An Accurate System for Face Detection and Recognition

Abstract

During the last few years, Local Binary Patterns (LBP) has aroused increasing interest in image processing and computer vision. LBP was originally proposed for texture analysis, and has proved a simple yet powerful approach to describe local structures. It has been extensively exploited in many applications, for instance, face image analysis, image and video retrieval, environment modeling, visual inspection, motion analysis, biomedical and aerial image analysis, remote sensing. Face recognition is an interesting and challenging problem, and impacts important applications in many areas such as identification for law enforcement, authentication for banking and security system access, and personal identification among others. In this paper we are concerned with face recognition in a video stream using Local Binary Pattern histogram with processed data. First we will detect faces by using a combination of Haar cascade files that uses skin detection, eye detection and nose detection as input of LBP to increase the accuracy of the proposed recognition system. Also, our system can be used to build a dataset of faces and names to be used in a recognition step. The experimental results have shown that the proposed system can achieve accuracy of recognition up to 96.5% which was better than the relevant methods.

Technique for recognizing faces using a hybrid of moments and a local binary pattern histogram

“…Digital image moments provide a very elegant way to describe the binary image area with a small number of intuitive and highly descriptive values. The equation ( 4) describes the public equation of any order moment [28]:…”

A novel hybrid face recognition framework based on a low-resolution camera for biometric applications

“…The Viola-Jones algorithm is a significant face detection method developed by Viola and Jones back in 2001 [8]- [11], [30]. The Viola-Jones algorithm follows three stages namely, haar classifier, integral image, and cascading classifier.…”

“…Irgens et al [10] implemented the Viola-Jones algorithm in field programmable gate arrays (FPGA) platform for video surveillance and tracking applications. Ali et al [11] proposed the modified local binary pattern histogram (MLBPH) method for face detection and recognition in a video stream and here Haar cascades were used for skin, eye, and nose detection of the human face.…”

A smart login system using face detection and recognition by ORB algorithm

“…Kumar et al the researchers proposed a review paper based on face detection techniques [15]. There are many researchers used face recognition and detection system in various purposes; even they developed a security system for face recognition [16][17][18][19][20][21]. From the above-mentioned research works, we have had some idea relevant to the system and conducted this research to overcome the previous limitations and to introduce the new idea.…”