Current learning approaches to computer vision have
mainly focused on low-level image processing and object
recognition, while tending to ignore high-level
processing such as understanding. Here we propose an
approach to object recognition that facilitates the
transition from recognition to understanding. The
proposed approach embraces the synergistic spirit of
soft computing, exploiting the global search powers of
genetic programming to determine fuzzy probabilistic
models. It begins by segmenting the images into regions
using standard image processing approaches, which are
subsequently classified using a discovered fuzzy
Cartesian granule feature classifier. Understanding is
made possible through the transparent and succinct
nature of the discovered models. The recognition of
roads in images is taken as an illustrative problem in
the vision domain. The discovered fuzzy models while
providing high levels of accuracy (97per cent), also
provide understanding of the problem domain through the
transparency of the learnt models. The learning step in
the proposed approach is compared with other techniques
such as decision trees, naive Bayes and neural networks
using a variety of performance criteria such as
accuracy, understandability and efficiency.
%0 Journal Article
%1 2000-shanahan
%A Shanahan, J.
%A Thomas, B.
%A Mirmehdi, M.
%A Martin, T.
%A Campbell, N.
%A Baldwin, J.
%D 2000
%J Journal of Intelligent and Robotic Systems
%K algorithms, genetic programming
%N 4
%P 349--387
%R doi:10.1023/A:1008158907779
%T A Soft Computing Approach to Road Classification
%V 29
%X Current learning approaches to computer vision have
mainly focused on low-level image processing and object
recognition, while tending to ignore high-level
processing such as understanding. Here we propose an
approach to object recognition that facilitates the
transition from recognition to understanding. The
proposed approach embraces the synergistic spirit of
soft computing, exploiting the global search powers of
genetic programming to determine fuzzy probabilistic
models. It begins by segmenting the images into regions
using standard image processing approaches, which are
subsequently classified using a discovered fuzzy
Cartesian granule feature classifier. Understanding is
made possible through the transparent and succinct
nature of the discovered models. The recognition of
roads in images is taken as an illustrative problem in
the vision domain. The discovered fuzzy models while
providing high levels of accuracy (97per cent), also
provide understanding of the problem domain through the
transparency of the learnt models. The learning step in
the proposed approach is compared with other techniques
such as decision trees, naive Bayes and neural networks
using a variety of performance criteria such as
accuracy, understandability and efficiency.
@article{2000-shanahan,
abstract = {Current learning approaches to computer vision have
mainly focused on low-level image processing and object
recognition, while tending to ignore high-level
processing such as understanding. Here we propose an
approach to object recognition that facilitates the
transition from recognition to understanding. The
proposed approach embraces the synergistic spirit of
soft computing, exploiting the global search powers of
genetic programming to determine fuzzy probabilistic
models. It begins by segmenting the images into regions
using standard image processing approaches, which are
subsequently classified using a discovered fuzzy
Cartesian granule feature classifier. Understanding is
made possible through the transparent and succinct
nature of the discovered models. The recognition of
roads in images is taken as an illustrative problem in
the vision domain. The discovered fuzzy models while
providing high levels of accuracy (97per cent), also
provide understanding of the problem domain through the
transparency of the learnt models. The learning step in
the proposed approach is compared with other techniques
such as decision trees, naive Bayes and neural networks
using a variety of performance criteria such as
accuracy, understandability and efficiency.},
abstract-url = {http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000525},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Shanahan, J. and Thomas, B. and Mirmehdi, M. and Martin, T. and Campbell, N. and Baldwin, J.},
biburl = {https://www.bibsonomy.org/bibtex/2ba048139ccccc6e85fbd4cf31cbd1db4/brazovayeye},
doi = {doi:10.1023/A:1008158907779},
interhash = {dd05c04abc5154d1c7f151bb95997e6f},
intrahash = {ba048139ccccc6e85fbd4cf31cbd1db4},
issn = {0921-0296},
journal = {Journal of Intelligent and Robotic Systems},
keywords = {algorithms, genetic programming},
month = {December},
notes = {Further Information.This paper is not on-line, please
contact the author.},
number = 4,
pages = {349--387},
pubtype = {101},
timestamp = {2008-06-19T17:51:33.000+0200},
title = {A Soft Computing Approach to Road Classification},
volume = 29,
year = 2000
}