Photobook: Content-based manipulation of image databases

@article{citeulike:2671798, abstract = {We describe the Photobook system, which is a set of interactive tools for browsing and searching images and image sequences. These query tools differ from those used in standard image databases in that they make direct use of the image content rather than relying on text annotations. Direct search on image content is made possible by use of semantics-preserving image compression, which reduces images to a small set of perceptually-significant coefficients. We discuss three types of Photobook descriptions in detail: one that allows search based on appearance, one that uses 2-D shape, and a third that allows search based on textural properties. These image content descriptions can be combined with each other and with text-based descriptions to provide a sophisticated browsing and search capability. In this paper we demonstrate Photobook on databases containing images of people, video keyframes, hand tools, fish, texture swatches, and 3-D medical data.}, author = {Pentland, A. and Picard, R. W. and Sclaroff, S. }, citeulike-article-id = {2671798}, doi = {10.1007/BF00123143}, journal = {International Journal of Computer Vision}, keywords = {cbir}, month = {June}, number = {3}, pages = {233--254}, posted-at = {2008-04-15 04:08:49}, priority = {2}, title = {Photobook: Content-based manipulation of image databases}, url = {http://dx.doi.org/10.1007/BF00123143}, volume = {18}, year = {1996} }

TY - JOUR ID - citeulike:2671798 L3 - citeulike-article-id:2671798 TI - Photobook: Content-based manipulation of image databases JF - International Journal of Computer Vision VL - 18 IS - 3 SP - 233 EP - 254 N2 - We describe the Photobook system, which is a set of interactive tools for browsing and searching images and image sequences. These query tools differ from those used in standard image databases in that they make direct use of the image content rather than relying on text annotations. Direct search on image content is made possible by use of semantics-preserving image compression, which reduces images to a small set of perceptually-significant coefficients. We discuss three types of Photobook descriptions in detail: one that allows search based on appearance, one that uses 2-D shape, and a third that allows search based on textural properties. These image content descriptions can be combined with each other and with text-based descriptions to provide a sophisticated browsing and search capability. In this paper we demonstrate Photobook on databases containing images of people, video keyframes, hand tools, fish, texture swatches, and 3-D medical data. KW - cbir AU - Pentland, A AU - Picard, RW AU - Sclaroff, S PY - 1996/06/01/ UR - http://dx.doi.org/10.1007/BF00123143 ER -