Object recognition is a hugely researched domain that employs methods derived from mathematics,physics and biology. This thesis combines the approaches for object classification that base on two features – color and shape. Color is represented by color histograms and shape by skeletal graphs. Four hybrids are proposed which combine those approaches in different manners and the hybrids are then tested to find out which of them gives best results.
Contents
1 INTRODUCTION
2 OBJECT RECOGNITION – CURRENT STATE OF THE ART
2.1 THE OVERALL APPROACH
2.2 REPRESENTING AND MATCHING OBJECTS BY COLOR
2.3 REPRESENTING AND MATCHING OBJECTS BY SHAPE
3 PROPOSED APPROACH
3.1 ALGORITHMS USED FOR HISTOGRAMS
3.2 ALGORITHMS USED FOR GRAPHS
3.3 MODELBASE, HYBRIDS AND THE APPLICATION
4 RESULTS AND DISCUSSION
4.1 SYSTEM PARAMETERS AND EXPERIMENT DESCRIPTION
4.2 PARAMETER TESTS
5 SUMMARY
6 BIBLIOGRAPHY
APPENDIX A – THE DICTIONARY
APPENDIX B – THE GALLERY
Author: Radoslaw Cichocki
Source: Blekinge Institute of Technology
Download URL 2: Visit Now