Shape measures for image retrieval

One of the main goals in Content Based Image Retrieval (CBIR) is to incorporate shape into the process in a reliable manner. In order to overcome the difficulties of directly obtaining shape information (in particular avoiding region segmentation) we develop several shape measures that tackle the problem in an indirect manner, requiring only a minimal amount of segmentation. A histogram-based scheme is then used, maintaining low complexity with high efficiency and robustness. The obtained results showed that the synergy of the shape measures worked out providing an improvement over the colour histogram.

• Type: Conference
• Year: 2001
• Where: ICIP
• Authors: George Gagaudakis, Paul L. Rosin
• Keywords: ICIP 2001, Image Processing, Particular Avoiding Region, Shape Information, Shape Measures