Retrieving images from very large collections, using image content as a key, is becoming an important problem. Finding objects in image databases is a big challenge in the field. This paper describes our approach to object recognition, which is distinguished by: a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with three case-studies: one demonstrating the use of color and texture descriptors; one learning scenery concepts using grouped features; and one demonstrating a possible application domain in detecting naked people in a scene.
|Number of pages||4|
|State||Published - 1996|
|Event||Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) - Lausanne, Switz|
Duration: 16 Sep 1996 → 19 Sep 1996
|Conference||Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)|
|Period||16/09/96 → 19/09/96|