Automatically Evolving Texture Image Descriptors using the Multi-tree Representation in Genetic Programming using Few Instances
Created by W.Langdon from
gp-bibliography.bib Revision:1.7964
- @Article{Al-Sahaf:EC,
-
author = "Harith Al-Sahaf and Ausama Al-Sahaf and Bing Xue and
Mengjie Zhang",
-
title = "Automatically Evolving Texture Image Descriptors using
the Multi-tree Representation in Genetic Programming
using Few Instances",
-
journal = "Evolutionary Computation",
-
year = "2021",
-
volume = "29",
-
number = "3",
-
pages = "331--366",
-
month = "Fall",
-
keywords = "genetic algorithms, genetic programming, ANN, image
descriptor, multi-tree, image classification, feature
extraction",
-
ISSN = "1063-6560",
-
URL = "https://doi.org/10.1162/evco_a_00284",
-
DOI = "doi:10.1162/evco_a_00284",
-
size = "36 pages",
-
abstract = "The performance of image classification is highly
dependent on the quality of the extracted features that
are used to build a model. Designing such features
usually requires prior knowledge of the domain and is
often undertaken by a domain expert who, if available,
is very costly to employ. Automating the process of
designing such features can largely reduce the cost and
efforts associated with this task. Image descriptors,
such as local binary patterns, have emerged in computer
vision, and aim at detecting keypoints, for example,
corners, line-segments, and shapes, in an image and
extracting features from those key points. In this
article, genetic programming (GP) is used to
automatically evolve an image descriptor using only two
instances per class by using a multitree program
representation. The automatically evolved descriptor
operates directly on the raw pixel values of an image
and generates the corresponding feature vector. Seven
well-known datasets were adapted to the few-shot
setting and used to assess the performance of the
proposed method and compared against six handcrafted
and one evolutionary computation-based image descriptor
as well as three convolutional neural network (CNN)
based methods. The experimental results show that the
new method has significantly outperformed the
competitor image descriptors and CNN-based methods.
Furthermore, different patterns have been identified
from analysing the evolved programs.",
- }
Genetic Programming entries for
Harith Al-Sahaf
Ausama Al-Sahaf
Bing Xue
Mengjie Zhang
Citations