Face Detection and Recognition Using Viola-Jones with PCA-LDA and Square Euclidean Distance

Abstract

Abstract-In this paper, an automatic face recognition system is proposed based on appearance-based features that focus on the entire face image rather than local facial features. The first step in face recognition system is face detection. Viola-Jones face detection method that capable of processing images extremely while achieving high detection rates is used. This method has the most impact in the 2000's and known as the first object detection framework to provide relevant object detection that can run in real time. Feature extraction and dimension reduction method will be applied after face detection. Principal Component Analysis (PCA) method is widely used in pattern recognition. Linear Discriminant Analysis (LDA) method that used to overcome drawback the PCA has been successfully applied to face recognition. It is achieved by projecting the image onto the Eigenface space by PCA after that implementing pure LDA over it. Square Euclidean Distance (SED) is used. The distance between two images is a major concern in pattern recognition. The distance between the vectors of two images leads to image similarity. The proposed method is tested on three databases (MUCT, Face94, and Grimace). Different number of training and testing images are used to evaluate the system performance and it show that increasing the number of training images will increase the recognition rate.

Applying Gamma and Histogram Equalization Algorithms for Improving System-performance of Face Recognition-based CNN

“…The proposed system tried to process low-quality images during the preprocessing stage, in which the Viola-Jones cannot detect faces. It has been trained on a faces94 data set, which contains 3060 images divided into 124 classes, according to the number of people in the database, to take images, they used artificial lights [1]. In some images, the Viola-Jones was unable to detect faces, either because of poor lighting or because of the tough reflection of light on the faces.…”

“…The process of detecting faces and recognizing faces is of great importance in most modern applications and systems [1], [2]. Detecting the face and determining its location in the image is a very important step that precedes the face recognition step, as it reduces the excess information during the face recognition process, thus increasing the speed and accuracy of the system [3], [4].…”

Adaptive Variable Extractions With Lda for Classification of Mixed Variables, and Applications to Medical Data

“…As such, this suggests that the independent variables are either near-linearly or linearly reliant on one another (Artoni et al, 2018), which may be due to displaying similar information. Moreover, utilising PCA in classification has been proven workable in facial recognition problems by Barnouti et al (2016) and Deshpande and Ravishhankar (2017), and has consequently become a notable option in simplifying data before constructing the classification model (i.e. Jamal et al, 2018;Li, 2017;Nasution et al, 2018).…”

"Faces Tracking from Multi-Surveillance Camera (FTMSC)"

“…As illustrate before, there are 180,000 feature values, in spite of the fact that need to be choses only a few features. For this reason, the Ada Boost algorithm is using to select that only the best features [16]. Cascaded classifiers: Viola and Jones created a stream architecture of classifiers from a chain of strong classifiers for to speedily rejected unfavorable area of the image.…”