Landmark-based partial shape recognition by a BAM neural network

Xianjun Liu, Nirwan Ansari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we develop a bidirectional associative memory (BAM) based neural network to achieve high-speed partial shape recognition. To recognize objects which 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 which may consist of several objects, landmarks in the scene are first extracted, and their corresponding landmark values are computed. Scene landmarks 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.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherPubl by Int Soc for Optical Engineering
Pages1069-1079
Number of pages11
Editionpt 2
ISBN (Print)0819407437, 9780819407436
DOIs
StatePublished - Jan 1 1991
EventVisual Communications and Image Processing '91: Image Processing Part 2 (of 2) - Boston, MA, USA
Duration: Nov 11 1991Nov 13 1991

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Numberpt 2
Volume1606
ISSN (Print)0277-786X

Other

OtherVisual Communications and Image Processing '91: Image Processing Part 2 (of 2)
CityBoston, MA, USA
Period11/11/9111/13/91

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Landmark-based partial shape recognition by a BAM neural network'. Together they form a unique fingerprint.

Cite this