Real Time Pattern Recognition using Matrox Imaging System

Praveen, N (2009) Real Time Pattern Recognition using Matrox Imaging System. MTech thesis.

[img]
Preview
PDF
2538Kb

Abstract

A primary goal of pattern recognition is to be able to classify data into a set of related elements. Many applications today take advantage of pattern recognition; among them are data mining, face recognition, web searching, robotics and a lot more. Pattern recognition concerning Artificial Intelligence has been in research and development for approximately 50 years. The ability to quickly locate one or more instances of a model in a grey scale image is of importance to industry. The recognition/ localization must be fast and accurate. Two algorithms are employed in this work to achieve fast recognition and localization. Both the algorithm relies on a pyramid representation of both the model image and the search image. Specifically these algorithms are suitable for implementation on a personal computer equipped with an image acquisition board and a camera. Finally, results are given for searches on real images with perspective distortion and the addition of Gaussian noise.

Item Type:Thesis (MTech)
Uncontrolled Keywords:Image segmentation, Pattern recognition
Subjects:Engineering and Technology > Computer and Information Science > Image Processing
Divisions: Engineering and Technology > Department of Electronics and Communication Engineering
ID Code:1393
Deposited By:Praveen N
Deposited On:29 May 2009 09:01
Last Modified:29 May 2009 09:01
Related URLs:
Supervisor(s):Meher, S

Repository Staff Only: item control page