Improved shape matching and retrieval using robust histograms of spatially distributed points and angular radial transform

In this paper, the problem of shape based image retrieval is addressed by proposing a hybrid shape descriptor. The proposed descriptor conforms to human visual perception along with its low computational complexity. Since global features are related to the holistic characteristics of images, whereas local features describe the finer details within objects of images, in the proposed hybrid descriptor both global and local features of images are used to describe the entire aspects of image shape. For global features extraction, we use angular radial transform, which is also adopted by MPEG-7 as a region based shape descriptor. On the other hand, for local feature extraction, a novel local descriptor is proposed, which is referred to as histograms of spatially distributed points (HSDP). It is based on two components: radial distance and differential coefficient, which are used to build 2D histograms. Global and local features are combined using effective distance measures viz. Min-Max and Bray-Curtis. Their superiority is validated by experimental results. Apart from that, an extensive range of image databases is employed to assess the performance of the proposed hybrid descriptor. These databases represent several characteristics of shape such as partial occlusion, distortion, subject change, gray scale objects, rotated and noise affected objects, unstructured images, trademarks, blurred images, Corel images, etc. The results of wide range of experiments reveal that the fusion of ART and HSDP significantly improves the image retrieval accuracy and provides a robust and invariant solution for effective shape matching.