Invariant and occluded object recognition based on graph matching
The paper describes an algorithm for object recognition using neural network. The objects may be occluded and may have any changes in position, orientation and scale. The paper aims to generate project ideas for the final year students at the university and also to provide a basis for further research.
Get full access to this article
View all access options for this article.
References
1.
Von der MalsburgC., ‘Pattern recognition by labelled graph matching’, Neural Networks, 1, pp. 141–148(1988)
2.
NasrabadiN. M., and LiWei, ‘Object recognition by a Hopfield neural network’, IEEE Trans. Sys. Man. Cybern., 21, No. 6, pp. 1523–1535 (Nov/Dec.1991)
3.
KochM. W., and KashyapR. L., ‘Using polygon to recognize and locate partially occluded objects’, IEEE. Trans. Pattern Anal. Machine Intell., PAMI-9, pp. 483–494 (July 1987)
4.
GareyM. R., and JohnsonD. S., Computers and Intractability, Freeman (1979)
5.
HopfieldJ. J., and TankD. M., ‘Neural computation of decisions in optimization’, Biol. Cybern., 53, pp. 141–152(1985)
6.
AartsE., and KorstJ., Simulated Annealing and Boltzmann Machine, John Wiley (1988)
