Multi-View Feature Combination for Ancient Paintings Chronological Classification

Abstract

Ancient paintings can provide valuable information for historians and archeologists to study the history and humanity of the corresponding eras. How to determine the era in which a painting was created is a critical problem, since the topic of a painting cannot be used as an effective basis without an era label. To address this problem, this article proposes a novel computational method by using multi-view local color features extracted from the paintings. First, we extract the multi-view local color features for all training images using a novel descriptor named Affine Lab-SIFT. Then we can learn the codebook from all these features by k -means clustering. Afterwards, we create a feature histogram for each image in the form of bag-of-visual-words and use a supervised fashion to train a classifier, which is used for further painting classification. Experimental results from two different datasets show the effectiveness of the proposed classification system and the advantage of the proposed features, especially in the case of small-size training samples.