实现智能生物识别系统对人脸的检测和分类

Michaela Chudobova, J. Kubícek, R. Ščurek, Marek Hutter
{"title":"实现智能生物识别系统对人脸的检测和分类","authors":"Michaela Chudobova, J. Kubícek, R. Ščurek, Marek Hutter","doi":"10.5593/sgem2022/2.1/s07.06","DOIUrl":null,"url":null,"abstract":"This article deals with the design and implementation of an intelligent biometric system that allows the detection and classification of a person's face from static image data and creates a system for evaluating its reliability. In its introductory part, it theoretically describes applied biometrics and biometric systems for security identification and user verification, and also deals with the theory of the description of algorithms for human face detection and recognition. Subsequently, the authors use the MATLAB programming language, which is highly optimized for modern processors and memory architectures, to focus on the implementation and testing of a biometric system using Viola-Jones algorithms and a convolutional neural network with a pre-trained network NetNet. Convolutional neural networks (CNN) are the most recognized and popular deep-learning neural networks, which are based on layers that perform two-dimensional (2D) convolution of input data with learned filters. In the final part there is a discussion where, based on the results of testing, the robustness and efficiency of the proposed intelligent biometric system is objectively evaluated. The results allow for the continued development of other pre-trained artificial neural networks, variable implementations for facial recognition, but also other things, such as the recognition of potentially dangerous people.","PeriodicalId":375880,"journal":{"name":"22nd SGEM International Multidisciplinary Scientific GeoConference Proceedings 2022, Informatics, Geoinformatics and Remote Sensing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"IMPLEMENTATION OF INTELLIGENT BIOMETRIC SYSTEM FOR FACE DETECTION AND CLASSIFICATION\",\"authors\":\"Michaela Chudobova, J. Kubícek, R. Ščurek, Marek Hutter\",\"doi\":\"10.5593/sgem2022/2.1/s07.06\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article deals with the design and implementation of an intelligent biometric system that allows the detection and classification of a person's face from static image data and creates a system for evaluating its reliability. In its introductory part, it theoretically describes applied biometrics and biometric systems for security identification and user verification, and also deals with the theory of the description of algorithms for human face detection and recognition. Subsequently, the authors use the MATLAB programming language, which is highly optimized for modern processors and memory architectures, to focus on the implementation and testing of a biometric system using Viola-Jones algorithms and a convolutional neural network with a pre-trained network NetNet. Convolutional neural networks (CNN) are the most recognized and popular deep-learning neural networks, which are based on layers that perform two-dimensional (2D) convolution of input data with learned filters. In the final part there is a discussion where, based on the results of testing, the robustness and efficiency of the proposed intelligent biometric system is objectively evaluated. The results allow for the continued development of other pre-trained artificial neural networks, variable implementations for facial recognition, but also other things, such as the recognition of potentially dangerous people.\",\"PeriodicalId\":375880,\"journal\":{\"name\":\"22nd SGEM International Multidisciplinary Scientific GeoConference Proceedings 2022, Informatics, Geoinformatics and Remote Sensing\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"22nd SGEM International Multidisciplinary Scientific GeoConference Proceedings 2022, Informatics, Geoinformatics and Remote Sensing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5593/sgem2022/2.1/s07.06\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"22nd SGEM International Multidisciplinary Scientific GeoConference Proceedings 2022, Informatics, Geoinformatics and Remote Sensing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5593/sgem2022/2.1/s07.06","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本文讨论了一个智能生物识别系统的设计和实现,该系统允许从静态图像数据中检测和分类人脸,并创建了一个评估其可靠性的系统。在导论部分,从理论上描述了用于安全识别和用户验证的生物识别和生物识别系统的应用,并讨论了人脸检测和识别算法的理论描述。随后,作者使用针对现代处理器和内存架构进行高度优化的MATLAB编程语言,重点关注使用Viola-Jones算法和卷积神经网络与预训练网络NetNet的生物识别系统的实现和测试。卷积神经网络(CNN)是最受认可和流行的深度学习神经网络,它基于使用学习滤波器对输入数据进行二维(2D)卷积的层。最后,根据测试结果,对所提出的智能生物识别系统的鲁棒性和效率进行了客观评估。该结果允许继续开发其他预训练的人工神经网络,面部识别的可变实现,以及其他事情,例如识别潜在危险的人。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
IMPLEMENTATION OF INTELLIGENT BIOMETRIC SYSTEM FOR FACE DETECTION AND CLASSIFICATION
This article deals with the design and implementation of an intelligent biometric system that allows the detection and classification of a person's face from static image data and creates a system for evaluating its reliability. In its introductory part, it theoretically describes applied biometrics and biometric systems for security identification and user verification, and also deals with the theory of the description of algorithms for human face detection and recognition. Subsequently, the authors use the MATLAB programming language, which is highly optimized for modern processors and memory architectures, to focus on the implementation and testing of a biometric system using Viola-Jones algorithms and a convolutional neural network with a pre-trained network NetNet. Convolutional neural networks (CNN) are the most recognized and popular deep-learning neural networks, which are based on layers that perform two-dimensional (2D) convolution of input data with learned filters. In the final part there is a discussion where, based on the results of testing, the robustness and efficiency of the proposed intelligent biometric system is objectively evaluated. The results allow for the continued development of other pre-trained artificial neural networks, variable implementations for facial recognition, but also other things, such as the recognition of potentially dangerous people.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信