Abstract / Description of output
We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the accurate boundaries of the objects, rather than just their bounding-boxes. This is made possible by 1) a novel technique for learning a shape model of an object class given images of example instances; 2) the combination of Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately, while needing no segmented examples for training (only bounding-boxes).
Original language | English |
---|---|
Title of host publication | Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on |
Pages | 1-8 |
Number of pages | 8 |
ISBN (Electronic) | 1-4244-1180-7 |
DOIs | |
Publication status | Published - 1 Jun 2007 |
Keywords / Materials (for Non-textual outputs)
- image matching
- object detection
- accurate object detection
- bounding-boxes
- cluttered images
- deformable shape models
- shape matcher
- Computer vision
- Deformable models
- Detectors
- Image segmentation
- Impedance matching
- Object detection
- Prototypes
- Shape
- Signal to noise ratio
- Voting