이진 웨이브렛 변환을 이용한 신경회로망의 필기체 문자 인식

• 영문명: A Neural Network Based Handwritten-Charater Recognition using Binary Wavelet Transform
• 발행기관: 강원대학교 산업기술연구소
• 저자명: 이정문(Jung Moon Lee) 유경산(Kyoung San You)
• 간행물 정보: 『산업기술연구』vol.17, 331~338쪽, 전체 8쪽
• 주제분류: 공학 > 공학일반
• 파일형태: PDF
• 발행일자: 1997.09.30

영문 초록

In this paper, we propose a new neural pattern recognition from wavelet transform. We first analysis in BFT(Binary Field Transform) in character image. The proposed neural network and wavelet transform is able to improve learning time and scaling. The ability and effectiveness of identifying image using the proposed wavelet transform will be demonstrated by computer simulation.

목차

ABSTRACT

1. 서론

2. Wavelet

3. BFT(Binary Field Transform)

4. BPN (Back Propergation Neural Network)

5. 모의 실험

6. 결론

참고문헌