object in the image?
Output: y  {Pixels}
From: M. Pawan Kumar
What is the semantic class of each pixel?
Output: y  {1,2,…,C}|Pixels|
car
road
grass
treesky
22:55AMiTANS’16, Albena, 26 of June, 2016
16
A Simplified View of the Pipeline
Input
x
Features
Φ(x)
Scores
f(Φ(x),y)
Extract Features
Compute
Scores
maxy f(Φ(x),y)Prediction
y(f)
Learn f
From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016
17
Learning Objective
Data distribution P(x,y)
Prediction
f* = argminf EP(x,y) Error(y(f),y)
Ground Truth
Measure of prediction quality (error, loss)
Distribution is unknown
Expectation over
data distribution
From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016
18
Learning Objective
Training data {(xi,yi), i = 1,2,…,n}
Prediction
f* = argminf EP(x,y) Error(y(f),y)
Ground Truth
Measure of prediction quality
Expectation over
data distribution
From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016
19
Learning Objective
Training data {(xi,yi), i = 1,2,…,n}
Prediction
f* = argminf Σi Error(yi(f),yi)
Ground Truth
Measure of prediction quality
Expectation over
empirical distribution
Finite samples
From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016
20
The problem of image classification
21
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Dual representation of images as points/vectors
22
22:55
AMiTANS’16, Albena, 26 of June, 2016
32x32x3 D vector
Each image of M rows by N columns by C channels ( 3 for color
images) can be considered as a vector/point in RMxNxC and
viceversa.
Linear Classier and key classification components
22:55
23
Given two classes how to learn a hyperplane to separate them?
To find the hyperplane we need to specify :
• Score function
• Loss function
• Optimization
AMiTANS’16, Albena, 26 of June, 2016
Interpreting a linear classifier
24
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
32x32x3 D vector
General learning pipeline
25
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Training consists of constructing the prediction model f according to a training set.
The problem of image classification
26
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Parametric approach: linear classifier
27
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Score function:
Loss function/optimization
28
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
The score function
Image classification
29
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Loss function and optimisation
 Question: if you were to assign a single number to how unhappy you are
with these scores, what would you do?
22:55
30
Question : Given the score and the loss function, how to find the parameters W?
AMiTANS’16, Albena, 26 of June, 2016
Interpreting a linear classifier
31
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
10x3072
Why is a CNN doing deep learning?
32
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
where fi=Σjwij * xj w1n
f1
f2
fm
x1
x2
xn
w11
w12
Activation functions of NN
33
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Setting the number of layers and their size
34
- Neurons arranged into fully-connected layers
- Bigger = better (but might have to regularize more strongly).
- How many parameters to learn?
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Why a CNN is neural network?
35
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Architecture of neural networks
22:55
36
Modern CNNs: ~10 million neurons
Human visual cortex: ~5 billion neurons
AMiTANS’16, Albena, 26 of June, 2016
Activation functions of NN
37
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
What is it a Convolutional Neural Network?
22:55
38
AMiTANS’16, Albena, 26 of June, 2016
Convolutional and Max-pooling layer
22:55
39
Convolutional layer
Max-pool layer
How does the CNN work?
22:55
40
AMiTANS’16, Albena, 26 of June, 2016
Example architecture
22:55
41
The trick is to train the weights such that when the network sees a picture of a truck, the last layer will say “truck”.
AMiTANS’16, Albena, 26 of June, 2016
Training a CNN
22:55AMiTANS’16, Albena, 26 of June, 2016
42
The process of training a CNN consists of training all hyperparameters: convolutional
matrices and weights of the fully connected layers.
- Several millions pf parameters!!!
Learned convolutional filters
22:55
43
AMiTANS’16, Albena, 26 of June, 2016
Neural network training
44
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson
Using the chain rule, optimize the parameters, W of the
neural network by gradient descent and backpropagation.
22:55AMiTANS’16, Albena, 26 of June, 2016
Optimization consists of training severalmillions of parameters!
Monitoring loss and accuracy
22:55
45
Looks linear?
Learning rate too low!
Decreases too slowly?
Learning rate too high.
Looks too noisy?
Increases the batch size.
Big gap?
- you're overfitting, increase
regularization!
AMiTANS’16, Albena, 26 of June, 2016
Transfer learning
46
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Imagenet
22:55
47
AMiTANS’16, Albena, 26 of June, 2016
1001 benefits of CNN
 Transfer learning: Fine tunning for object recognition
 Replace and retrain the classier on top of the ConvNet
 Fine-tune the weights of the pre-trained network by continuing the backpropagation
 Feature extraction by CNN
 Object detectiion
 Object segmentation
 Image similarity and matching by CNN
22:55
48
Convolutional Neural Networks (4096 Features)AMiTANS’16, Albena, 26 of June, 2016
ConvNets are everywhere
49
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
ConvNets are everywhere
50
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
ConvNets are everywhere
51
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
ConvNets are everywhere
52
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
ConvNets are everywhere
53
From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
Index
 Motivation
 Learning and Deep learning
 Deep learning for food analysis
 Lifelogging
54
22:55AMiTANS’16, Albena, 26 of June, 2016
Automatic food analysis
55
Can we automatically recognize food?
• To detect every instance of a dish in all of its variants, shapes and positions and in a
large number of images.
The main problems that arise are:
• Complexity and variability of the data.
• Huge amounts of data to analyse.
22:55AMiTANS’16, Albena, 26 of June, 2016
Automatic Food Analysis
 Food detection
 Food recognition
 Food environment recognition
 Eating pattern extraction
56
22:55AMiTANS’16, Albena, 26 of June, 2016
Food datasets
57
Food256 - 25.600 images (100 images/class)
Classes: 256
Food101 – 101.000 images (1000 images/class)
Classes: 101
Food101+FoodCAT: 146.392 (101.000+45.392)
Classes: 131
EgocentricFood: 5038 images
Classes: 9
22:55AMiTANS’16, Albena, 26 of June, 2016
Food localization and recognition
58
General scheme of our food localization and recognition proposal 22:55AMiTANS’16, Albena, 26 of June, 2016
Food localization
Food
Non Food
...
w1
w2
wn
G
oogleNet
Softm
ax
G
AP
inception4eoutput
Deep
Convolution
X
FAM
Bounding
Box
G
eneration
59
Examples of localization and recognition on UECFood256 (top) and EgocentricFood (bottom). Ground
truth is shown in green and our method in blue.
22:55AMiTANS’16, Albena, 26 of June, 2016
Image Input
Foodness Map
Extraction
Food Detection CNN
Food Recognition CNN
Food Type
Recognition
Apple
Strawberry
Food recognition
Results: TOP-1 74.7%
TOP-5 91.6%
SoA (Bossard,2014): TOP-1 56,4%22:55AMiTANS’16, Albena, 26 of June, 2016
60
Demo
61
22:55AMiTANS’16, Albena, 26 of June, 2016
Food environment classification
62
Bakery
Banquet hall
Bar
Butcher shop
Cafetería
Ice cream parlor
Kitchen
Kitchenette
Market
Pantry
Picnic Area
Restaurant
Restaurant Kitchen
Restaurant Patio
Supermarket
Candy store
Coffee shop
Dinette
Dining room
Food court
Galley
Classification results:
0.92 - Food-related vs. Non-food-related
0.68 - 22 classes of Food-related categories
22:55AMiTANS’16, Albena, 26 of June, 2016
Index
 Motivation
 Learning and Deep learning
 Deep learning for food analysis
 Lifelogging
63
22:55AMiTANS’16, Albena, 26 of June, 2016
Wearable cameras and the life-logging trend
64
Shipments of wearable computing devices worldwide by
category from 2013 to 2015 (in millions)
22:55AMiTANS’16, Albena, 26 of June, 2016
Life-logging data
 What we have:
22:55
65
AMiTANS’16, Albena, 26 of June, 2016
Wealth of life-logging data
 We propose an energy-based approach for motion-based event
segmentation of life-logging sequences of low temporal
resolution
 - The segmentation is reached integrating different kind of
image features and classifiers into a graph-cut framework to
assure consistent sequence treatment.
22:55AMiTANS’16, Albena, 26 of June, 2016
66
Complete dataset of a day captured with SenseCam (more than 4,100 images
Choice of devise depends on:
1) where they are set: a hung up camera has
the advantage that is considered more
unobtrusive for the user, or
2) their temporal resolution: a camera with a
low fps will capture less motion information,
but we will need to process less data.
We chose a SenseCam or Narrative - cameras
hung on the neck or pinned on the dress that
capture 2-4 fps.
Or the hell of life-logging data
Visual Life-logging data
Events to be extracted from life-logging images
67
The camera captures up to 2000 images per day, around 100.000 images per month. Applying Computer Vision
algorithms we are able to extract the diary of the person:
- Activities he/she has done
- Interactions he/she has participated
- Events he/she has taken part
- Duties he/she has performed
- Environments and places he/she visited, etc.
22:55AMiTANS’16, Albena, 26 of June, 2016
Towards healthy habits
Towards visualizing summarized lifestyle data to ease the management of the user’s
healthy habits (sedentary lifestyles, nutritional activity, etc.).
22:55AMiTANS’16, Albena, 26 of June, 2016
68
Conclusions
 Healthy habits – one of the main health concern for people, society,
and governments
 Deep learning – a technology that “came to stay”
 A new technological trend with huge power
 Specially useful for food recognition and analysis
 Lifelogging – a unexplored technology that hides big potential to help
people monitor and describe their behaviour and thus improve their
lifestyle.
69
22:55AMiTANS’16, Albena, 26 of June, 2016
22:55
70
AMiTANS’16, Albena, 26 of June, 2016
Deep learning applications
71
22:55AMiTANS’16, Albena, 26 of June, 2016

More Related Content

What's hot

What's hot (20)

Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-gInternet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
 
Wireless Sensor Networks ppt
Wireless Sensor Networks pptWireless Sensor Networks ppt
Wireless Sensor Networks ppt
 
Back propagation
Back propagationBack propagation
Back propagation
 
Principal component analysis
Principal component analysisPrincipal component analysis
Principal component analysis
 
Color Image Processing: Basics
Color Image Processing: BasicsColor Image Processing: Basics
Color Image Processing: Basics
 
ML - Simple Linear Regression
ML - Simple Linear RegressionML - Simple Linear Regression
ML - Simple Linear Regression
 
3.7 outlier analysis
3.7 outlier analysis3.7 outlier analysis
3.7 outlier analysis
 
Detection of plant diseases
Detection of plant diseasesDetection of plant diseases
Detection of plant diseases
 
Cnn
CnnCnn
Cnn
 
implementation and design of 32-bit adder
implementation and design of 32-bit adderimplementation and design of 32-bit adder
implementation and design of 32-bit adder
 
Edge detection
Edge detectionEdge detection
Edge detection
 
Dimensionality Reduction
Dimensionality ReductionDimensionality Reduction
Dimensionality Reduction
 
Linear discriminant analysis
Linear discriminant analysisLinear discriminant analysis
Linear discriminant analysis
 
IOT and Characteristics of IOT
IOT and  Characteristics of IOTIOT and  Characteristics of IOT
IOT and Characteristics of IOT
 
Sensors in IOT
Sensors in IOTSensors in IOT
Sensors in IOT
 
IoT Enabling Technologies
IoT Enabling TechnologiesIoT Enabling Technologies
IoT Enabling Technologies
 
K Nearest Neighbors
K Nearest NeighborsK Nearest Neighbors
K Nearest Neighbors
 
Half adder and full adder
Half adder and full adderHalf adder and full adder
Half adder and full adder
 
Unit 2,3,4 _ Internet of Things A Hands-On Approach (Arshdeep Bahga, Vijay Ma...
Unit 2,3,4 _ Internet of Things A Hands-On Approach (Arshdeep Bahga, Vijay Ma...Unit 2,3,4 _ Internet of Things A Hands-On Approach (Arshdeep Bahga, Vijay Ma...
Unit 2,3,4 _ Internet of Things A Hands-On Approach (Arshdeep Bahga, Vijay Ma...
 
IoT Security
IoT SecurityIoT Security
IoT Security
 

Viewers also liked

The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...
The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...
The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...Francois Stepman
 
Deep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingDeep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingGrigory Sapunov
 
Food Analysis Quality Control
Food Analysis Quality ControlFood Analysis Quality Control
Food Analysis Quality ControlVedpal Yadav
 
Importance of food quality and nutritional analysis
Importance of food quality and nutritional analysisImportance of food quality and nutritional analysis
Importance of food quality and nutritional analysisPoshadri Achinna
 
FAWIRA: Work Package2 - Analysis of food, agriculture and water research an...
FAWIRA: Work Package2  - Analysis of food,  agriculture and water research an...FAWIRA: Work Package2  - Analysis of food,  agriculture and water research an...
FAWIRA: Work Package2 - Analysis of food, agriculture and water research an...INRA Algérie
 
Adulterants in food stuffs by siddharth
Adulterants in food stuffs by  siddharthAdulterants in food stuffs by  siddharth
Adulterants in food stuffs by siddharthPalak Sinha
 
INTERNAL ANALYSIS OF FOOD BAZAAR
INTERNAL ANALYSIS OF FOOD BAZAARINTERNAL ANALYSIS OF FOOD BAZAAR
INTERNAL ANALYSIS OF FOOD BAZAARpriyaranjan
 
Hazard analysis and food control
Hazard analysis and food controlHazard analysis and food control
Hazard analysis and food controlMa E.C.C.
 
Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...
Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...
Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...SYED ASSIM HAQ
 
TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習Mark Chang
 
Lifecycle nutrition: Pregnancy and Lactation
Lifecycle nutrition: Pregnancy and LactationLifecycle nutrition: Pregnancy and Lactation
Lifecycle nutrition: Pregnancy and LactationHelen Corless
 
Indian Processed Food Industry Analysis
Indian Processed Food Industry AnalysisIndian Processed Food Industry Analysis
Indian Processed Food Industry AnalysisNikhil Saraf
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesHJ van Veen
 
TensorFlow 深度學習講座
TensorFlow 深度學習講座TensorFlow 深度學習講座
TensorFlow 深度學習講座Mark Chang
 
Recent Development In Halal Food Analysis
Recent Development In Halal Food AnalysisRecent Development In Halal Food Analysis
Recent Development In Halal Food AnalysisIslamiculture
 
Quality control techniques for food safety
Quality control techniques for food safety Quality control techniques for food safety
Quality control techniques for food safety Jithin Mj
 
Physiological changes during pregnancy
Physiological changes during pregnancyPhysiological changes during pregnancy
Physiological changes during pregnancyNaila Memon
 
Packaging & labeling in food industries
Packaging & labeling in food industriesPackaging & labeling in food industries
Packaging & labeling in food industriesnaveenaugust
 

Viewers also liked (20)

The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...
The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...
The Laboratory of Food Analysis at the Faculty of Pharmaceutical Sciences (UG...
 
Deep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingDeep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image Processing
 
Food Analysis Quality Control
Food Analysis Quality ControlFood Analysis Quality Control
Food Analysis Quality Control
 
Importance of food quality and nutritional analysis
Importance of food quality and nutritional analysisImportance of food quality and nutritional analysis
Importance of food quality and nutritional analysis
 
FAWIRA: Work Package2 - Analysis of food, agriculture and water research an...
FAWIRA: Work Package2  - Analysis of food,  agriculture and water research an...FAWIRA: Work Package2  - Analysis of food,  agriculture and water research an...
FAWIRA: Work Package2 - Analysis of food, agriculture and water research an...
 
Adulterants in food stuffs by siddharth
Adulterants in food stuffs by  siddharthAdulterants in food stuffs by  siddharth
Adulterants in food stuffs by siddharth
 
Risk Analysis in Food - Bangladesh Experience
Risk Analysis in Food - Bangladesh ExperienceRisk Analysis in Food - Bangladesh Experience
Risk Analysis in Food - Bangladesh Experience
 
INTERNAL ANALYSIS OF FOOD BAZAAR
INTERNAL ANALYSIS OF FOOD BAZAARINTERNAL ANALYSIS OF FOOD BAZAAR
INTERNAL ANALYSIS OF FOOD BAZAAR
 
Hazard analysis and food control
Hazard analysis and food controlHazard analysis and food control
Hazard analysis and food control
 
Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...
Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...
Trophic ecology of fishes,polyculture, fish food analysis and fish deformitie...
 
TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習TensorFlow 深度學習快速上手班--機器學習
TensorFlow 深度學習快速上手班--機器學習
 
Lifecycle nutrition: Pregnancy and Lactation
Lifecycle nutrition: Pregnancy and LactationLifecycle nutrition: Pregnancy and Lactation
Lifecycle nutrition: Pregnancy and Lactation
 
Indian Processed Food Industry Analysis
Indian Processed Food Industry AnalysisIndian Processed Food Industry Analysis
Indian Processed Food Industry Analysis
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar Dresses
 
Introduction to pattern recognition
Introduction to pattern recognitionIntroduction to pattern recognition
Introduction to pattern recognition
 
TensorFlow 深度學習講座
TensorFlow 深度學習講座TensorFlow 深度學習講座
TensorFlow 深度學習講座
 
Recent Development In Halal Food Analysis
Recent Development In Halal Food AnalysisRecent Development In Halal Food Analysis
Recent Development In Halal Food Analysis
 
Quality control techniques for food safety
Quality control techniques for food safety Quality control techniques for food safety
Quality control techniques for food safety
 
Physiological changes during pregnancy
Physiological changes during pregnancyPhysiological changes during pregnancy
Physiological changes during pregnancy
 
Packaging & labeling in food industries
Packaging & labeling in food industriesPackaging & labeling in food industries
Packaging & labeling in food industries
 

Similar to Deep Learning Food Analysis

Large Scale Recommendation: a view from the Trenches
Large Scale Recommendation: a view from the TrenchesLarge Scale Recommendation: a view from the Trenches
Large Scale Recommendation: a view from the TrenchesAnne-Marie Tousch
 
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA ijscai
 
Essential econometrics for data scientists
Essential econometrics for data scientistsEssential econometrics for data scientists
Essential econometrics for data scientistsBenjamin Skrainka
 
Comparative Study of Data Mining Classification Algorithms in Heart Disease P...
Comparative Study of Data Mining Classification Algorithms in Heart Disease P...Comparative Study of Data Mining Classification Algorithms in Heart Disease P...
Comparative Study of Data Mining Classification Algorithms in Heart Disease P...paperpublications3
 
Preserving the currency of analytics outcomes over time through selective re-...
Preserving the currency of analytics outcomes over time through selective re-...Preserving the currency of analytics outcomes over time through selective re-...
Preserving the currency of analytics outcomes over time through selective re-...Paolo Missier
 
New Perspectives in Scientific Publishing
New Perspectives in Scientific PublishingNew Perspectives in Scientific Publishing
New Perspectives in Scientific PublishingAlexander Grossmann
 
Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...
Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...
Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...Petia Radeva
 
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATAA BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATAIJSCAI Journal
 
Leibniz: A Digital Scientific Notation
Leibniz: A Digital Scientific NotationLeibniz: A Digital Scientific Notation
Leibniz: A Digital Scientific Notationkhinsen
 
The data, they are a-changin’
The data, they are a-changin’The data, they are a-changin’
The data, they are a-changin’ Paolo Missier
 
A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data
A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data
A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data ijscai
 
Paper multi-modal biometric system using fingerprint , face and speech
Paper   multi-modal biometric system using fingerprint , face and speechPaper   multi-modal biometric system using fingerprint , face and speech
Paper multi-modal biometric system using fingerprint , face and speechAalaa Khattab
 
PSY520 – Module 7Answer SheetSubmit your answers in the .docx
PSY520 – Module 7Answer SheetSubmit your answers in the .docxPSY520 – Module 7Answer SheetSubmit your answers in the .docx
PSY520 – Module 7Answer SheetSubmit your answers in the .docxwoodruffeloisa
 
An application of artificial intelligent neural network and discriminant anal...
An application of artificial intelligent neural network and discriminant anal...An application of artificial intelligent neural network and discriminant anal...
An application of artificial intelligent neural network and discriminant anal...Alexander Decker
 

Similar to Deep Learning Food Analysis (20)

Large Scale Recommendation: a view from the Trenches
Large Scale Recommendation: a view from the TrenchesLarge Scale Recommendation: a view from the Trenches
Large Scale Recommendation: a view from the Trenches
 
Nursing research
Nursing researchNursing research
Nursing research
 
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
 
Essential econometrics for data scientists
Essential econometrics for data scientistsEssential econometrics for data scientists
Essential econometrics for data scientists
 
Comparative Study of Data Mining Classification Algorithms in Heart Disease P...
Comparative Study of Data Mining Classification Algorithms in Heart Disease P...Comparative Study of Data Mining Classification Algorithms in Heart Disease P...
Comparative Study of Data Mining Classification Algorithms in Heart Disease P...
 
Pride Cluster 062016 Update
Pride Cluster 062016 UpdatePride Cluster 062016 Update
Pride Cluster 062016 Update
 
Preserving the currency of analytics outcomes over time through selective re-...
Preserving the currency of analytics outcomes over time through selective re-...Preserving the currency of analytics outcomes over time through selective re-...
Preserving the currency of analytics outcomes over time through selective re-...
 
New Perspectives in Scientific Publishing
New Perspectives in Scientific PublishingNew Perspectives in Scientific Publishing
New Perspectives in Scientific Publishing
 
Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...
Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...
Can Deep Learning and Egocentric Vision for Visual Lifelogging help us eat be...
 
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATAA BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
A BINARY BAT INSPIRED ALGORITHM FOR THE CLASSIFICATION OF BREAST CANCER DATA
 
Building the next generation of statistical tools for outbreak response using R
Building the next generation of statistical tools for outbreak response using RBuilding the next generation of statistical tools for outbreak response using R
Building the next generation of statistical tools for outbreak response using R
 
Leibniz: A Digital Scientific Notation
Leibniz: A Digital Scientific NotationLeibniz: A Digital Scientific Notation
Leibniz: A Digital Scientific Notation
 
The data, they are a-changin’
The data, they are a-changin’The data, they are a-changin’
The data, they are a-changin’
 
Shockomics milano april_2016_v2
Shockomics milano april_2016_v2Shockomics milano april_2016_v2
Shockomics milano april_2016_v2
 
A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data
A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data
A Binary Bat Inspired Algorithm for the Classification of Breast Cancer Data
 
Paper multi-modal biometric system using fingerprint , face and speech
Paper   multi-modal biometric system using fingerprint , face and speechPaper   multi-modal biometric system using fingerprint , face and speech
Paper multi-modal biometric system using fingerprint , face and speech
 
PSY520 – Module 7Answer SheetSubmit your answers in the .docx
PSY520 – Module 7Answer SheetSubmit your answers in the .docxPSY520 – Module 7Answer SheetSubmit your answers in the .docx
PSY520 – Module 7Answer SheetSubmit your answers in the .docx
 
An application of artificial intelligent neural network and discriminant anal...
An application of artificial intelligent neural network and discriminant anal...An application of artificial intelligent neural network and discriminant anal...
An application of artificial intelligent neural network and discriminant anal...
 
QMC: Transition Workshop - Selected Highlights from the Probabilistic Numeric...
QMC: Transition Workshop - Selected Highlights from the Probabilistic Numeric...QMC: Transition Workshop - Selected Highlights from the Probabilistic Numeric...
QMC: Transition Workshop - Selected Highlights from the Probabilistic Numeric...
 
UNIT 1_2.ppt
UNIT 1_2.pptUNIT 1_2.ppt
UNIT 1_2.ppt
 

Recently uploaded

Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxLoriGlavin3
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 

Recently uploaded (20)

Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 

Deep Learning Food Analysis

  • 1.  Deep Learning for Food Analysis Petia Radeva www.cvc.uab.es/~petia Computer Vision at UB (CVUB), Universitat de Barcelona & Medical Imaging Laboratory, Computer Vision Center
  • 2. Index  Motivation  Learning and Deep learning  Deep learning for food analysis  Lifelogging 2 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 3. Metabolic diseases and health 3 22:55AMiTANS’16, Albena, 26 of June, 2016  4.2 million die of chronic diseases in Europe (diabetes or cancer) linked to lack of physical activities and unhealthy diet.  Physical activities can increase lifespan by 1.5-3.7 years.  Obesity is a chronic disease associated with huge economic, social and personal costs.  Risk factors for cancers, cardiovascular and metabolic disorders and leading causes of premature mortality worldwide.
  • 4. Health and medical care  Today, 88% of U.S. healthcare dollars are spent on medical care – access to physicians, hospitals, procedures, drugs, etc.  However, medical care only accounts for approximately 10% of a person’s health.  Approximately half the decline in U.S. Deaths from coronary heart disease from 1980 through 2000 may be attributable to reductions in major risk factors (systolic blood pressure, smoking, physical inactivity). 4 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 5. Health and medical care Recent data shows evidence of stagnation that may be explained by the increases in obesity and diabetes prevalence. Healthcare resources and dollars must now be dedicated to improving lifestyle and behavior. 5 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 6. Why food analysis?  Today, measuring physical activities is not a problem.  But what about food and nutrition?  Nutritional health apps are based on food diaries 6 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 7. Two main questions?  What we eat?  Automatic food recognition vs. Food diaries  And how we eat?  Automatic eating pattern extraction – when, where, how, how long, with whom, in which context?  Lifelogging 7 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 8. Index  Motivation  Learning and Deep learning  Deep learning for food analysis  Lifelogging 8 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 9. Why “Learn”?  Machine learning consists of:  Developing models, methods and algorithms to make computers learn i.e. take decision.  Training from big amount of example data.  Learning is used when:  Humans are unable to explain their expertise (speech recognition)  Human expertise does not exist (navigating on Mars),  Solution changes in time (routing on a computer network)  Solution needs to be adapted to particular cases (user biometrics)  Data is cheap and abundant (data warehouses, data marts); knowledge is expensive and scarce.  Example in retail: Customer transactions to consumer behavior: People who bought “Da Vinci Code” also bought “The Five People You Meet in Heaven” (www.amazon.com)  Build a model that is a good and useful approximation to the data. 9 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 10. Growth of Machine Learning  This trend is accelerating due to:  Big data and data science today are a reality  Improved data capture, networking, faster computers  New sensors / IO devices / Internet of Things  Software too complex to write by hand  Demand for self-customization to user  It turns out to be difficult to extract knowledge from human expertsfailure of expert systems in the 1980’s.  Improved machine learning algorithms AMiTANS’16, Albena, 26 of June, 2016 10 22:55
  • 11. 22:55AMiTANS’16, Albena, 26 of June, 2016 11
  • 14. Formalization of learning  Consider:  training examples: D= {z1, z2, .., zn} with the zi being examples sampled from an unknown process P(Z);  a model f and a loss functional L(f,Z) that returns a real-valued scalar. Minimize the expected value of L(f,Z) under the unknown generating process P(Z).  Supervised Learning: each example is an (input,target) pair: Z=(X,Y)  classification: Y is a finite integer (e.g. a symbol) corresponding to a class index, and we often take as loss function the negative conditional log-likelihood, with the interpretation that fi(X) estimates P(Y=i|X): L(f,(X,Y)) = -log fi(X), where fi(X)>=0, Σi fi(X) = 1. 14 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 15. Classification/Recognition Is this an urban or rural area? Input: x Output: y  {-1,+1} From: M. Pawan Kumar Which city is this? Output: y  {1,2,…,C} Binary classification Multi-class classification 22:55AMiTANS’16, Albena, 26 of June, 2016 15
  • 16. Object Detection and segmentation Where is the object in the image? Output: y  {Pixels} From: M. Pawan Kumar What is the semantic class of each pixel? Output: y  {1,2,…,C}|Pixels| car road grass treesky 22:55AMiTANS’16, Albena, 26 of June, 2016 16
  • 17. A Simplified View of the Pipeline Input x Features Φ(x) Scores f(Φ(x),y) Extract Features Compute Scores maxy f(Φ(x),y)Prediction y(f) Learn f From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016 17
  • 18. Learning Objective Data distribution P(x,y) Prediction f* = argminf EP(x,y) Error(y(f),y) Ground Truth Measure of prediction quality (error, loss) Distribution is unknown Expectation over data distribution From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016 18
  • 19. Learning Objective Training data {(xi,yi), i = 1,2,…,n} Prediction f* = argminf EP(x,y) Error(y(f),y) Ground Truth Measure of prediction quality Expectation over data distribution From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016 19
  • 20. Learning Objective Training data {(xi,yi), i = 1,2,…,n} Prediction f* = argminf Σi Error(yi(f),yi) Ground Truth Measure of prediction quality Expectation over empirical distribution Finite samples From: M. Pawan Kumar22:55AMiTANS’16, Albena, 26 of June, 2016 20
  • 21. The problem of image classification 21 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 22. Dual representation of images as points/vectors 22 22:55 AMiTANS’16, Albena, 26 of June, 2016 32x32x3 D vector Each image of M rows by N columns by C channels ( 3 for color images) can be considered as a vector/point in RMxNxC and viceversa.
  • 23. Linear Classier and key classification components 22:55 23 Given two classes how to learn a hyperplane to separate them? To find the hyperplane we need to specify : • Score function • Loss function • Optimization AMiTANS’16, Albena, 26 of June, 2016
  • 24. Interpreting a linear classifier 24 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016 32x32x3 D vector
  • 25. General learning pipeline 25 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016 Training consists of constructing the prediction model f according to a training set.
  • 26. The problem of image classification 26 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 27. Parametric approach: linear classifier 27 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016 Score function:
  • 28. Loss function/optimization 28 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016 The score function
  • 29. Image classification 29 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 30. Loss function and optimisation  Question: if you were to assign a single number to how unhappy you are with these scores, what would you do? 22:55 30 Question : Given the score and the loss function, how to find the parameters W? AMiTANS’16, Albena, 26 of June, 2016
  • 31. Interpreting a linear classifier 31 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016 10x3072
  • 32. Why is a CNN doing deep learning? 32 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016 where fi=Σjwij * xj w1n f1 f2 fm x1 x2 xn w11 w12
  • 33. Activation functions of NN 33 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 34. Setting the number of layers and their size 34 - Neurons arranged into fully-connected layers - Bigger = better (but might have to regularize more strongly). - How many parameters to learn? From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 35. Why a CNN is neural network? 35 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 36. Architecture of neural networks 22:55 36 Modern CNNs: ~10 million neurons Human visual cortex: ~5 billion neurons AMiTANS’16, Albena, 26 of June, 2016
  • 37. Activation functions of NN 37 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 38. What is it a Convolutional Neural Network? 22:55 38 AMiTANS’16, Albena, 26 of June, 2016
  • 39. Convolutional and Max-pooling layer 22:55 39 Convolutional layer Max-pool layer
  • 40. How does the CNN work? 22:55 40 AMiTANS’16, Albena, 26 of June, 2016
  • 41. Example architecture 22:55 41 The trick is to train the weights such that when the network sees a picture of a truck, the last layer will say “truck”. AMiTANS’16, Albena, 26 of June, 2016
  • 42. Training a CNN 22:55AMiTANS’16, Albena, 26 of June, 2016 42 The process of training a CNN consists of training all hyperparameters: convolutional matrices and weights of the fully connected layers. - Several millions pf parameters!!!
  • 44. Neural network training 44 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson Using the chain rule, optimize the parameters, W of the neural network by gradient descent and backpropagation. 22:55AMiTANS’16, Albena, 26 of June, 2016 Optimization consists of training severalmillions of parameters!
  • 45. Monitoring loss and accuracy 22:55 45 Looks linear? Learning rate too low! Decreases too slowly? Learning rate too high. Looks too noisy? Increases the batch size. Big gap? - you're overfitting, increase regularization! AMiTANS’16, Albena, 26 of June, 2016
  • 46. Transfer learning 46 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 48. 1001 benefits of CNN  Transfer learning: Fine tunning for object recognition  Replace and retrain the classier on top of the ConvNet  Fine-tune the weights of the pre-trained network by continuing the backpropagation  Feature extraction by CNN  Object detectiion  Object segmentation  Image similarity and matching by CNN 22:55 48 Convolutional Neural Networks (4096 Features)AMiTANS’16, Albena, 26 of June, 2016
  • 49. ConvNets are everywhere 49 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 50. ConvNets are everywhere 50 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 51. ConvNets are everywhere 51 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 52. ConvNets are everywhere 52 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 53. ConvNets are everywhere 53 From: Fei-Fei Li & Andrej Karpathy & Justin Johnson22:55AMiTANS’16, Albena, 26 of June, 2016
  • 54. Index  Motivation  Learning and Deep learning  Deep learning for food analysis  Lifelogging 54 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 55. Automatic food analysis 55 Can we automatically recognize food? • To detect every instance of a dish in all of its variants, shapes and positions and in a large number of images. The main problems that arise are: • Complexity and variability of the data. • Huge amounts of data to analyse. 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 56. Automatic Food Analysis  Food detection  Food recognition  Food environment recognition  Eating pattern extraction 56 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 57. Food datasets 57 Food256 - 25.600 images (100 images/class) Classes: 256 Food101 – 101.000 images (1000 images/class) Classes: 101 Food101+FoodCAT: 146.392 (101.000+45.392) Classes: 131 EgocentricFood: 5038 images Classes: 9 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 58. Food localization and recognition 58 General scheme of our food localization and recognition proposal 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 59. Food localization Food Non Food ... w1 w2 wn G oogleNet Softm ax G AP inception4eoutput Deep Convolution X FAM Bounding Box G eneration 59 Examples of localization and recognition on UECFood256 (top) and EgocentricFood (bottom). Ground truth is shown in green and our method in blue. 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 60. Image Input Foodness Map Extraction Food Detection CNN Food Recognition CNN Food Type Recognition Apple Strawberry Food recognition Results: TOP-1 74.7% TOP-5 91.6% SoA (Bossard,2014): TOP-1 56,4%22:55AMiTANS’16, Albena, 26 of June, 2016 60
  • 62. Food environment classification 62 Bakery Banquet hall Bar Butcher shop Cafetería Ice cream parlor Kitchen Kitchenette Market Pantry Picnic Area Restaurant Restaurant Kitchen Restaurant Patio Supermarket Candy store Coffee shop Dinette Dining room Food court Galley Classification results: 0.92 - Food-related vs. Non-food-related 0.68 - 22 classes of Food-related categories 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 63. Index  Motivation  Learning and Deep learning  Deep learning for food analysis  Lifelogging 63 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 64. Wearable cameras and the life-logging trend 64 Shipments of wearable computing devices worldwide by category from 2013 to 2015 (in millions) 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 65. Life-logging data  What we have: 22:55 65 AMiTANS’16, Albena, 26 of June, 2016
  • 66. Wealth of life-logging data  We propose an energy-based approach for motion-based event segmentation of life-logging sequences of low temporal resolution  - The segmentation is reached integrating different kind of image features and classifiers into a graph-cut framework to assure consistent sequence treatment. 22:55AMiTANS’16, Albena, 26 of June, 2016 66 Complete dataset of a day captured with SenseCam (more than 4,100 images Choice of devise depends on: 1) where they are set: a hung up camera has the advantage that is considered more unobtrusive for the user, or 2) their temporal resolution: a camera with a low fps will capture less motion information, but we will need to process less data. We chose a SenseCam or Narrative - cameras hung on the neck or pinned on the dress that capture 2-4 fps. Or the hell of life-logging data
  • 67. Visual Life-logging data Events to be extracted from life-logging images 67 The camera captures up to 2000 images per day, around 100.000 images per month. Applying Computer Vision algorithms we are able to extract the diary of the person: - Activities he/she has done - Interactions he/she has participated - Events he/she has taken part - Duties he/she has performed - Environments and places he/she visited, etc. 22:55AMiTANS’16, Albena, 26 of June, 2016
  • 68. Towards healthy habits Towards visualizing summarized lifestyle data to ease the management of the user’s healthy habits (sedentary lifestyles, nutritional activity, etc.). 22:55AMiTANS’16, Albena, 26 of June, 2016 68
  • 69. Conclusions  Healthy habits – one of the main health concern for people, society, and governments  Deep learning – a technology that “came to stay”  A new technological trend with huge power  Specially useful for food recognition and analysis  Lifelogging – a unexplored technology that hides big potential to help people monitor and describe their behaviour and thus improve their lifestyle. 69 22:55AMiTANS’16, Albena, 26 of June, 2016

Editor's Notes

  1. Face recognition: Pose, lighting, occlusion (glasses, beard), make-up, hair style Character recognition: Different handwriting styles. Speech recognition: Temporal dependency. Use of a dictionary or the syntax of the language. Sensor fusion: Combine multiple modalities; eg, visual (lip image) and acoustic for speech Medical diagnosis: From symptoms to illnesses Web Advertizing: Predict if a user clicks on an ad on the Internet.
  2. Other methods also use unsupervised pre-training to structure a neural network, making it first learn generally useful feature detectors. Then the network is trained further by supervised back-propagation to classify labeled data. The deep model of Hinton et al. (2006) involves learning the distribution of a high level representation using successive layers of binary or real-valued latent variables. It uses a restricted Boltzmann machine to model each new layer of higher level features. Each new layer guarantees an increase on the lower-bound of the log likelihood of the data, thus improving the model, if trained properly. Once sufficiently many layers have been learned the deep architecture may be used as a generative model by reproducing the data when sampling down the model (an "ancestral pass") from the top level feature activations.[8] Hinton reports that his models are effective feature extractors over high-dimensional, structured data.[9] Natural Language Processing which is used heavily in language conversion in chat rooms or processing text from where human speeches. Optical Character Recognition which is scanning of images. It's gaining traction lately to read an image and extract text out of it and correlate to the objects found on image Speech Recognition applications like Siri or Cortana needs no introduction Artificial Intelligence induction to different robots for automating at least a minute level of tasks a human can do. We want them to be a little smarter. Drug discovery though medical imaging-based diagnosis using deep learning. It's kind of in early stages now. Check Butterfly Network for the work they are doing. CRM needs for companies are growing day by day. There are hundreds of thousands of companies around the globe from small to big companies who wants to know their potential customers. Deep Learning has provided some outstanding results. Check for companies like RelateIQ (product) who has seen astounding success of using Machine Learning in this area.
  3. Exponential linear units- ELU all benefits of relu, does not die, closer to zero meanoutputs, but computation requires exp()
  4. Medical applications - there are tremendous advances in robotic surgery that relies on extremely sensitive tactile equipment. However, if a doctor can advise a robot to "move a fraction of a millimeter to the left of the clavicle" they could potentially gain more control by directing the robot via full understood voice control. Automotive - we are already seeing self driving cars; deep learning will possibly integrate into automated driving systems to detect and interpret sights and sounds that might be beyond the capacity of humans. Military - drones are particularly well suited to deep learning. Surveillance - here too drones will play a role, but the idea of computers that are able to sense and interpret with a human-like degree of accuracy will change the way in which surveillance is done.