Article
Journal/Revue :
International Journal of Applied Metaheuristic Computing (IJAMC)
ISSN : 1947-8291
Publisher :
Informations
Période : April 2018
Volume : 9 Numéro : 2
Pages : 48-71
Détails
A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval
Feature selection is an important pre-processing technique in the pattern recognition domain. This article proposes a hybridization between Genetic Algorithm (GA) and the Linear Discriminant Analysis (LDA) for solving the feature selection problem in Content-Based Image Retrieval (CBIR) applied to dermatological images. In the first step, we preprocess and segment the input image, then we derive color and texture features characterizing healthy skin and the segmented skin lesion. At this stage, a binary GA is used to evolve chromosome subsets whose fitness is evaluated by a Logistic Regression classifier. The optimal identified features are then used to feed LDA for a CBIR system, based on a K-Nearest Neighbor classification. To assess the proposed approach, the authors have opted for a K-fold cross validation method on a database of 1097 images of melanomas and other skin lesions. As a result, the authors obtained a reduced number of features and an improved CBDIR system compared to PCA, LDA and ICA methods.
Texte intégral
ACM :
K. Belattar, S. Mostefai and A. Draa. 2018. A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval. International Journal of Applied Metaheuristic Computing (IJAMC), 9, 2 (April 2018), IGI Global, 48-71. DOI: https://doi.org/10.4018/IJAMC.2018040103.
APA :
Belattar, K., Mostefai, S. & Draa, A. (2018, April). A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval. International Journal of Applied Metaheuristic Computing (IJAMC), 9(2), IGI Global, 48-71. DOI: https://doi.org/10.4018/IJAMC.2018040103
IEEE :
K. Belattar, S. Mostefai and A. Draa, "A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval". International Journal of Applied Metaheuristic Computing (IJAMC), vol. 9, no. 2, IGI Global, pp. 48-71, April, 2018. DOI: https://doi.org/10.4018/IJAMC.2018040103.
BibTeX :
@article{misc-lab-120,
author = {Belattar, Khadidja and Mostefai, Sihem and Draa, Amer},
title = {A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval},
journal = {International Journal of Applied Metaheuristic Computing (IJAMC)},
volume = {9},
number = {2},
issn = {1947-8291},
pages = {48--71},
publisher = {IGI Global},
year = {2018},
month = {April},
doi = {10.4018/IJAMC.2018040103},
url = {https://www.igi-global.com/article/a-hybrid-ga-lda-scheme-for-feature-selection-in-content-based-image-retrieval/199040}
}
RIS :
TI  - A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval
AU - K. Belattar
AU - S. Mostefai
AU - A. Draa
PY - 2018
SN - 1947-8291
JO - International Journal of Applied Metaheuristic Computing (IJAMC)
VL - 9
IS - 2
SP - 48
EP - 71
PB - IGI Global
AB - Feature selection is an important pre-processing technique in the pattern recognition domain. This article proposes a hybridization between Genetic Algorithm (GA) and the Linear Discriminant Analysis (LDA) for solving the feature selection problem in Content-Based Image Retrieval (CBIR) applied to dermatological images. In the first step, we preprocess and segment the input image, then we derive color and texture features characterizing healthy skin and the segmented skin lesion. At this stage, a binary GA is used to evolve chromosome subsets whose fitness is evaluated by a Logistic Regression classifier. The optimal identified features are then used to feed LDA for a CBIR system, based on a K-Nearest Neighbor classification. To assess the proposed approach, the authors have opted for a K-fold cross validation method on a database of 1097 images of melanomas and other skin lesions. As a result, the authors obtained a reduced number of features and an improved CBDIR system compared to PCA, LDA and ICA methods.
DO - 10.4018/IJAMC.2018040103
UR - https://www.igi-global.com/article/a-hybrid-ga-lda-scheme-for-feature-selection-in-content-based-image-retrieval/199040
ID - misc-lab-120
ER -