Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 35, Issue 9, Pages 2189-2205Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2013.35
Keywords
Deformable templates; object recognition; image grammar; information projection
Funding
- US Defense Advanced Research Projects Agency (DARPA) [FA 8650-11-1-7149]
- US National Science Foundation (NSF) [IIS1018751]
- MURI [ONR N00014-10-1-0933]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1018751] Funding Source: National Science Foundation
Ask authors/readers for more resources
This paper presents a framework for unsupervised learning of a hierarchical reconfigurable image template-the AND-OR Template (AOT) for visual objects. The AOT includes: 1) hierarchical composition as AND nodes, 2) deformation and articulation of parts as geometric OR nodes, and 3) multiple ways of composition as structural OR nodes. The terminal nodes are hybrid image templates (HIT) [17] that are fully generative to the pixels. We show that both the structures and parameters of the AOT model can be learned in an unsupervised way from images using an information projection principle. The learning algorithm consists of two steps: 1) a recursive block pursuit procedure to learn the hierarchical dictionary of primitives, parts, and objects, and 2) a graph compression procedure to minimize model structure for better generalizability. We investigate the factors that influence how well the learning algorithm can identify the underlying AOT. And we propose a number of ways to evaluate the performance of the learned AOTs through both synthesized examples and real-world images. Our model advances the state of the art for object detection by improving the accuracy of template matching.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available