Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences


UC Berkeley


2010 Research Summary

Recognition using Regions

View Current Project Information

Jitendra Malik, Chunhui Gu, Pablo Arbelaez and Joseph Lim

ARO MURI W911NF-06-1-0076 and ONR/MURI N00014-06-1-0734

This paper presents a unified framework for object detection, segmentation, and classification using regions. Region features are appealing in this context because: (1) they encode shape and scale information of objects naturally; (2) they are only mildly affected by background clutter.

Regions have not been popular as features due to their sensitivity to segmentation errors. In this paper, we start by producing a robust bag of overlaid regions for each image using Arbelaez et al, CVPR 2009. Each region is represented by a rich set of image cues (shape, color and texture). We then learn region weights using a max-margin framework. In detection and segmentation, we apply a generalized Hough voting scheme to generate hypotheses of object locations, scales and support, followed by a verification classifier and a constrained segmenter on each hypothesis.

The proposed approach significantly outperforms the state of the art on the ETHZ shape database (87.1% average detection rate compared to Ferrari et al's 67.2%), and achieves competitive performance on the Caltech 101 database.