Authors - Prerna Agarwal, Bharat Gupta, Pranav Shrivastava, Saquib Hussain, Kareena Tuli, Amaanur Rahman, Aishwarya Keshri Abstract - We propose a classification method for Ise-katagami stencil images based on SIFT keypoints and an optimal matching framework. Ise-katagami are traditional Japanese stencil papers originally developed for kimono dyeing, many of which have been preserved over long periods yet lack annotation. Because of copyright-related limitations, methods based on conventional deep learning or transfer learning―which typically depend on large labeled datasets―cannot be readily applied. To address this challenge, the proposed method formulates the classification task as an optimal matching problem over sets of SIFT keypoints, allowing robust comparison of local image structures without relying on pixellevel features. The method requires only a small number of copyrightfree training images to extract representative features for each class, thereby eliminating the need for large-scale training data and enabling fast classification. According to the experimental evaluation, our method computes a suitable decision threshold within seconds, whereas the PCAbased method demands more than 3,000 seconds for optimization, despite both achieving almost perfect classification accuracy.
Open Zoom