Learning indexing functions for 3-D model-based object recognition
- 1 January 1994
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 275-280
- https://doi.org/10.1109/cvpr.1994.323840
Abstract
Indexing is an efficient method of recovering match hypotheses in model-based object recognition. Unlike other methods, which search for viewpoint-invariant shape descriptors to use as indices, we use a learning method to model the smooth variation in appearance of local feature sets (LFS). Indexing from LFS effectively deals with the problems of occlusion and missing features. The indexing functions generated by the learning method are probability distributions describing the possible interpretations of each index value. During recognition, this information can be used to select the least ambiguous features for matching. A verification stage follows so that the final reliability and accuracy of the match is greater than that from indexing alone. This approach has the potential to work with a wide range of image features and model types.Keywords
This publication has 11 references indexed in Scilit:
- Three-dimensional model matching from an unconstrained viewpointPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient model library access by projectively invariant indexing functionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- 3D object recognition by indexing structural invariants from multiple viewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Invariance-a new framework for visionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Structural indexing: efficient 2D object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Structural indexing: efficient 3-D object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Space and time bounds on indexing 3D models from 2D imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Recognizing partially visible objects using feature indexed hypothesesIEEE Journal on Robotics and Automation, 1986
- Perceptual Organization and Visual RecognitionPublished by Springer Nature ,1985
- An Algorithm for Finding Best Matches in Logarithmic Expected TimeACM Transactions on Mathematical Software, 1977