Enhancing Detection Performance of Face Recognition Algorithm Using PCA-Faster R-CNN

Hashiru Isiaka Muhammad,Kabir Ibrahim Musa,Kabiru Umar,Abdullahi Abubakar,Abdulhakeem Ishola,Mustapha Lawal Abdulrahman

doi:10.24018/ejece.2021.5.3.321

Abstract

In this paper, we present a new face detection scheme using deep learning and achieving state-of-the-art recognition performance using real-world datasets. We designed and implemented a face recognition system using Principal Component Analysis (PCA) and Faster R Convolutional Neural Network (Faster R CNN). In particular, we improve the state-of-the-art Faster RCNN framework by using Principal Component Analysis (PCA) technique and Faster R CNN to detect and recognise faces in a face database. The Principal Component Analysis (PCA) was used to extract features and dimensionality reduction from the face database, while the Faster R Convolutional Neural Network algorithm was used to identify patterns in the dataset via training the neural network. The three real-world datasets used in our experiment are ORL, Yale, and California face dataset. When implemented on the ORL face dataset, the algorithm achieved average recognition accuracy of 99%, with a recognition time of 147.72 seconds for 10 runs, and the recognition time/image was 0.3 sec/image on 400 images. The Yale face dataset achieved average recognition accuracy of 99.24% with a recognition time of 63.45 seconds for 10 runs, and the recognition time/image was 0.53 sec/image on 120 images. Finally, on California Face Database (CFD), it achieved average recognition accuracy of 99.52% with a recognition time of 226.05 seconds for 10 runs, and the recognition time/image was 0.27 sec/image on 827 images. On the CFD dataset, however, the proposed approach has excellent classification performance when the recall ratio is high. The proposed method achieves a higher recall and accuracy ratio than the Faster RCNN without PCA method. For the F-score, the proposed method achieved 0.98, which is significantly higher than the 0.95 achieved by the Faster-RCNN. This demonstrates the superiority of our model performance-wise as against state-of-the-art, both in terms of accuracy and fast recognition. Therefore our model is more efficient when compared to the latest researches done in the area of facial recognition.

Highlights

Face detection is the preliminary stage for all systems that interact with human robots, computer-based, and visionbased such as the ASIMO robot by Honda, which has advanced face detection and recognition component [3]
One of the challenges with this approach is that the computational complexity is high for object detection compared to the recent Faster-Convolutional Neural Network (CNN)
This study aims to use Principal Component Analysis (PCA) to extract features from the face dataset and use Faster region-based convolutional neural network (R-CNN) to identify patterns in the dataset to build and deploy a face recognition model

Summary

Introduction

Face detection is the preliminary stage for all systems that interact with human robots, computer-based, and visionbased such as the ASIMO robot by Honda, which has advanced face detection and recognition component [3]. Face detection helps in tagging images on social media such as Facebook and Instagram, among others. Automatic face detection can be seen as the foundation stone of programs spinning around automatic facial images analysis, including face detection, face verification, gender or age recognition, face surveillance and tracking, relighting, and morphing. Embedded face detector can be found in digital cameras and smartphones used to focus the image to be detected automatically [3]. Research has shown that automatic face detection and facial feature recognition were first computer vision-based applications [20]. Face recognition is a well-studied research area in computer vision. Build face detectors, such as “Face detection based on YOLOv3” [23], can detect frontal faces quickly and accurately on face detections task

Objectives

Methods

Results

Conclusion