Recognition of two-dimensional objects using geometric constraints based on a modified genetic algorithm

The aim of the research work is to develop a recognition system for identifying and localising of a two- dimensional object from a scene image acquired using a standard CCD camera. Before proposing an effective matching paradigm, a survey on 2D object recognition systems is conducted to identify...

Full description

Saved in:
Bibliographic Details
Main Author: Lim, Swee Kim.
Other Authors: Wong, Kok Cheong
Format: Theses and Dissertations
Language:English
Published: 2009
Subjects:
Online Access:http://hdl.handle.net/10356/20496
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:The aim of the research work is to develop a recognition system for identifying and localising of a two- dimensional object from a scene image acquired using a standard CCD camera. Before proposing an effective matching paradigm, a survey on 2D object recognition systems is conducted to identify their strengths and weaknesses. To accomplish the 2D interpretation problem, a novel matching paradigm based on a modified genetic algorithm (GA) [35] [36] [37] is proposed and implemented for recognising 2D objects subjected to Euclidean transformation, partial occlusion and clusters of irrelevant objects.