A Domain Independent Approach to 2D Object Detection
Based on the Neural and Genetic Paradigms
M. Zhang. Department of Computer Science, RMIT University, Melbourne, Victoria, Australia, (August 2000)
Abstract
The development of traditional object detection
systems usually involves a time consuming investigation
of good preprocessing and filtering methods and a
hand-crafting of different programs for the extraction
and selection of important image features in different
problem domains. To avoid these problems, this thesis
describes a domain independent approach to multiple
class, translation and rotation invariant object
detection problems without any preprocessing,
segmentation and specific feature extraction. The
approach is based on learning/adaptive methods --
neural networks, genetic algorithms and genetic
programming. Rather than using...
6th 'a method which uses genetic programming to build
the object detector'. Retina images.
%0 Thesis
%1 mengjie-thesis
%A Zhang, Mengjie
%C Melbourne, Victoria, Australia
%D 2000
%K ANN, algorithms, computer genetic programming, vision
%T A Domain Independent Approach to 2D Object Detection
Based on the Neural and Genetic Paradigms
%U http://citeseer.ist.psu.edu/zhang00domain.html
%X The development of traditional object detection
systems usually involves a time consuming investigation
of good preprocessing and filtering methods and a
hand-crafting of different programs for the extraction
and selection of important image features in different
problem domains. To avoid these problems, this thesis
describes a domain independent approach to multiple
class, translation and rotation invariant object
detection problems without any preprocessing,
segmentation and specific feature extraction. The
approach is based on learning/adaptive methods --
neural networks, genetic algorithms and genetic
programming. Rather than using...
6th 'a method which uses genetic programming to build
the object detector'. Retina images.
@phdthesis{mengjie-thesis,
abstract = {The development of traditional object detection
systems usually involves a time consuming investigation
of good preprocessing and filtering methods and a
hand-crafting of different programs for the extraction
and selection of important image features in different
problem domains. To avoid these problems, this thesis
describes a domain independent approach to multiple
class, translation and rotation invariant object
detection problems without any preprocessing,
segmentation and specific feature extraction. The
approach is based on learning/adaptive methods --
neural networks, genetic algorithms and genetic
programming. Rather than using...
6th 'a method which uses genetic programming to build
the object detector'. Retina images.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Melbourne, Victoria, Australia},
author = {Zhang, Mengjie},
biburl = {https://www.bibsonomy.org/bibtex/2db5de3af6491f85e4c808cd785959612/brazovayeye},
interhash = {21ce9d34ad4826a1ba9c8f3bf5fae6c5},
intrahash = {db5de3af6491f85e4c808cd785959612},
keywords = {ANN, algorithms, computer genetic programming, vision},
month = {August},
school = {Department of Computer Science, RMIT University},
size = {225 pages},
timestamp = {2008-06-19T17:55:31.000+0200},
title = {A Domain Independent Approach to 2{D} Object Detection
Based on the Neural and Genetic Paradigms},
url = {http://citeseer.ist.psu.edu/zhang00domain.html},
year = 2000
}