The automatic classification of digital photographs in semantic categories is an unresolved challenge in the multimedia and imaging communities. Annotating images with a description of the content can facilitate the organization, storage and retrieval of image databases. It can also be useful in processing images, by automatically adopting content-specific strategies. A framework for automatic image classification will be presented together with some examples of its application to problems related to image processing, enhancement, and retrieval. More in detail, it will be shown how automatic color constancy, adaptive image cropping, and retrieval by relevance feedback may benefit from a content-based approach.
Claudio Cusano is a post-doc student at DISCo (Department of Information Science, Systems Theory, and Communication) of the University of Milano-Bicocca, where he took his PhD in Computer Science. Since April 2001 he has been a fellow of the the ITC Institute of the Italian National Research Council. The main topics of his current research concern 2D and 3D imaging, with a particular focus on image analysis and classification, and on face recognition.