Machine Vision full report

[manju das]

[attachment=14051]
OUTLINE
Properties of Machine Vision Systems
Methods in Machine Vision
2. Example: Fingerprint Recognition System
Machine Vision System
creates a model of the real world from images
recovers useful information about a scene from its two dimensional projections
A typical control system:
Components of a M.V. system
HARDWARE
SOFTWARE
Optics (lenses, lighting)
Cameras
Interface (frame grabber)
Computer
Application Fields
Medical imaging
Industrial automation
Robotics
Radar Imaging
Forensics
Remote Sensing
Cartography
Character recognition
Machine Vision Stages
Image Formation
Perspective projection
Orthographic projection
Digital Image Representation
Different Sampling Rates
Different Quantization Levels
Image Processing (IP)
Filtering
Smoothing
Thinning
Expending
Shrinking
Compressin
Fundementals
Neigborhood
Histogram: gray levels vs number of pixels
IP Examples (2)
IP Examples (4)
Smoothing
Binary Image Processing
WHY?
better efficiency in acquiring, storage,
processing and transmission
TRESHOLDING
Different tresholds
Region Segmentation
Histogram Based
Edge Detection
Find the curves on the image where rapid changes occur
Pattern Recognition (PR)
Approaches to PR
Statistical
Structural
Neural
3D VISION
Dynamic Vision
Fingerprint Recognition
most precise identification biometric
has many applications
has the largest database
Fingerprint recognition system
Fingerprint Representation
Image Processing & Analysis for Fingerprint Recognition
Pre-Processing
Binarization
search through array pixel by pixel;
if current byte colour value is above threshold then
change value to white;
else
change colour to black
Noise Removal
if the pixel is white and all immediate surrounding pixels are black
then
change pixel to black;
else if the pixel is black and all immediate surrounding pixels are white then
change pixel to white
Pre-Processing(2)
Smoothing
for each pixel do
add the values of surrounding pixels;
divide by the number of surrounding pixels (usually 8 unless
at the edge);
assign current pixel the calculated result;
Thinning