Image retrieval systems based on compact shape descriptor and relevance feedback information

One of the most important and most used low-level image feature is the shape employed in a variety of systems such as document image retrieval through word spotting. In this paper an MPEG-like descriptor is proposed that contains conventional contour and region shape features with a wide applicability from any arbitrary shape to document retrieval through word spotting. Its size and storage requirements are kept to minimum without limiting its discriminating ability. In addition to that, a relevance feedback technique based on Support Vector Machines is provided that employs the proposed descriptor with the purpose to measure how well it performs with it. In order to evaluate the proposed descriptor it is compared against different descriptors at the MPEG-7 CE1 Set B database.

► A shape descriptor is proposed that contains contour and region shape features. ► A relevance feedback technique based on Support Vector Machines is provided. ► We suggest a more precise algorithm for the calculation of the SVM parameters. ► We evaluated it against various descriptors using the MPEG-7 CE1 Set B database. ► Its size and storage requirements are minimal without limiting the effectiveness.