{"title":"手写体数字识别结合神经网络分类器","authors":"A. Khofanzad, C. Chung","doi":"10.1109/IAI.1998.666880","DOIUrl":null,"url":null,"abstract":"A new classification scheme for handwritten digit recognition is proposed. The method is based on combining the decisions of two multilayer perceptron (MLP) artificial neural network classifiers operating on two different feature types. The first feature set is defined on the pseudo Zernike moments of the image whereas the second feature type is derived from the shadow code of the image using a newly defined projection mask. A MLP network is employed to perform the combination task. The performance is tested on a data base of 15000 samples and the advantage of the combination approach is demonstrated.","PeriodicalId":373701,"journal":{"name":"1998 IEEE Southwest Symposium on Image Analysis and Interpretation (Cat. No.98EX165)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Handwritten digit recognition using combination of neural network classifiers\",\"authors\":\"A. Khofanzad, C. Chung\",\"doi\":\"10.1109/IAI.1998.666880\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A new classification scheme for handwritten digit recognition is proposed. The method is based on combining the decisions of two multilayer perceptron (MLP) artificial neural network classifiers operating on two different feature types. The first feature set is defined on the pseudo Zernike moments of the image whereas the second feature type is derived from the shadow code of the image using a newly defined projection mask. A MLP network is employed to perform the combination task. The performance is tested on a data base of 15000 samples and the advantage of the combination approach is demonstrated.\",\"PeriodicalId\":373701,\"journal\":{\"name\":\"1998 IEEE Southwest Symposium on Image Analysis and Interpretation (Cat. No.98EX165)\",\"volume\":\"14 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"1998 IEEE Southwest Symposium on Image Analysis and Interpretation (Cat. No.98EX165)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IAI.1998.666880\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"1998 IEEE Southwest Symposium on Image Analysis and Interpretation (Cat. No.98EX165)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IAI.1998.666880","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Handwritten digit recognition using combination of neural network classifiers
A new classification scheme for handwritten digit recognition is proposed. The method is based on combining the decisions of two multilayer perceptron (MLP) artificial neural network classifiers operating on two different feature types. The first feature set is defined on the pseudo Zernike moments of the image whereas the second feature type is derived from the shadow code of the image using a newly defined projection mask. A MLP network is employed to perform the combination task. The performance is tested on a data base of 15000 samples and the advantage of the combination approach is demonstrated.