Abstract—Identity recognition is a very important task in intelligent surveillance systems. Today, identity recognition systems have achieved high accuracy and widely used in specific application areas such as recognition system based on retina imaging in immigration inspection, civil security and citizen management. In these systems, human is required to be submissive for data acquisition to identify themselves. However, the automated monitoring systems are required to be active for information retrieval and human is passively monitored in this situation. In this kind of approach, human recognition is still a challenging task for the overall system performance. This study proposes a solution for human identification based on the human face recognition in images extracted from conventional cameras at a low resolution and quality. Our proposed approach for human identification is based on a deep learning method for feature extraction and classification for human identification using a similarity estimation. This approach was evaluated on some standard databases which are available online and also on our own collected dataset. The results from the comparison to the state of the art approach illustrate that our proposed approach achieves high accuracy and is suitable for practical applications.
Index Terms—Personal identification, face image, feature extraction.
Van-Huy Pham is with the Information Technology Department, Ton Duc Thang University, Vietnam.
Diem- Phuc Tran is with Duy Tan University, Vietnam. Van-Dung Hoang is with the Intelligent Systems Lab., Quang Binh University, Vietnam (e-mail: firstname.lastname@example.org).
Cite: Van-Huy Pham, Diem-Phuc Tran, and Van-Dung Hoang, "Personal Identification Based on Deep Learning Technique Using Facial Images for Intelligent Surveillance Systems," International Journal of Machine Learning and Computing vol. 9, no. 4, pp. 465-470, 2019.Copyright © 2019 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).