This document outlines a quality control project that uses image processing to identify faulty bolts on a conveyor belt. It includes an overview of the project requirements and specifications, design aspects like the hardware components and software used. Block diagrams and a flowchart illustrate the process workflow. The software implementation section describes various Matlab functions used for image processing tasks like preprocessing, feature extraction and matching. Finally, the document provides a schedule and references.
3. Overview of quality control
System using Image Processing
Quality control Technology involves
Video to frame conversion
Storing features in a database
Using them to identify objects on conveyer belt
Quality control process flow :-
1. Sample Capture – digital camera
2. Feature Extraction – creation of template
3. Template Comparison –
Verification - 1 to 1 comparison
- gives yes/no decision
4. Matching – Uses different matching algorithms
4. Project Requirements :
Input : Image in JPEG format
Intel processor with 128 MB RAM
Hard Disk Space 40 MB
Web Camera
WINDOWS operating system
MATLAB 7.0
5. Specifications
The project developed uses various components.
They are as follows:
Specifications
Microcontroller
PIC18F458
OP-AMP
LM 358
Camera
Webcam
Stepper
Motor driver
ULN 2003
7. 1.Hardware
The main hardware components that are used in this project are as follows:
Hardware Aspect
(a) Microcontroller PIC18F458
(b) OP-AMP LM 358
(c)Camera Webcam
(d) Stepper motor
driver
ULN 2003
8. 2.Software
Three main softwares are used that forms the software
aspect of this project.
They are as given below:
Software Aspect
Matlab Used to write the program code
Flash magic
Used to burn the program in the
microcontroller IC
Proteaus To Create PCB Layout
11. Flowchart
START
Wait until some charector from controller as indication of
object came in front of IR sensor
Take image of Object & subtract backgrond from image
Gray level thresholing for convesion to binary & Adjust some
brightness
Dialate(D) & Erode(E) the image & subtract as(D-E) for
border detection & clear holes
Use sobel function edge detection & extrct properties for
matching ilke Form Factor, Area ,perimeter..
If image is
faulty
Send charector to controller to indicate fauly nuts came ,
oprate soleniod.
14. Various Matlab Functions To Be Used
1.Imresize
B = imresize(A, [mrows ncols]) returns image B that has the
number of rows and columns specified by [mrows ncols].
15. 2.Imadjust
J = imadjust(I,[low_in; high_in],[low_out; high_out]) maps the
values in I to new values in J such that values between low_in
and high_in map to values between low_out and high_out. We
have used an empty matrix ([]) for [low_in high_in] or for
[low_out high_out] to specify the default of [0 1].
16. 3.im2bw
BW = im2bw(I, level) converts the grayscale image I to a binary
image. The output image BW replaces all pixels in the input image
with luminance greater than level with the value 1 (white) and
replaces all other pixels with the value 0 (black). To compute the
level argument, we have used the function graythresh. If the level
is not specified im2bw uses the value 0.5.
17. 4.Dilation Operation (imdilate)
Original Image Dilated Image
In Dilation operation,the value of the output pixel is
the maximum value of all the input pixels
neighbourhood.Dilation process basically expands an
image.
18. 5.Erosion (imerode)
Erosion is opposite to that of dilation. In Erosion operation the
value of output pixel is the minimum value of all the pixels in the
input pixels neighbourhood. Basically, erosion shrinks an image.
Original image Eroded Image
19. 6.Filling up holes (imfill)
Imfill displays the binary image on the screen and lets you
define the region to fill by selecting points interactively by
using the mouse. Binary image must be a 2-D image.
Dilation-erosion Filled Up Image
20. 7.Imclearborder
IM2 = imclearborder(IM,conn) specifies the desired connectivity.
conn can have any scalar values. Imclearborder suppresses
structures that are lighter than their surroundings and that are
connected to the image border. (In other words, use this function
to clear the image border.) IM can be a grayscale or binary image.
The output image, IM2, is grayscale or binary, respectively.
21. 8.Edge Detection (Canny Operator)
It uses a multistage algorithm to detect a wide range of edges in
an image.It is the most powerful edge detector which uses
Gaussian LPF and takes first derivative.The Canny edge
detector uses a filter based on the 1st derivative of a
Gaussian.The image is smoothened using a Gaussian filter.
Original Image Edge detected Image
22. 9.Region Properties (regionprops)
Regionprops computes area, centroid and
Bounding Box. Area scalar actual number of pixels
in the scalar actually returns the distance around the
boundary of a region.
Regionprops computes the perimeter by
calculating the distance between each adjoining pair
of pixels around the border of the region. If the
images contains discontinuity regions,regionprops
returns unexpected result.
23. Results obtained using regionprops
1.For Non-faulty bolt
perimeter is :-
415.5046
Area is :-
360
Form Factor :-
0.0262
Bolt is Not Faulty
24. Results obtained using regionprops
2.For Faulty bolt
perimeter is :-
704.4823
Area is :-
603
Form Factor :-
0.0153
Bolt is Faulty
30. References
Ambarish A. Salodkar and M.M.Khanapurkar “ Recognition of Bolt
and Nut using Image Processing” International Conference on
Emerging Frontiers in Technology for Rural Area (EFITRA) 2012
Teuku Muhammad Johan, Anton Satria Prabuwono “Recognition of
Bolt and Nut using Artificial Neural Network” International
Conference on Emerging Frontiers in Technology for Rural Area
(EFITRA) 2011
Raffaella Mattone, Linda Adduci and Andreas Wolf “On-line
scheduling algorithms for improving performance of pick-and-place
operations on a moving conveyor belt” Proceedings of the 1998
IEEE International Conference on Robotics & Automation Leuven,
Belgium May 1998
31. Schedule for Semester-II
Sr.No. Job Scheduled Date
1. Presentation number 3 before
committee
30/12/2013
2. Verification of Software aspect 12/01/2014
3. Preparation of various layouts 27/01/2014
4. Functional Simulations 02/02/2014
5. Verification of Simulations 15/02/2014
6. Soldering of PCB 30/02/2014
7. Verification of Hardware and
Troubleshooting
15/03/2014
8. Presentation of final project before
committee
31/03/2014