[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124852-en":3,"doc-seo-124852-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124852,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","A Real-Time Autonomous Machine Learning System for Face Recognition Using Pre-Trained Convolutional Neural Networks","A real-time autonomous machine learning system for face recognition combines pre-trained convolutional neural networks with autonomous learning and real-time classification. Facial images are encoded using a pre-trained ResNet50 model from a camera stream, while cognitive tracking agents monitor multiple people. A novelty detection algorithm using a Naive Multinomial Bayes model and an SVM-based novelty check triggers learning for newly detected faces. Experiments show accurate learning of new identities under favorable conditions, with recognition quality depending on novelty detection reliability. The approach supports security, access control, and personalized services while reducing training data needs.","European Research Studies Journal Volume XXVII, Special Issue 2, 2024  \npp. 3-13  \nA Real-Time Autonomous Machine Learning System for Face Recognition Using Pre-Trained Convolutional Neural Networks  \nSubmitted 18/02/24, 1st revision 16/03/24, 2nd revision 20/04/24, accepted 16/05/24  \nMichał Maj 1, Jacek Korzeniak2, Józef Stokłosa3, Paweł Barwiak4, Bartłomiej Bartnik5, Łukasz Maciura6  \nAbstract:  \nPurpose: This paper aims to present a novel real-time, autonomous machine learning system for face recognition. This system employs pre-trained convolutional neural networks for encoding facial images and applies a Naive Multinomial Bayes model for autonomous learning and real-time classification.  \nDesign/Methodology/Approach: The system leverages a pre-trained ResNet50 model to encode facial images from a camera, while cognitive tracking agents collaborate with machine learning models to monitor the faces of multiple people. A novelty detection algorithm based on a Support Vector Machine (SVM) classifier checks whether a detected face is new or already recognized. The system autonomously starts the learning process if an unrecognized face is identified. Real-time classification of individuals relies on a Naive Multinomial Bayes model, with special agents tracking each face.  \nFindings: Experiments demonstrated that the system can accurately learn new faces appearing within the camera frame in favorable conditions. The key determinant of successful recognition and learning is the novelty detection algorithm, which, if it fails, may assign multiple identities or group new individuals into existing clusters.  \nPractical Implications: This system offers a practical solution for real-time, autonomous face recognition, with potential applications in security, access control, and personalized services. Its ability to quickly learn new faces while maintaining classification accuracy ensures adaptability in dynamic environments.  \nOriginality/Value: The research introduces an innovative approach by combining pretrained neural networks with autonomous learning and a novelty detection algorithm to classify faces in real-time. This hybrid method ensures rapid and accurate face recognition while minimizing the need for extensive training data or prolonged training times.  \n1Corresponding Author: Netrix/ WSEI University , Lublin, Poland, [e-mail:](e-mail: michal.maj@netrix.com.pl)[ ](e-mail: michal.maj@netrix.com.pl)[michal.maj@netrix.com.pl](e-mail: michal.maj@netrix.com.pl);  \n2WSEI University, Lublin, Poland, [e-mail:](e-mail: jacek.korzeniak@wsei.lublin.pl)[ j](e-mail: jacek.korzeniak@wsei.lublin.pl)[acek.korzeniak@wsei.lublin.pl](e-mail: jacek.korzeniak@wsei.lublin.pl);  \n3WSEI University, Lublin, Poland, e-mail: jozef.stokł[osa@wsei.lublin.pl](osa@wsei.lublin.pl);  \n4WSEI University, Lublin, Poland, e-mail: paweł.[barwiak@wsei.lublin.pl](barwiak@wsei.lublin.pl);  \n5Wyższa Szkoła Biznesu-National Louis University, e-mail: [bbartnik@wsb-nlu.edu.pl](bbartnik@wsb-nlu.edu.pl);  \n6Netrix , Lublin, Poland, e-mail: [lukasz.maciura@netrix.com.pl](lukasz.maciura@netrix.com.pl);  \nKeywords: Real-Time Face Recognition, Autonomous Systems, Machine Learning, Convolutional Neural Networks, Deep Learning, Computer Vision, Artificial Intelligence.  \nJEL codes: C45, C61, C84, L11, L86, O33..  \nPaper type: Research article.  \n1. Introduction  \nThe system can learn unsupervised to recognize speakers based on microphone or audio file data, so it does not require any training data. The system checks whether a given signal belongs to speech for each time window. Then, after the previous condition is met, the system checks whether the signal comes from a new (unknown) speaker. If so, automatic learning occurs, and a new identifier is assigned; if not, the previously trained face is recognized.  \nThe most important output of the system is the identifiers of newly recognized speakers, which can be integrated with other systems (e.g., super-system-robot or intelli","cbCaindEnOGPlDbU","https://ap.wps.com/l/cbCaindEnOGPlDbU","pdf",409147,1,11,"English","en",105,"# Abstract\n# 1. Introduction\n# 2. Literature Review","[{\"question\":\"How does the system encode face images and perform real-time classification?\",\"answer\":\"It uses a pre-trained ResNet50 model to encode faces captured by a camera, then applies a Naive Multinomial Bayes model for real-time classification while agents track each face.\"},{\"question\":\"What triggers automatic learning of a new identity?\",\"answer\":\"An SVM-based novelty detection algorithm checks whether a detected face is new or already recognized; if the face is unrecognized, autonomous learning starts and a new identifier is assigned.\"},{\"question\":\"What is the main factor affecting recognition and learning accuracy?\",\"answer\":\"The novelty detection algorithm. If it fails, the system may assign multiple identities or incorrectly merge new individuals into existing clusters.\"}]","A Real-Time Autonomous Machine Learning System for Face Recognition Using Pre-Trained Convolutional Neural Networks | PDF",1785895010,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-real-time-autonomous-machine-learning-system-for-face-recognition-using-pre-trained-convolutional-neural-networks","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-real-time-autonomous-machine-learning-system-for-face-recognition-using-pre-trained-convolutional-neural-networks/124852/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the system encode face images and perform real-time classification?","Question",{"text":75,"@type":76},"It uses a pre-trained ResNet50 model to encode faces captured by a camera, then applies a Naive Multinomial Bayes model for real-time classification while agents track each face.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What triggers automatic learning of a new identity?",{"text":80,"@type":76},"An SVM-based novelty detection algorithm checks whether a detected face is new or already recognized; if the face is unrecognized, autonomous learning starts and a new identifier is assigned.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the main factor affecting recognition and learning accuracy?",{"text":84,"@type":76},"The novelty detection algorithm. If it fails, the system may assign multiple identities or incorrectly merge new individuals into existing clusters.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]