Batik Lasem images classification using voting feature intervals 5 and statistical features selection approach

Batik Lasem has the unique pattern and it consists of the main pattern and the additional ornaments. Voting Feature Intervals 5 algorithm together with statistical features selection method based on features variance are proposed to classify Batik Lasem motifs. The experiment result shows that classification without feature selection method is producing the maximum accuracy 62%. Features selection method is applied to select a subset of features which have high variance across the samples. After applying feature selection method, the maximum accuracy is reaching 99.96%.