ENHANCED HUMAN FACE RECOGNITION USING LBPH DESCRIPTOR, MULTI-KNN, AND BACK-PROPAGATION NEURAL NETWORK

Abstract

Face recognition has become a fascinating field for researchers. The motivation behind the enormous interest in the topic is the need to improve the accuracy of many real-time applications. The complexity of the human face and the changes due to different effects make it more challenging to design as well as implement a powerful computational system for human face recognition. In this work, we presented an enhanced approach to improve human face recognition using a Back-Propagation Neural Network (BPNN) and features extraction based on the correlation between the training images. A key contribution of this work is the generation of a new set called the T-Dataset from the original training dataset, which is used to train the BPNN. We generated the T-Dataset using the correlation between the training images without using a common technique of image density. The correlated T-Dataset provides a high distinction layer between the training images, which helps the BPNN to converge faster and achieve better accuracy. Data and features reduction are essential in the face recognition process, and researchers have recently focused on the modern Neural Network (NN). Therefore, we used a Local Binary Pattern Histogram (LBPH) descriptor to prove that there is potential improvement even using traditional methods. We applied five distance measurement algorithms and then combined them to obtain the T-Dataset, which we fed into the BPNN. We achieved higher face recognition accuracy with less computational cost compared to the current approach by using reduced image features. We test the proposed framework on two small datasets, the YALE and AT&T datasets, as the ground truth. We achieved tremendous accuracy. Furthermore, we evaluate our method on one of the state-of-the-art benchmark datasets, Labeled Faces in the Wild (LFW), where we produce a competitive face recognition performance.

Existing System

Direction coded LBP (DLBP) and transition LBP (TLBP), Linear Discriminate Analysis (LDA)

Proposed System

The main contribution of this work is an enhanced human face recognition using LBPH, multi-KNN, and BPNN. The strength of our approach is based on adding a step after the features extraction and dimension reduction to obtain a clear distinction T-Dataset, which will be used to train the BPNN. The novelty consists in a new T-Dataset achieved by taking into consideration the correlation between the training images, unlike existing methods that rely only on the density of the images. This system starts with some of the preprocessing operations, which helps to reduce the processing time. Thereafter, we used the LBPH method to reduce the image dimension by selecting significant features. The new T-Dataset is obtained using five distance methods. In the final phase, we feed the T-Dataset to our BPNN for offline training. We tested our framework on three datasets, Yale, ORL, and LFW. We have achieved a higher recognition rate accuracy.

Architecture

BLOCK DIAGRAM