Robust face recognition algorithm based on linear operators discrete wavelet transformation and simple linear regression
[ X ]
Tarih
2018
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Assoc Computing Machinery
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Face recognition system performance would sharply decrease if there were noticeable issues in the face images conditions such as light variation, contrast, and brightness issues that can deeply affect the system performance directly. The process of face analysis comes here to put the face image environment in a spot of light to enable the interested researchers to find out the factors that have vital effects on these systems. In this paper, we are producing a hybrid method that based on discrete wavelet transformation DWT output and linear edge detection operators such as Sobel, Prewitt and Roberts output as a solution to cover some of these related image condition issues. For feature extraction, a new method based on simple linear regression slope with -SLP name-that proved the ability to find features in critical regions of the face, and eigenface based on principal components analysis PCA used with linear edge detection operators for comparison, studying the interrelation among them, and investigation the effects on the performance of the proposed system. A segmentation used to handle the details of a face image by dividing dataset images to equaled size blocks. Modified Artificial neural network MANN used for classification and all results obtained evaluated. The proposed method examined and evaluated with different face datasets using modified MANN classifier. The experimental results were displaying the superiority of the proposed algorithm over the algorithms that used the state-of-art techniques.
Açıklama
1rst International Conference on Data Science, E-Learning and Information Systems (DATA) -- OCT 01-02, 2018 -- Univ Distancia Madrid, Madrid, SPAIN
alazzawi, abdulbasit/0000-0001-9210-7080
alazzawi, abdulbasit/0000-0001-9210-7080
Anahtar Kelimeler
Face Analysis, Face Recognition, Network, PCA SLP, MANN
Kaynak
Proceedings of the First International Conference on Data Science, E-Learning and Information Systems 2018 (Data'18)
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
