Browse > Article
http://dx.doi.org/10.3745/KIPSTB.2002.9B.5.673

Edge detection method using unbalanced mutation operator in noise image  

Kim, Su-Jung (조선대학교 대학원 전산통계학과)
Lim, Hee-Kyoung (서강정보대학교 정보통신부)
Seo, Yo-Han (서강정보대학교 인터넷정보과)
Jung, Chai-Yeoung (조선대학교 수학·전산통계학부)
Publication Information
The KIPS Transactions:PartB / v.9B, no.5, 2002 , pp. 673-680 More about this Journal
Abstract
This paper proposes a method for detecting edge using an evolutionary programming and a momentum back-propagation algorithm. The evolutionary programming does not perform crossover operation as to consider reduction of capability of algorithm and calculation cost, but uses selection operator and mutation operator. The momentum back-propagation algorithm uses assistant to weight of learning step when weight is changed at learning step. Because learning rate o is settled as less in last back-propagation algorithm the momentum back-propagation algorithm discard the problem that learning is slow as relative reduction because change rate of weight at each learning step. The method using EP-MBP is batter than GA-BP method in both learning time and detection rate and showed the decreasing learning time and effective edge detection, in consequence.
Keywords
Evolutionary Programming; Back-Propagation Algorithm;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 J. M. Zurada, 'Introduction to Artificial Neural System,' St. Paul. West Publishing Co. 1992
2 D.H.Ballard and C.M.Brown, 'Computer vision,' Presentice- Hall, Inc Englewood Cliffs, NJ, 1982
3 박찬란 외, '유전자와 역전파 알고리즘을 이용한 효율적인 윤곽선 추출', 정보처리학회논문지, 제5권 제11호, pp.3010-3023, 1998   과학기술학회마을
4 Sukhan Lee, 'Robust Recognition of Handwritten Numerals based on Dual Cooperative Network,' IEEE IJCNN, Vol. 3, pp.760-768, 1992   DOI
5 이흥호, 'M 변환과 환 이동 불변 신경망을 이용한 효율적인 패턴인식', 서울대학교 학위논문, 1994
6 Y. H. Yu, R. F. Simmons, 'Descending Epsilon in Back-Propagation : A Technique for Better Generalization,' IEEE IJCNN, Vol.3, pp.167-172, 1990   DOI
7 권세욱 외, '계층적 신경망을 이용한 다중크기의 다중활자체 한글 문서 인식', 한국정보과학회논문지, 제19권 제1호, pp.69-79, 1992
8 Randy Crane, 'Simplified approach to Image Processing,' Prentice-Hall, 1997
9 D. B. Fogel, 'Evolving artificial intelligence,' Ph.D thesis, University of California, San Diego, CA, 1992
10 David E. Goldberg, 'Genetic Algorithm in Search, Optimization, and Machine Learning,' Addison-Wesley, 1989
11 김부열, '배열문법을 이용한 필기체 숫자 인식에 관한 연구', 충북대학교 학위논문, 1991
12 오명관 외, '복소-대수 사상함수와 신경회로망을 이용한 필기체 숫자의 불변인식', 한국정보과학회논문지, 제21권 제3 호, pp.464-470
13 S. Kageyu, 'Augmented Multi-layer Perception for Rota-tion-and-Scale Invariant Hand-Written Numeral Recognition', IEEE IJCNN, pp.54-59, 1991
14 Karin Sobottka, Ioannis Pitas, 'Extraction of Facial Regions and Features Using Color and Shape Information,' Proceeding of the International Conference on Pattern Recognition, pp.421-425, 1996   DOI
15 김종호 외, '신경회로망과 Log-Polar Sampling 기법을 사용한 항공기 영상의 연상인식', 대한전자공학회논문지, 제28권 제12호, pp.59-67, 1991
16 P. D. Wasserman, 'Neural Computing : Theory and Practice,' New York, Van Nostrand Roinhold, 1989