A sparse object category model for efficient learning and exhaustive recognition

Conference item

We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in an exhaustive manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.

Authors: Fergus, R; Perona, P; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
• Volume: 1
• Pages: 380-387
• Publication date: 2005-07-25
• Event title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005)
• Event location: San Diego, California, USA
• Event website: https://www.computer.org/csdl/proceedings/cvpr/2005/12OmNA0MYYm
• Event start date: 2005-06-20
• Event end date: 2005-06-26
• DOI: 10.1109/cvpr.2005.47
• ISSN: 1063-6919
• ISBN: 0769523722
• Language: English
• Keywords: region 1; image edge detection; object detection; optimal matching; image segmentation; detectors; image recognition; computer vision; cats; topology