A proficient approach for face detection and recognition using machine learning and high‐performance computing

Abstract

The objective of this article is to increase the efficiency of face recognition in the aspect of a dynamic frame. Studies were carried out that focus on maintaining the high detection rate as well as increasing the accuracy. The study was conducted by considering the current recording of the dynamic frame of randomly selected people walking on a treadmill. Here, the variety of facial features was studied and extracted using different viewing angles on the subject. The existence of a huge amount of datasets and economical processing power is subject to value enhancement in the presence of a convolutional neural network (CNN) on different object identification and realization criteria. These methodologies with excellent knowledge of deep learning techniques that subjects to enhance the potential of the machine to learn the face values. CNN is capable to identify faces, positive positioning facial benchmarks, estimating postures and understanding faces in interconnected images and dynamic video frames.In this article, we present a novel phase detector technique that is rapid and has the potential of recognizing faces with huge changes. This is performed by a technique of using adopted CNN and recurrent neural network's subpart long-short term memory technique in a particular way so that the objective of bringing improvement in the reorganization procedure can be fulfilled.

Emotion Recognition of Online Education Learners by Convolutional Neural Networks

“…The Extended Cohn-Kanade Dataset (CK+) was collected and proposed by Lucey in 2010 and extended based on Cohn-Kanade Dataset (CK). It is the most widely used facial expression dataset captured under controlled laboratory conditions at present [ 23 ]. In order to be compatible with the seven basic expressions in the Fer2013 dataset, contempt expressions with a small sample size were removed in this experiment, and 3 to 5 frames were intercepted from each image sequence as expression samples in this experiment [ 24 ].…”