1 July 1993 Recognizing partially occluded objects by a bidirectional associative memory neural network
Author Affiliations +
We develop a bidirectional associative memory (BAM)-based neural network to achieve high-speed partial shape recognition. To recognize objects that are partially occluded, we represent each object by a set of landmarks. The landmarks of an object are points of interest relative to the object that have important shape attributes. To achieve recognition, feature values (landmark values) of each model object are trained and stored in the network. Each memory cell is trained to store landmark values of a model object for all possible positions. Given a scene that may consist of several objects, landmarks in the scene are first extracted, and their corresponding landmark values are computed. Scene landmark values are entered to each trained memory cell. The memory cell is shown to be able to recall the position of the model object in the scene. A heuristic measure is then computed to validate the recognition.
Nirwan Ansari, Nirwan Ansari, Xianjun Liu, Xianjun Liu, } "Recognizing partially occluded objects by a bidirectional associative memory neural network," Optical Engineering 32(7), (1 July 1993). https://doi.org/10.1117/12.152189 . Submission:


Dynamic neural network for visual memory
Proceedings of SPIE (August 31 1990)
Neural structures in digital halftoning
Proceedings of SPIE (May 20 1993)
Weighted-outer-product associative neural network
Proceedings of SPIE (October 31 1991)

Back to Top