Exploiting Low-Level Image Segmentation for Object Recognition

Roth, Volker und Ommer, Björn (2006): Exploiting Low-Level Image Segmentation for Object Recognition. DAGM 2006: 28th Annual Symposium of the German Association for Pattern Recognition, Berlin, Deutschland, 12. - 14. September 2006. Franke, Katrin; Müller, Klaus-Robert; Nickolay, Bertram und Schäfer, Ralf (eds.) : In: Pattern Recognition : 28th DAGM Symposium Berlin, Germany, September 12-14, 2006 Proceedings, Berlin: Springer. pp. 11-20

Abstract

A method for exploiting the information in low-level image segmentations for the purpose of object recognition is presented. The key idea is to use a whole ensemble of segmentations per image, computed on different random samples of image sites. Along the boundaries of those segmentations that are stable under the sampling process we extract strings of vectors that contain local image descriptors like shape, texture and intensities. Pairs of such strings are aligned, and based on the alignment scores a mixture model is trained which divides the segments in an image into fore- and background. Given such candidate foreground segments, we show that it is possible to build a state-of-the-art object recognition system that exhibits excellent performance on a standard benchmark database. This result shows that despite the inherent problems of low-level image segmentation in poor data conditions, segmentation can indeed be a valuable tool for object recognition in real-world images.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Mathematics, Computer Science and Statistics > Computer Science
• Subjects: 000 Computer science, information and general works > 000 Computer science, knowledge, and systems; 700 Arts and recreation > 700 Arts
• ISBN: 978-3-540-44412-1
• ISSN: 0302-9743
• Place of Publication: Berlin
• Language: English