Recognition of partially occluded target objects

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

This paper presents a new method of consistent object representation which can be used for partially occluded target object recognition. We proposed a boundary smoothing method for curvature estimation using a constrained regularization technique in the previous paper. Even though the method is effective in detecting corners due to the use of corner sharpness to increase the robustness of the proposed algorithm, it does not preserve corners well. We propose another approach to boundary smoothing for curvature estimation using a mean field annealing technique in this paper to improve the capability of detecting corners. It removes the noise while preserving corners very well. In addition, we show some matching results in occlusion environment based on the corners detected by corner sharpness with the mean field annealing approach using a hybrid Hopfield neural network.

Original languageEnglish
Pages595-598
Number of pages4
Publication statusPublished - 1996 Dec 1
EventProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3) - Lausanne, Switz
Duration: 1996 Sep 161996 Sep 19

Other

OtherProceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3)
CityLausanne, Switz
Period96/9/1696/9/19

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Sohn, K. (1996). Recognition of partially occluded target objects. 595-598. Paper presented at Proceedings of the 1996 IEEE International Conference on Image Processing, ICIP'96. Part 2 (of 3), Lausanne, Switz, .