一种新的基于网络模型的ICA滤波器用于人脸识别

2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) Pub Date : 2017-12-01 DOI:10.1109/ICCWAMTIP.2017.8301462

Yongqing Zhang, Tianyu Geng, Ying Cai

{"title":"一种新的基于网络模型的ICA滤波器用于人脸识别","authors":"Yongqing Zhang, Tianyu Geng, Ying Cai","doi":"10.1109/ICCWAMTIP.2017.8301462","DOIUrl":null,"url":null,"abstract":"Despite the great success of deep learning convolution networks, researchers are not yet clear about its feature learning mechanism and optimal network configuration. In this paper, we present a cascaded linear convolution network based on ICA filters, termed ICANet. ICANet mainly includes three parts: convolution layer, binary hash and block histogram. The results show that ICANet has a very good performance in face recognition tasks.","PeriodicalId":259476,"journal":{"name":"2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"A novel network model based ICA filter for face recognition\",\"authors\":\"Yongqing Zhang, Tianyu Geng, Ying Cai\",\"doi\":\"10.1109/ICCWAMTIP.2017.8301462\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Despite the great success of deep learning convolution networks, researchers are not yet clear about its feature learning mechanism and optimal network configuration. In this paper, we present a cascaded linear convolution network based on ICA filters, termed ICANet. ICANet mainly includes three parts: convolution layer, binary hash and block histogram. The results show that ICANet has a very good performance in face recognition tasks.\",\"PeriodicalId\":259476,\"journal\":{\"name\":\"2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)\",\"volume\":\"16 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCWAMTIP.2017.8301462\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCWAMTIP.2017.8301462","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

尽管深度学习卷积网络取得了巨大的成功，但研究人员对其特征学习机制和最优网络配置尚不清楚。在本文中，我们提出了一个基于ICA滤波器的级联线性卷积网络，称为ICANet。ICANet主要包括三个部分:卷积层、二值哈希和块直方图。结果表明，ICANet在人脸识别任务中具有很好的性能。

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 novel network model based ICA filter for face recognition

Despite the great success of deep learning convolution networks, researchers are not yet clear about its feature learning mechanism and optimal network configuration. In this paper, we present a cascaded linear convolution network based on ICA filters, termed ICANet. ICANet mainly includes three parts: convolution layer, binary hash and block histogram. The results show that ICANet has a very good performance in face recognition tasks.

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

2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)

自引率

0.00%

发文量