Combination of texture feature extraction and forward selection for one-class support vector machine improvement in self-portrait classification

<span lang="EN-US">This study aims to validate self-portraits using one-class support vector machine (OCSVM). To accurately, we build a model by combining texture feature extraction methods, Haralick and local binary pattern (LBP). We also reduce irrelevant features forward selection (FS). OCSVM was selected because it can solve the problem caused inadequate variation of negative class population. In OCSVM, only need feed algorithm true data, data with that does not match will be classified as false. However, two extractions produces many features, leading curse dimensionality. The FS method is used overcome this selecting best features. From experiments carried out, Haralick+LBP+FS+OCSVM outperformed other models an accuracy 95.25% on validation 91.75% test data.</span>