Face recognition and detection using Random forest and combination of LBP and HOG features

The effective facial recognition method should perform well in unregulated environments based on video broadcast to satisfy the demands of applications in real-world However, this still remains a big challenge for most current face recognition algorithms that will affect the accuracy of the system. This study was conducted to develop face recognition method based on video broadcast under illumination variation, facial expressions, different pose, orientation, occlusion, nationality variation and motion. Viola-Jones algorithm was applied to improve face detection which is these method have proven to detect the faces in an uncontrolled environment in the real world simply and high accuracy. A combination of Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) descriptors was conducted for faces features extraction purpose. These descriptors have proven to be lower computational time. The latest and accurate technique was applied for face classification based on Random Forest classifier (RF). To evaluate the efficiency of the Random Forest classifier, compared it with Support Vector Machine classifiers (SVM) is done with different existing feature extraction methods. Four experiments were implemented on Mediu staff database and excellent results have reported the efficiency of proposed algorithm average recognition accuracy 97.6% The Computer Vision and Image Processing MAT LAB 2016b Toolboxes was used for coding the desired system, dataset based on videos.