二维图像识别的简单不变神经网络

Thirteenth National Radio Science Conference. NRSC '96 Pub Date : 1996-03-19 DOI:10.1109/NRSC.1996.551116

A. Abo-Zaid

{"title":"二维图像识别的简单不变神经网络","authors":"A. Abo-Zaid","doi":"10.1109/NRSC.1996.551116","DOIUrl":null,"url":null,"abstract":"A simple invariant neural network has been proposed. The network has invariance against scale and, rotation changes, in addition to the inherent shift of starting point on the image contour. This invariance comes from the new use of the MT-transform as a feature vector in a pre-processing stage. Thus, a complete invariance has been achieved, without any complexity in the network. Testing of the network, shows about a 100% recognition rate.","PeriodicalId":127585,"journal":{"name":"Thirteenth National Radio Science Conference. NRSC '96","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1996-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A simple invariant neural network for 2-D image recognition\",\"authors\":\"A. Abo-Zaid\",\"doi\":\"10.1109/NRSC.1996.551116\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A simple invariant neural network has been proposed. The network has invariance against scale and, rotation changes, in addition to the inherent shift of starting point on the image contour. This invariance comes from the new use of the MT-transform as a feature vector in a pre-processing stage. Thus, a complete invariance has been achieved, without any complexity in the network. Testing of the network, shows about a 100% recognition rate.\",\"PeriodicalId\":127585,\"journal\":{\"name\":\"Thirteenth National Radio Science Conference. NRSC '96\",\"volume\":\"31 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1996-03-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Thirteenth National Radio Science Conference. NRSC '96\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NRSC.1996.551116\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thirteenth National Radio Science Conference. NRSC '96","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NRSC.1996.551116","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

提出了一种简单的不变神经网络。该网络对尺度和旋转变化具有不变性，除了图像轮廓上的起始点固有的移位。这种不变性来自于在预处理阶段将mt变换作为特征向量的新使用。因此，在网络中没有任何复杂性的情况下，实现了完全不变性。经过测试，该网络的识别率约为100%。

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

A simple invariant neural network for 2-D image recognition

A simple invariant neural network has been proposed. The network has invariance against scale and, rotation changes, in addition to the inherent shift of starting point on the image contour. This invariance comes from the new use of the MT-transform as a feature vector in a pre-processing stage. Thus, a complete invariance has been achieved, without any complexity in the network. Testing of the network, shows about a 100% recognition rate.

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

Thirteenth National Radio Science Conference. NRSC '96

自引率

0.00%

发文量