L'identification humaine est la fonctionnalité tendance dans la plupart des logiciels, qui est utilisé par les organisations de sécurité. La plupart de ce type de logiciel est orienté uniquement pour l'identification humaine en le recherchant dans la base de données du visage. Nous proposons le logiciel qui identifie l'humain en streaming vidéo par certains paramètres de classification. Dans notre travail, nous classons les personnes en âge, sexe et groupes raciaux en fonction des traits du visage. Il y a 3 algorithmes de reconnaissance faciale : Eigenfaces, Fisherfaces et Histogrammes de motifs binaires locaux ; qui conviennent pour les tâches de classification. Pour chaque algorithme, des classificateurs avec 1500 images provenant du même ensemble de données sont formés. Le but de la recherche est de déterminer le plus approprié parmi les algorithmes de reconnaissance faciale choisis pour la tâche d'identification humaine en fonction des paramètres de classification. À cette fin, une expérience de test de performance, qui détermine le temps de reconnaissance et le taux des algorithmes de reconnaissance faciale, est effectuée. Selon les résultats de l'expérience, Fisherfaces est sélectionné comme algorithme le plus approprié pour notre tâche d'identification humaine.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne
Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Human identification is the trending feature in most software, which is used by security organizations. Most of this type of software is oriented only for human identification by searching him from face database. We propose the software that identifies human in video-streaming by some classification parameters. In our work we classify people into age, gender, and race groups based on facial features. There are 3 face recognition algorithms: Eigenfaces, Fisherfaces and Local Binary Patterns Histograms; that are suitable for classification task. For every algorithm classifiers with 1500 images from same dataset are trained. Purpose of the research is to determine the most appropriate one from chosen face recognition algorithms for human identification task based on classification parameters. For this purpose performance test experiment, which determines the recognition time and rate of face recognition algorithms, is performed. According to the results of experiment, Fisherfaces is selected as most appropriate algorithm for our human identification task. 76 pp. Englisch. N° de réf. du vendeur 9783659669835
Quantité disponible : 2 disponible(s)
Vendeur : moluna, Greven, Allemagne
Etat : New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Akhmetov YerlanYerlan Akhmetov has been interested in IT and has programmed softwaresince 2008. He received his B.Sc from Suleyman Demirel University and his M.Sc from International Information Technologies University. He currently r. N° de réf. du vendeur 14642047
Quantité disponible : Plus de 20 disponibles
Vendeur : buchversandmimpf2000, Emtmannsberg, BAYE, Allemagne
Taschenbuch. Etat : Neu. This item is printed on demand - Print on Demand Titel. Neuware -Human identification is the trending feature in most software, which is used by security organizations. Most of this type of software is oriented only for human identification by searching him from face database. We propose the software that identifies human in video-streaming by some classification parameters. In our work we classify people into age, gender, and race groups based on facial features. There are 3 face recognition algorithms: Eigenfaces, Fisherfaces and Local Binary Patterns Histograms; that are suitable for classification task. For every algorithm classifiers with 1500 images from same dataset are trained. Purpose of the research is to determine the most appropriate one from chosen face recognition algorithms for human identification task based on classification parameters. For this purpose performance test experiment, which determines the recognition time and rate of face recognition algorithms, is performed. According to the results of experiment, Fisherfaces is selected as most appropriate algorithm for our human identification task.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 76 pp. Englisch. N° de réf. du vendeur 9783659669835
Quantité disponible : 1 disponible(s)
Vendeur : AHA-BUCH GmbH, Einbeck, Allemagne
Taschenbuch. Etat : Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - Human identification is the trending feature in most software, which is used by security organizations. Most of this type of software is oriented only for human identification by searching him from face database. We propose the software that identifies human in video-streaming by some classification parameters. In our work we classify people into age, gender, and race groups based on facial features. There are 3 face recognition algorithms: Eigenfaces, Fisherfaces and Local Binary Patterns Histograms; that are suitable for classification task. For every algorithm classifiers with 1500 images from same dataset are trained. Purpose of the research is to determine the most appropriate one from chosen face recognition algorithms for human identification task based on classification parameters. For this purpose performance test experiment, which determines the recognition time and rate of face recognition algorithms, is performed. According to the results of experiment, Fisherfaces is selected as most appropriate algorithm for our human identification task. N° de réf. du vendeur 9783659669835
Quantité disponible : 1 disponible(s)
Vendeur : preigu, Osnabrück, Allemagne
Taschenbuch. Etat : Neu. Human Identification in Video-streaming | Based on Classification Parameters | Yerlan Akhmetov | Taschenbuch | 76 S. | Englisch | 2015 | LAP LAMBERT Academic Publishing | EAN 9783659669835 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu. N° de réf. du vendeur 104891308
Quantité disponible : 5 disponible(s)