中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Multiresolution locally expanded HONN for handwritten numeral recognition

文献类型:期刊论文

作者Liu, CL; Kim, JH; Dai, RW
刊名PATTERN RECOGNITION LETTERS
出版日期1997-10-01
卷号18期号:10页码:1019-1025
关键词handwritten numeral recognition high order neural network local expansion multiresolution representation
英文摘要In this paper, we propose a neural network architecture, multiresolution locally expanded high order neural network (MRLHONN) to solve the problem of handwritten numeral recognition. In this recognition scheme, the multiresolution representation of character image is input into a high order neural network (HONN), while in each resolution, only neighboring pixels are expanded to produce high order input. The property of this architecture is that, the local expansion alleviate the problem of large connecting weight set, and the multiresolution representation remedy the inadequacy of local expansion. Two forms of multiresolution representations, quadtree representation and Gaussian pyramid, were used in experiments. The recognition results demonstrate the efficiency of the proposed architecture. (C) 1997 Elsevier Science B.V.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Artificial Intelligence
研究领域[WOS]Computer Science
关键词[WOS]ORDER NEURAL NETWORKS
收录类别SCI
语种英语
WOS记录号WOS:000071648900007
公开日期2015-12-24
源URL[http://ir.ia.ac.cn/handle/173211/9763]  
专题自动化研究所_09年以前成果
作者单位1.Korea Adv Inst Sci & Technol, Dept Comp Sci, Taejon 305701, South Korea
2.Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714
Liu, CL,Kim, JH,Dai, RW. Multiresolution locally expanded HONN for handwritten numeral recognition[J]. PATTERN RECOGNITION LETTERS,1997,18(10):1019-1025.
APA Liu, CL,Kim, JH,&Dai, RW.(1997).Multiresolution locally expanded HONN for handwritten numeral recognition.PATTERN RECOGNITION LETTERS,18(10),1019-1025.
MLA Liu, CL,et al."Multiresolution locally expanded HONN for handwritten numeral recognition".PATTERN RECOGNITION LETTERS 18.10(1997):1019-1025.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。