Application of Artificial Intelligence in Adaptive Face Recognition System

• Published in: 2021 IEEE 11th International Conference on System Engineering and Technology (ICSET) pp. 263 - 268
• Main Authors: Garcia, Rhose Anne C., Lacayanga, Raymond Paolo, Cruz, Febus Reidj G.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06-11-2021
• Subjects: adaptive face recognition; Face detection; Face recognition; Feature extraction; Histograms; Internet of Things; Lighting; local binary pattern histogram; Raspberry Pi; Surveillance
• ISSN: 2470-640X
• DOI: 10.1109/ICSET53708.2021.9612439

Adaptive facial recognition includes the features of artificial intelligence (AI) technology, internet of things (IoT) devices, and wireless fidelity (Wi-Fi) connection. The application of Artificial Intelligence was used to detect faces from the captured images. Using video image to extract features from the face, Local Binary Pattern Histogram (LBPH) algorithm was used. The ideal distance between the subject and the webcam must be 30 cm for minimum percent error. The study proposes a designed face recognition system of surveillance cameras that adapts through the changes of the features of the person by re-training the AI by saving various images of it. This utilizes the component Raspberry Pi 4 where the local binary pattern histogram is applied. Based on the results, the proposed method was able to produce an overall detection accuracy of 91.72% and an average processing time of 1.4 seconds. The output shows very promising results for face detection devices in the field of face recognition monitoring system.