omar ezz (7 résultats)

Etat : New.

Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Today's machine learning is widely used in diverse areas. For example, fraudulent systems, recommended systems, exploited prediction, and many other applications. One of these applications, is being exploited in this search. This paper presents an approach to detecting a person's gender through the front face image by using extraction features and classification techniques. Gender prediction can be a very useful method in HCI (Human Computer Interaction) systems. As a very powerful method of extracting data, the classification is used here to collect class data and to classify the gender as either male or female. To extract data features, Local Binary Pattern (LBP) is used, whereas the Random Forest (RF) algorithm of classification is used to gauge the maximum accuracy. Various database models were used in this search: ORL database, FEI database, Jaffe database, and CUHK database where JAFFE database gave a very high level of accuracy which is 99.89% in contrast CUHK database which gave a lower level of accuracy 76.18% with relative stability. Details of the prediction model and results model are reported in this paper. 80 pp. Englisch.

Etat : New. Print on Demand.

Etat : New. PRINT ON DEMAND.

Etat : New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Omar EzzMaster s degree in Computer Science with a specialization in Artificial Intelligence.Today s machine learning is widely used in diverse areas. For example, fraudulent systems, recommended systems, exploited prediction, .

Taschenbuch. Etat : Neu. This item is printed on demand - Print on Demand Titel. Neuware -Today's machine learning is widely used in diverse areas. For example, fraudulent systems, recommended systems, exploited prediction, and many other applications. One of these applications, is being exploited in this search. This paper presents an approach to detecting a person's gender through the front face image by using extraction features and classification techniques. Gender prediction can be a very useful method in HCI (Human Computer Interaction) systems. As a very powerful method of extracting data, the classification is used here to collect class data and to classify the gender as either male or female. To extract data features, Local Binary Pattern (LBP) is used, whereas the Random Forest (RF) algorithm of classification is used to gauge the maximum accuracy. Various database models were used in this search: ORL database, FEI database, Jaffe database, and CUHK database where JAFFE database gave a very high level of accuracy which is 99.89% in contrast CUHK database which gave a lower level of accuracy 76.18% with relative stability. Details of the prediction model and results model are reported in this paper.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 80 pp. Englisch.

Taschenbuch. Etat : Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - Today's machine learning is widely used in diverse areas. For example, fraudulent systems, recommended systems, exploited prediction, and many other applications. One of these applications, is being exploited in this search. This paper presents an approach to detecting a person's gender through the front face image by using extraction features and classification techniques. Gender prediction can be a very useful method in HCI (Human Computer Interaction) systems. As a very powerful method of extracting data, the classification is used here to collect class data and to classify the gender as either male or female. To extract data features, Local Binary Pattern (LBP) is used, whereas the Random Forest (RF) algorithm of classification is used to gauge the maximum accuracy. Various database models were used in this search: ORL database, FEI database, Jaffe database, and CUHK database where JAFFE database gave a very high level of accuracy which is 99.89% in contrast CUHK database which gave a lower level of accuracy 76.18% with relative stability. Details of the prediction model and results model are reported in this paper.