Abstract:
We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows t...Show MoreMetadata
Abstract:
We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 29, Issue: 3, March 2007)
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Object Recognition ,
- Robust Object Recognition ,
- Computer Vision ,
- Visual Cortex ,
- Recognition Task ,
- Training Examples ,
- Hierarchical System ,
- Template Matching ,
- Maximum Operating ,
- Scene Understanding ,
- Training Set ,
- Visual System ,
- Changes In Position ,
- Image Size ,
- Object Detection ,
- Receptive Field ,
- Training Images ,
- Target Object ,
- Primary Visual Cortex ,
- Scale Space ,
- Simple Cells ,
- Benchmark System ,
- Universal Set ,
- Gabor Filters ,
- Computer Vision System ,
- SIFT Features ,
- Appearance Variations ,
- Original Aspect Ratio ,
- S Units
- Author Keywords
- MeSH Terms
- Algorithms ,
- Artificial Intelligence ,
- Biomimetics ,
- Computer Simulation ,
- Humans ,
- Image Enhancement ,
- Image Interpretation, Computer-Assisted ,
- Models, Biological ,
- Pattern Recognition, Automated ,
- Pattern Recognition, Visual ,
- Reproducibility of Results ,
- Sensitivity and Specificity ,
- Visual Cortex
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Object Recognition ,
- Robust Object Recognition ,
- Computer Vision ,
- Visual Cortex ,
- Recognition Task ,
- Training Examples ,
- Hierarchical System ,
- Template Matching ,
- Maximum Operating ,
- Scene Understanding ,
- Training Set ,
- Visual System ,
- Changes In Position ,
- Image Size ,
- Object Detection ,
- Receptive Field ,
- Training Images ,
- Target Object ,
- Primary Visual Cortex ,
- Scale Space ,
- Simple Cells ,
- Benchmark System ,
- Universal Set ,
- Gabor Filters ,
- Computer Vision System ,
- SIFT Features ,
- Appearance Variations ,
- Original Aspect Ratio ,
- S Units
- Author Keywords
- MeSH Terms
- Algorithms ,
- Artificial Intelligence ,
- Biomimetics ,
- Computer Simulation ,
- Humans ,
- Image Enhancement ,
- Image Interpretation, Computer-Assisted ,
- Models, Biological ,
- Pattern Recognition, Automated ,
- Pattern Recognition, Visual ,
- Reproducibility of Results ,
- Sensitivity and Specificity ,
- Visual Cortex