使用时空关联模型的手印数字识别

Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 1992-06-15 DOI:10.1109/CVPR.1992.223277

T. Fontaine, L. Shastri

{"title":"使用时空关联模型的手印数字识别","authors":"T. Fontaine, L. Shastri","doi":"10.1109/CVPR.1992.223277","DOIUrl":null,"url":null,"abstract":"A connectionist model for recognizing unconstrained handprinted digits is described. Instead of treating the input as a static signal, the image is canned over time and converted into a time-varying signal. The temporalized image is processed by a spatiotemporal connectionist network. The resulting system offers shift-invariance along the temporalized axis, a reduction in the number of free parameters, and the ability to process images of arbitrary length. For a set of real-world ZIP code digit images, the system achieved a 99.1% recognition rate on the training set and a 96.0% recognition rate on the test with no rejections. A 99.0% recognition rate on the test set was achieved when 14.6% of the images were rejected.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Handprinted digit recognition using spatiotemporal connectionist models\",\"authors\":\"T. Fontaine, L. Shastri\",\"doi\":\"10.1109/CVPR.1992.223277\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A connectionist model for recognizing unconstrained handprinted digits is described. Instead of treating the input as a static signal, the image is canned over time and converted into a time-varying signal. The temporalized image is processed by a spatiotemporal connectionist network. The resulting system offers shift-invariance along the temporalized axis, a reduction in the number of free parameters, and the ability to process images of arbitrary length. For a set of real-world ZIP code digit images, the system achieved a 99.1% recognition rate on the training set and a 96.0% recognition rate on the test with no rejections. A 99.0% recognition rate on the test set was achieved when 14.6% of the images were rejected.<<ETX>>\",\"PeriodicalId\":325476,\"journal\":{\"name\":\"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition\",\"volume\":\"35 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1992-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.1992.223277\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.1992.223277","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 13

摘要

描述了一种用于识别无约束手印数字的联结主义模型。不是将输入作为静态信号处理，而是将图像随时间保存并转换为时变信号。时间化后的图像通过时空连接网络进行处理。由此产生的系统提供了沿时间轴的平移不变性，减少了自由参数的数量，并且能够处理任意长度的图像。对于一组真实世界的邮政编码数字图像，系统在训练集上达到了99.1%的识别率，在测试中达到了96.0%的识别率，没有拒绝。当14.6%的图像被拒绝时，测试集的识别率达到了99.0%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Handprinted digit recognition using spatiotemporal connectionist models

A connectionist model for recognizing unconstrained handprinted digits is described. Instead of treating the input as a static signal, the image is canned over time and converted into a time-varying signal. The temporalized image is processed by a spatiotemporal connectionist network. The resulting system offers shift-invariance along the temporalized axis, a reduction in the number of free parameters, and the ability to process images of arbitrary length. For a set of real-world ZIP code digit images, the system achieved a 99.1% recognition rate on the training set and a 96.0% recognition rate on the test with no rejections. A 99.0% recognition rate on the test set was achieved when 14.6% of the images were rejected.<>

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

自引率

0.00%

发文量