Abstract
Patent information and images play important roles to describe the novelty of an invention. However, current patent collections do not support image retrieval and patent images are become almost unsearchable. This paper presents a short review of the existing research work and challenges in patent image retrieval domain. From the review, the image feature extraction step is found to be an important step to match the query and database images successfully. In order to improve the current feature extraction step in image patent retrieval, we propose a patent image retrieval approach based on Affine-SIFT technique. Comparison discussions between the existing feature extraction techniques are presented to assess the potential of this proposed approach. (C) 2013 The Authors. Published by Elsevier Ltd. Selection and peer-review under responsibility of the Faculty of Information Science & Technology, Universiti Kebangsaan Malaysia.