Proposing an Image Enhancement Algorithm Using CNN for Applications of Face Recognition System
Phat Nguyen Huu, Loc Hoang Bao, Hoang Lai The
Journal of Advances in Mathematics and Computer Science · pp. 1–14 · Published 17 Jan 2020
10.9734/jamcs/2019/v34i630230Abstract
Many researches have been going on since last two decades for object recognition, shape matching, and pattern recognition in the field of computer vision. Face recognition is one of the important issues in object recognition and computer vision. Many face image datasets, related competitions, and evaluation programs have encouraged innovation, producing more powerful facial recognition technology with promising results. In recent years, we have witnessed tremendous improvements in face recognition performance from complex deep neural network architectures trained on millions of face images. Face recognition is the most important biometric and stills many challenges such as pose variation, illumination variation, etc. In order to achieve the desired performance when deploying in reality, the methods depend on many factors. One of the main factors is quality of input image. Therefore, facial recognition systems is installed outdoors which are always affected by extreme weather events such as haze, fog. The existence of haze dramatically degrades the visibility of outdoor images captured in inclement weather and affects many high-level computer vision tasks such as detection and recognition system. In this paper, we propose a preprocessing method to remove haze from input images that enhances their quality to improve effectiveness and recognition rate for face identification based on Convolutional Neural Network (CNN) based on the available datasets and our self-built data. To perform the proposed method for outdoor face recognition system, we have improved the system accuracy from 90.53% to 98.14%. The results show that the proposed method improves the quality of the image with other traditional methods.
References (22)
- 1 Going deeper with convolutions [DOI]
- 2 Visualizing and Understanding Convolutional Networks [DOI]
- 3 Backpropagation Applied to Handwritten Zip Code Recognition [DOI]
- 4 Single Image Haze Removal Using Dark Channel Prior [DOI]
- 5 DeepFace: Closing the Gap to Human-Level Performance in Face Verification [DOI]
- 6 Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks [DOI]
- 7 Distance Metric Learning for Large Margin Nearest Neighbor Classification [DOI]
- 8 Understanding of a convolutional neural network [DOI]
- 9 Visibility in bad weather from a single image [DOI]
- 10 Single image dehazing [DOI]
- 11 A Closed-Form Solution to Natural Image Matting [DOI]
- 12 Contrast restoration of weather degraded images [DOI]
- 13 High-accuracy stereo depth maps using structured light [DOI]
- 14 Fast visibility restoration from a single color or gray level image [DOI]
- 15 Efficient Image Dehazing with Boundary Constraint and Contextual Regularization [DOI]
- 16 Deeply learned face representations are sparse, selective, and robust [DOI]
- 17 Instant dehazing of images using polarization [DOI]
- 18 Chromatic framework for vision in bad weather [DOI]
- 19 Neurocomputing: Foundations of Research
- 20 Bayesian Face Revisited: A Joint Formulation [DOI]
- 21 Automatic recovery of the atmospheric light in hazy images [DOI]
- 22 Deep Learning Face Representation by Joint Identification-Verification [DOI]
Cited by 5
Phat Nguyen Huu, Loc Hoang Bao · Journal of Information Systems and Telecommunication (JIST) · 2021
Bo Fu · Journal of Intelligent Systems · 2023
Showing 2 of 5 known citations — external sources report more than can currently be individually listed.
Related research
- A Systematic Literature Review of Machine Learning Methods in Healthcare — shares topic coverage
- Application of Deep Learning Techniques in the Development of Predictive Maintenance and Fault Detection in Electric Motors — shares topic coverage
- Comparative Analysis of Fully Convolutional Networks (FCN), SegNet, and U-Net for Semantic Segmentation of Synthetic Wafer Map Defect Patterns — shares topic coverage
- Image Compression Based on Deep Learning: A Review — shares topic coverage
- Detection of Diabetic Retinopathy Based on Convolutional Neural Networks: A Review — shares topic coverage
Article metrics
Real usage data collected on this platform.
29
Page views
0
PDF downloads
8
Outbound clicks
5
Citations
Views over time
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
Traffic sources
Referring site, by host.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.