Recognition using regions
Chunhui Gu, Joseph J. Lim, Pablo Arbeláez et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2009
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 Arbeldez 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.
Cited by 347 works. doi:10.1109/cvpr.2009.5206727
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- Histograms of Oriented Gradients for Human Detection
- LIBSVM
- The Pascal Visual Object Classes (VOC) Challenge
- Object Detection with Discriminatively Trained Part-Based Models
- Robust Real-Time Face Detection
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Normalized cuts and image segmentation
- Caltech-256 Object Category Dataset
- Neural network-based face detection