Applying a Deep Learning Convolutional Neural Network (CNN) Approach for Building a Face Recognition System: A Review
Binyam Tesfahun Liyew · Journal of Emerging Technologies and Innovative Research · 2017
Deep learning is a new advanced research area of machine learning. The Deep learning come up with a successful learning approach to make the machine learning closer to Artificial intelligence. In Deep learning, multiple processing layers are organized for simulating mathematical models that learn characteristics of data with various levels of abstraction. These techniques have greatly improved the state-of-the-art in pattern recognition. Deep learning finds out complex structure in large datasets by the help of backpropagation technique to show how the AI supposed to change its internal parameters that are used to calculate the characterization in each layer from the characterization in the previous layer. Basically, the Deep Convolutional nets have been used in the development to deal with images, speech, video, and audio. In contrast, recurrent nets give out a bright way on sequential data like text and speech. Recently, the deep learning CNN has reached propitious results in face recognition. In this survey paper, we are going to study about CNN-based face recognition systems. One of the objective of this study is to know more about the field of pattern recognition in our case face recognition, which is very interesting and have a tremendous benefits in real life applications that require peoples identity, such as Payments, Passport immigration, Access and security, Criminal identification, Advertising, Healthcare, Students attendance, and etc.