Browse > Article
http://dx.doi.org/10.5391/JKIIS.2007.17.2.226

Colored Object Extraction using Fuzzy Neural Network  

Kim, Yong-Soo (대전대학교 컴퓨터공학과)
Chung, Seung-Won (대전대학교 컴퓨터공학과)
Publication Information
Journal of the Korean Institute of Intelligent Systems / v.17, no.2, 2007 , pp. 226-231 More about this Journal
Abstract
This paper presents a method of colored object extraction from an image using the fuzzy neural network. Fuzzy neural network divides an image into two clusters. It extracts the prototypes of Cb and Cr of object and background by controlling the vigilance parameter. The proposed method extracted object regardless of the position, the size, and the intensity of object. We compared the performance of the proposed method with that of the method of using subjective threshold value. And, we compared the performance of the proposed method with that of the method of using subjective threshold value by using several images with added noises.
Keywords
Improved IAFC(Integrated Adaptive Fuzzy Clustering) Fuzzy Neural Network; Vigilance Parameter; RGB; YCbCr; Object Extraction;
Citations & Related Records
연도 인용수 순위
  • Reference
1 D. M. Weber and D. P. Casasent, 'Quadratic Gabor filters for object detection,' IEEE Trans. on Image Processing, Vol. 10, No.2, pp. 218-230, 2001   DOI   ScienceOn
2 김남진, '영상 향상 기법들에 관한 비교 연구,' 대전대학교 석사학위논문, 2005
3 문성원, 장언동, 송영준, '기울어진 차량 번호판 영역의 검출' 한국콘텐츠학회논문집, Vol. 4, No.3, 2004
4 이운석, 김희승, 'HSI 컬러 모텔에 기반한 자동차 번호판 영역 검출,' 한국정보과학회 가을 학술발표 논문집 , Vol. 26, No.2, pp. 524-526, 1999
5 R. P. Broussard, S. K. Rogers, M. E. Oxley, and G. L. TaIT, 'Physiologically motivated image fusion for object detection using a pulse coupled neural networks,' IEEE Trans. on Neural Networks, Vol. 10, No.3, pp. 554-563, 1999   DOI   ScienceOn
6 김영길, 한재혁, 안재형 '컬러 정지 영상에서 색상과 모양 정보를 이용한 얼굴 영역 검출,' 멀티미디어학회 논문지, Vol. 4, No. 1, pp. 67-74, 2001
7 김용수, 함창현, 백용선, 'Underutilization 문제를 해결한 퍼지 신경회로망 모델,' 한국퍼지 및 지능시스템학회논문집, Vol. 11, No. 4, pp.354-357, 2001
8 M. A. Khabou and P. D. Gader, 'Automatic target detection using entropy optimized shared-weight neural networks,' IEEE Trans. on Neural Networks, Vol. 11, No.1, pp. 186-193, 2000   DOI   ScienceOn