EVALUATING KEYPOINT METHODS FOR CONTENT-BASED COPYRIGHT PROECTION OF DIGITAL IMAGES (FriPmPO1)

Author(s) : Larry Huston (Intel Research Pittsburgh, United States of America) Rahul Sukthankar (Intel Research and Carnegie Mellon, United States of America) Yan Ke (Carnegie Mellon University, United States of America)

Abstract : This paper evaluates the effectiveness of keypoint methods for content-based protection of digital images. These methods identify a set of ``distinctive'' regions (termed keypoints) in an image and encode them using descriptors that are robust to expected image transformations. To determine whether a particular image was derived from a protected image, the keypoints for both images are generated and matched. We describe a comprehensive set of experiments to examine how keypoint methods cope with three real-world challenges: (1) loss of keypoints due to cropping; (2) matching failures caused by approximate nearest-neighbor indexing schemes; (3) degraded descriptors due to significant image distortions. While keypoint methods perform very well in general, this paper identifies cases where the accuracy of these methods degrades.

Menu