Discriminatively Trained And-Or Graph Models for Object Shape Detection
- 23 September 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (5), 959-972
- https://doi.org/10.1109/tpami.2014.2359888
Abstract
In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images. Our proposed model consists of four layers: leaf-nodes at the bottom are local classifiers for detecting contour fragments; or-nodes above the leaf-nodes function as the switches to activate their child leaf-nodes, making the model reconfigurable during inference; and-nodes in a higher layer capture holistic shape deformations; one root-node on the top, which is also an or-node, activates one of its child and-nodes to deal with large global variations (e.g. different poses and views). We propose a novel structural optimization algorithm to discriminatively train the And-Or model from weakly annotated data. This algorithm iteratively determines the model structures (e.g. the nodes and their layouts) along with the parameter learning. On several challenging datasets, our model demonstrates the effectiveness to perform robust shape-based object detection against background clutter and outperforms the other state-of-the-art approaches. We also release a new shape database with annotations, which includes more than 1500 challenging shape instances, for recognition and detection.Funding Information
- National Natural Science Foundation of China (61173082, 61173084)
- Guangdong Science and Technology Program (2012B031500006)
- Guangdong Natural Science Foundation (S2013050014548)
- Special Project on Integration of Industry
- Education and Research of Guangdong Province (2012B091000101, 2012B091100148)
- Fundamental Research Funds for the Central Universities (13lgjc26)
This publication has 34 references indexed in Scilit:
- Learning AND-OR Templates for Object Recognition and DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Learning hierarchical poselets for human parsingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Contextualizing object detection and classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Learning Active Basis Model for Object Detection and RecognitionInternational Journal of Computer Vision, 2009
- 2D Shape Matching by Contour FlexibilityIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Shape matching and registration by data-driven EMComputer Vision and Image Understanding, 2008
- Optimized cutting plane algorithm for support vector machinesPublished by Association for Computing Machinery (ACM) ,2008
- Groups of Adjacent Contour Segments for Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Scale-invariant shape features for recognition of object categoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Contour-based object identification and segmentation: Stimuli, norms and data, and software toolsBehavior Research Methods, Instruments & Computers, 2004