Recognition of planar object classes
- 1 January 1996
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 223-230
- https://doi.org/10.1109/cvpr.1996.517078
Abstract
We present a new framework for recognizing planar object classes, which is based on local feature detectors and a probabilistic model of the spatial arrangement of the features. The allowed object deformations are represented through shape statistics, which are learned from examples. Instances of an object in an image are detected by finding the appropriate features in the correct spatial configuration. The algorithm is robust with respect to partial occlusion, detector false alarms, and missed features. A 94% success rate was achieved for the problem of locating quasi-frontal views of faces in cluttered scenes.Keywords
This publication has 17 references indexed in Scilit:
- Combining point distribution models with shape models based on finite element analysisImage and Vision Computing, 1995
- Use of active shape models for locating structures in medical imagesImage and Vision Computing, 1994
- Distortion invariant object recognition in the dynamic link architectureIEEE Transactions on Computers, 1993
- General shape distributions in a planeAdvances in Applied Probability, 1991
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991
- Deformable Templates for Face RecognitionJournal of Cognitive Neuroscience, 1991
- A Survey of the Statistical Theory of ShapeStatistical Science, 1989
- Size and Shape Spaces for Landmark Data in Two DimensionsStatistical Science, 1986
- A statistical method for biological shape comparisonsJournal of Theoretical Biology, 1984
- Shape Manifolds, Procrustean Metrics, and Complex Projective SpacesBulletin of the London Mathematical Society, 1984