Tal Semantic - oriented 3 d shape retrieval using relevance feedback ∗

G. Leifman ( ) ·R. Meir ·A. Tal Department of Electrical Engineering Technion – Israel Institute of Technology {gleifman@techunix, rmeir@ee, ayellet@ee}.technion.ac.il ∗ This work was partially supported by European FP6 NoE grant 506766 (AIM@SHAPE), by the Israeli Ministry of Science, grant 01-01-01509 and by the Ollendorff foundation. Abstract Shape-based retrieval of 3D models has become an important challenge in computer graphics. Object similarity, however, is a subjective matter, dependent on the human viewer, since objects have semantics and are not mere geometric entities. Relevance feedback aims at addressing the subjectivity of similarity. This paper presents a novel relevance feedback algorithm that is based on supervised as well as unsupervised feature extraction techniques. It also proposes a novel signature for 3D models, the sphere projection. A Web search engine that realizes the signature and the relevance feedback algorithm is presented. We show that the proposed approach produces good results and outperforms previous techniques.