1 November 1992 Operator for object recognition and scene analysis by estimation of set occupancy with noisy and incomplete data sets
Author Affiliations +
Proceedings Volume 1825, Intelligent Robots and Computer Vision XI: Algorithms, Techniques, and Active Vision; (1992) https://doi.org/10.1117/12.131537
Event: Applications in Optical Science and Engineering, 1992, Boston, MA, United States
Abstract
Once feature extraction has occurred in a processed image, the recognition problem becomes one of defining a set of features which maps sufficiently well onto one of the defined shape/object models to permit a claimed recognition. This process is usually handled by aggregating features until a large enough weighting is obtained to claim membership, or an adequate number of located features are matched to the reference set. A requirement has existed for an operator or measure capable of a more direct assessment of membership/occupancy between feature sets, particularly where the feature sets may be defective representations. Such feature set errors may be caused by noise, by overlapping of objects, and by partial obscuration of features. These problems occur at the point of acquisition: repairing the data would then assume a priori knowledge of the solution. The technique described in this paper offers a set theoretical measure for partial occupancy defined in terms of the set of minimum additions to permit full occupancy and the set of locations of occupancy if such additions are made. As is shown, this technique permits recognition of partial feature sets with quantifiable degrees of uncertainty. A solution to the problems of obscuration and overlapping is therefore available.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
S. John Rees, S. John Rees, Bryan F. Jones, Bryan F. Jones, } "Operator for object recognition and scene analysis by estimation of set occupancy with noisy and incomplete data sets", Proc. SPIE 1825, Intelligent Robots and Computer Vision XI: Algorithms, Techniques, and Active Vision, (1 November 1992); doi: 10.1117/12.131537; https://doi.org/10.1117/12.131537
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Model-Based Object Recognition Using The Connection Machine
Proceedings of SPIE (February 19 1988)
Three-Dimensional Object Recognition Using Range Data
Proceedings of SPIE (March 27 1989)
Hough transform for 3-D object recognition
Proceedings of SPIE (March 01 1992)
Object Recognition by a Hopfield Neural Network
Proceedings of SPIE (March 01 1990)
Two-Dimensional Shape Recognition Using Redundant Hashing
Proceedings of SPIE (March 01 1990)
Indexing Shapes for Recognition
Proceedings of SPIE (March 27 1987)

Back to Top