Object Categorization Using Genetic Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.8028
- @InProceedings{Korra:2010:ICGEC,
-
author = "Jyothi Korra and Susheela Devi",
-
title = "Object Categorization Using Genetic Programming",
-
booktitle = "Fourth International Conference on Genetic and
Evolutionary Computing (ICGEC 2010)",
-
year = "2010",
-
month = "13-15 " # dec,
-
pages = "297--300",
-
address = "Shenzhen, China",
-
abstract = "In Computer Vision, problem of identifying or
classifying the objects present in an image is called
Object Categorisation. It is challenging problem,
especially when the images have clutter background,
occlusions or different lighting conditions. Many
vision features have been proposed which aid object
categorization even in such adverse conditions. Past
research has shown that, employing multiple features
rather than any single features leads to better
recognition. Multiple Kernel Learning (MKL) framework
has been developed for learning an optimal combination
of features for object categorization. Existing MKL
methods use linear combination of base kernels which
may not be optimal for object categorization.
Real-world object categorisation may need to consider
complex combination of kernels(non-linear) and not only
linear combination. Evolving non-linear functions of
base kernels using Genetic Programming is proposed in
this paper. Experiment results show that non-kernel
generated using genetic programming gives good accuracy
as compared to linear combination of kernels.",
-
keywords = "genetic algorithms, genetic programming, SVM, MKL
method, computer vision, linear combination, linear
combination, multiple kernel learning framework, real
world object categorisation, vision feature, computer
vision, image classification, object detection, support
vector machines",
-
DOI = "doi:10.1109/ICGEC.2010.80",
-
notes = "Caltech-5 Also known as \cite{5715428}",
- }
Genetic Programming entries for
Jyothi Korra
V Susheela Devi
Citations