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}
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.