FTIP 2013 - Special Session on Fuzzy Techniques for Image Processing and Retrieval

The increasing availability of huge image collections on the Web is pressing need for the development of efficient techniques for the processing, the analysis, the indexing and the retrieval of image data. Fairly consolidated results were obtained in the area of content-based image retrieval (CBIR) aiming at indexing images with low-level content-based features. However CBIR applicability is hampered by the known problem of semantic gap, which is the gap between the low-level description of images and their semantic interpretation given by humans. Current research on image processing and retrieval is devoted to investigate how to fill the semantic gap, which still poses many challenges and open problems. Among these, the difficulty of users to express their requests in the form of well defined queries, the need of effective methods for the extraction of relevant as well concise features from images, the definition of flexible similarity measures for object matching, the automatic annotation of visual contents with semantic concepts. All these challenges can be addressed with the help of fuzzy techniques, which may provide efficient tools for image processing as well as convenient mechanisms for both content- based and concept-based image retrieval.