Combination and optimization of classifiers in gender classification using genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Article{Khan:2005:IJKBIE,

• author = "Asifullah Khan and Abdul Majid and Anwar M. Mirza",
• title = "Combination and optimization of classifiers in gender classification using genetic programming",
• journal = "International Journal of Knowledge-Based and Intelligent Engineering Systems",
• year = "2005",
• volume = "9",
• number = "1",
• pages = "1--11",
• keywords = "genetic algorithms, genetic programming, gender classification, principal component analysis, eigenface, jackknife technique, receiver operating characteristics curve, area under the convex hull, AUROC",
• ISSN = "1327-2314",
• URL = "http://content.iospress.com/articles/international-journal-of-knowledge-based-and-intelligent-engineering-systems/kes00019",
• DOI = "doi:10.3233/KES-2005-9101",
• size = "11 pages",
• abstract = "we have investigated the problem of gender classification using frontal facial images. Four different classifiers, namely K-means, k-nearest neighbours, Linear Discriminant Analysis and Mahalanobis Distance Based classifiers are compared. Receiver operating characteristics (ROC) curve along with the area under the convex hull (AUCH) have been used as the performance measures of the classifiers at different feature subsets. To measure the overall performance of a classifier with single scalar value, the new scheme of finding the area under the convex hull of AUCH of ROC curves (AUCH of AUCHS) is proposed. It has been observed that, when the number of macro features is increased beyond 5, the AUCH saturates and even decreases for some classifiers, illustrating the curse of dimensionality. We then used genetic programming to combine classifiers and thus evolved an optimum combined classifier (OCC), producing better performance than the individual classifiers. We found that using only two features, the OCC has comparable performance to that of original classifier using 20 macro features. It produces true positive rate values as high as 0.94 corresponding to false positive rate as low as 0.15 for 1: 3 train to testing ratio. We also observed that heterogeneous combination of classifiers is more promising than the homogenous combination.",

}

Genetic Programming entries for Asifullah Khan Abdul Majid Anwar M Mirza

Citations