Effects of Training Set Dimension on Recognition of Dysmorphic Faces with Statistical Classifiers
Journal: The International Arab Journal of Information Technology (Vol.12, No. 2)Publication Date: 2015-03-01
Authors : Şafak Saraydemir; Necmi Taşpınar; Osman Eroğul; Hülya Kayserili;
Page : 204-211
Keywords : Dysmorphology; GWT; Principal component analysis; face recognition; SVM; K-NN;
Abstract
In this paper, an evaluation using various training data sets for discrimination of dysmorphic facial features with distinctive information will be presented. We utilize Gabor Wavelet Transform (GWT) as feature extractor, K-Nearest Neighbor (K-NN) and Support Vector Machines (SVM) as statistical classifiers. We analyzed the classification accuracy according to increasing dimension of training data set, selecting kernel function for SVM and distance metric for K-NN. At the end of the overall classification task, GWT-SVM approach with Radial Basis Function (RBF) kernel type achieved the best classification accuracy rate as 97,5% with 400 images in training data set.
Other Latest Articles
- Topical Web Crawling for Domain-Specific Resource Discovery Enhanced by Selectively using Link-Context
- Arabic Text Classification using K-Nearest Neighbour Algorithm
- Optimized Features Selection using Hybrid PSOGA for Multi-View Gender Classification
- Optimizing Ontology Alignments by using NSGA-II
- The Proposal of a Qualification Based Approach to Teach Software Engineering Course
Last modified: 2019-11-14 22:32:04