Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.
RECOGNIZING HANDWRITTEN DIGIT
USING K-NEAREST NEIGHBOUR
CLASSIFIER
By-
Vineet Raj
INTRODUCTION
Handwritten digit recognition is the process of
receiving and correctly interpreting a legible
hand-drawn dig...
APPLICATIONS
• Postal mail sorting
• Courtesy amounts on cheques
• Formation of data entry etc.
Recognition of
legal amoun...
PROBLEM STATEMENT
Given a set of greyscale isolated numerical images taken from
MNIST database.
The objectives are:-
 To ...
LITERATURE SURVEY
 Hand Written Character Recognition using Star-Layered Histogram Features
Stephen Karungaru, Kenji Tera...
We present a versatile technique for the purpose of feature selection and extraction -
Class Dependent Features (CDFs). CD...
EXISTING MODELS
Feature extraction methods
• Star layered histogram feature extraction algorithm
requires thinning operat...
Classification Algorithms
• Linear Classifier
error rate is 12.0%
• Neural Networks
requires thousands of training examp...
PROPOSED MODEL
ISOLATED
NUMERAL IMAGES
FROM MNIST
DATABASE
PRE-PROCESSING
FEATURE
EXTRACTION
CLASSIFICATION
ALGORITHM
The...
REFERENCES
Hand Written Character Recognition using Star-Layered Histogram
Features
Stephen Karungaru, Kenji Terada and M...
Nächste SlideShare
Wird geladen in …5
×

HANDWRITTEN DIGIT RECOGNITION USING k-NN CLASSIFIER

1.597 Aufrufe

Veröffentlicht am

PPT on recognizing handwritten digits using k-Nearest Neighbour classifier

Veröffentlicht in: Ingenieurwesen
  • Als Erste(r) kommentieren

HANDWRITTEN DIGIT RECOGNITION USING k-NN CLASSIFIER

  1. 1. RECOGNIZING HANDWRITTEN DIGIT USING K-NEAREST NEIGHBOUR CLASSIFIER By- Vineet Raj
  2. 2. INTRODUCTION Handwritten digit recognition is the process of receiving and correctly interpreting a legible hand-drawn digit from an input source (paper or photographs) by comparing it with previously trained data.
  3. 3. APPLICATIONS • Postal mail sorting • Courtesy amounts on cheques • Formation of data entry etc. Recognition of legal amounts on bank cheques Currency Recognition Number Plate Recognition House no. Recognition Postal mail sorting
  4. 4. PROBLEM STATEMENT Given a set of greyscale isolated numerical images taken from MNIST database. The objectives are:-  To recognize handwritten digits correctly.  To improve the accuracy of detection.  To develop a method which is independent of digit size and writer style/ink independent.
  5. 5. LITERATURE SURVEY  Hand Written Character Recognition using Star-Layered Histogram Features Stephen Karungaru, Kenji Terada and Minoru Fukumi In this method, a character recognition method using features extracted from a star layered histogram is presented and trained using neural networks. After several image preprocessing steps, the character region is extracted. Its contour is then used to determine the center of gravity (COG). This CoG point is used as the origin to create a histogram using equally spaced lines extending from the CoG to the contour. The first point the line touches the character represents the first layer of the histogram. If the line extension has not reached the region boundary, the next hit represents the second layer of the histogram. This process is repeated until the line touches the boundary of the character’s region. After normalization, these features are used to train a neural network. Result This method achieves an accuracy of about 93% using the MNIST database of handwritten digits.  A Novel Feature Selection and Extraction Technique for Classification
  6. 6. We present a versatile technique for the purpose of feature selection and extraction - Class Dependent Features (CDFs). CDFs identify the features innate to a class and extract them accordingly. The features thus extracted are relevant to the entire class and not just to the individual data item. This paper focuses on using CDFs to improve the accuracy of classification and at the same time control computational expense by tackling the curse of dimensionality. Result- This method achieves an accuracy of about 92%
  7. 7. EXISTING MODELS Feature extraction methods • Star layered histogram feature extraction algorithm requires thinning operation many inner details can not be captured using outer polygons • Class Dependent feature selection and extraction expensive in terms of computation
  8. 8. Classification Algorithms • Linear Classifier error rate is 12.0% • Neural Networks requires thousands of training examples and huge computation time
  9. 9. PROPOSED MODEL ISOLATED NUMERAL IMAGES FROM MNIST DATABASE PRE-PROCESSING FEATURE EXTRACTION CLASSIFICATION ALGORITHM The proposed method uses k-nearest neighbour(k-NN) classification algorithm for classifying the MNIST digit images. Accuracy of about 96% can be achieved. Less number of computations required. No thinning operation required.
  10. 10. REFERENCES Hand Written Character Recognition using Star-Layered Histogram Features Stephen Karungaru, Kenji Terada and Minoru Fukumi A Novel Feature Selection and Extraction Technique for Classification Kratarth Goel, Raunaq Vohra and Ainesh Bakshi Handwritten Digit Recognition Using K-Nearest Neighbour Classifier U Ravi Babu, Dr. Y Venkateswarlu and Aneel Kumar Chintha Y. LeCun, et al., Comparison of learning algorithms for handwritten digit recognition F. Fogelman-Souli e, P. Gallinari (Eds.) Yann LeCun,”THE MNIST database of handwritten digits” Courant Institute, NYU Corinna Cortes, Google Labs, NewYork

×