1 March 1991 Background characterization using a second-order moment function
Author Affiliations +
A typical object recognition problem deals mainly with the characterization of objects and treats background as noise. However, in many applications, we can assume the reverse. Intuitively, the background information is easier to describe in terms of intensity distributions (textures), while the unknown nature of objects' types and positions poses a more difficult formulation for general pattern recognition problems. In this paper, we propose the use of a second order moment function to describe the scene. Various types of backgrounds and objects are evaluated, and results from this experiment are presented.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Marija Scholl, Gabriel Udomkesmalee, "Background characterization using a second-order moment function", Proc. SPIE 1468, Applications of Artificial Intelligence IX, (1 March 1991); doi: 10.1117/12.45452; https://doi.org/10.1117/12.45452


Image segmentation based on pixel feature manifold
Proceedings of SPIE (December 08 2011)
Using Contextual Information In Classification Algorithms
Proceedings of SPIE (April 06 1987)
Region-of-interest detection for fingerprint classification
Proceedings of SPIE (February 25 1994)
Rapid Texture Identification
Proceedings of SPIE (December 23 1980)
Multithresholding: a neural approach
Proceedings of SPIE (May 01 1994)

Back to Top