Novel Illumination-invariant Face Recognition Approach via Reflectance-luminance and Local Matching Model with Weighted Voting System

MD. Ashiquzzaman *

Department of Electrical and Electronic Engineering, American International University-Bangladesh (AIUB), Dhaka, Bangladesh.

Sadman Shahriar Alam

Department of Electrical and Electronic Engineering, American International University-Bangladesh (AIUB), Dhaka, Bangladesh.

Abu Shufian

Department of Electrical and Electronic Engineering, American International University-Bangladesh (AIUB), Dhaka, Bangladesh.

Protik Parvez Sheikh

Department of Electrical and Electronic Engineering, American International University-Bangladesh (AIUB), Dhaka, Bangladesh.

Ahmed Hossain Siddiqui

Department of Electrical and Electronic Engineering, Faculty of Engineering, Stamford University Bangladesh, Bangladesh.

*Author to whom correspondence should be addressed.


Abstract

In this study, a novel approach has been introduced for face recognition that is unaffected by changes in illumination. This method is based on the reflectance-luminance model and incorporates local matching using a weighted voting technique to eliminate any artifacts present in the retina images. A total of 37 different linear and nonlinear filters were tested, including high pass and low pass filters, to achieve the reflectance component of the image, which remains invariant to changes in illumination. Among these filters, the maximum filter, which is a simple filter with low computational complexity, yielded the best results in extracting the illumination invariants. It was observed that the illumination invariants obtained through this method outperformed other methods such as QI, SQI, and image enhancement techniques in terms of recognition accuracy. Importantly, the proposed method does not require any prior knowledge about the facial shape or illumination conditions and can be applied to individual images independently. Unlike many existing methods, this approach does not rely on multiple images during the training stage and does not require any parameter selection to generate the illumination invariants. To further enhance the robustness of illumination, a weighted voting system was introduced. Certain regions of the image, which may adversely affect the recognition outcome due to poor illumination, occlusion, noise, or lack of distinctive information, were identified using predefined factors such as grayscale mean, image entropy, and mutual information. The proposed method was also compared to other face recognition methods in the presence of occlusions, and it demonstrated promising results outperforming existing methods. The Python algorithm successfully detects obstructed faces, genders, and ages in videos with a face matching accuracy between 80.9% to 96.9% based on proximity.

Keywords: Face recognition, haar feature, viola-jones method, raspberry pi


How to Cite

Ashiquzzaman, M., Alam , S. S., Shufian , A., Sheikh , P. P., & Siddiqui , A. H. (2024). Novel Illumination-invariant Face Recognition Approach via Reflectance-luminance and Local Matching Model with Weighted Voting System. Journal of Engineering Research and Reports, 26(6), 124–138. https://doi.org/10.9734/jerr/2024/v26i61167

Downloads

Download data is not yet available.

References

Nilsson, Nils J. The Quest for Artificial Intelligence. Cambridge University Press; 2009.

De Leeuw, Karl Bergstra.. The history of information security: A comprehensive handbook. Elsevier. 2007, Jan;266.

Gates Kelly. The biometric future: Facial recognition technology and the culture of surveillance. NYU Press. 2011;48–49. ISBN 9780814732090. Available:https://eholgersson.files.wordpress.com/2019/08/our-biometric-future-facial-recognition-technology-and-the-culture-of-surveillance.pdf

Malay K Kundu, Sushmita Mitra, Debasis Mazumdar, Sankar K Pal eds. Perception and Machine intelligence: first indo-japan conference, PerMIn 2012, Kolkata, India, January 12-13, 2011, Proceedings. Springer Science & Business Media. 2012; 29. ISBN 9783642273865

Wechsler Harry. Malay K Kundu, Sushmita Mitra (eds.). Reliable face recognition methods: System design, implementation and evaluation. Springer Science & Business Media. 2009;11–12. ISBN 9780387384641.

Jun Wang, Laiwan Chan, DeLiang Wang eds. Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part II. Springer Science & Business Media. 2012;198. ISBN 978354046482 7. Li Stan Z, Jain Anil K. Handbook of face recognition. Springer Science & Business Media. 2005;14–15. ISBN 9780387405957.

Rana Manish. Review on various face recognition databases. I-manager's Journal on Pattern Recognition; 2022. Available: 10.26634/jpr.9.2.19189

An application of viola jones method for face recognition for absence process efficiency (Journal of Physics) article: Rudolfo Rizki Damanik et al J. Phys. Conf. Ser. 2018;1007:012013.

Available:https://www.researchgate.net/publication/324854259_An_application_of_viola_jones_method_for_face_recognition_for_absence_process_efficiency

A Hendro Triatmoko, S Hadi Pramono, HS Dachlan. Penggunaan metode viola-jones dan algoritma eigen eyes dalam sistem kehadiran pegawai. Jurnal EECCIS. 2014, Juni;8(1) Available:https://jurnaleeccis.ub.ac.id/index.php/eeccis/article/view/234/207

Chen SK Chang YH. 2014 International Conference on Artificial Intelligence and Software Engineering (AISE2014). DEStech Publications, Inc; 2014.

Alam SS, Islam NNAJ, Ahammad KT. Hand gesture detection using haar classifier with appropriate skin color, kernel sizing & auto thresholding. International Journal of Scientific & Engineering Research. 2017;8(3):98.

ЖЕ Амиргалиева. Development of a modified viola-jones algorithm for face recognition. Habaršy - Abaj atyndaġy Almaty universitetì. Fizika-matematika seriâsy; 2023. Available:10.51889/2022-1.1728-7901.08

Sheikh Tasfia, Saha Reno. Face mask detection using viola-jones and cascade classifier; 2022 Available:10.1109/ICAISS55157.2022.10011114

Ari Prasetya D, Nurviyanto I. Deteksi wajah metode viola jones pada opencv menggunakan pemrograman python. Simposium Nasional RAPI XI FT UMS; 2012.

Available:https://www.raspberrypi.org/products/raspberry-pi-3-model-b/

Raspberry Pi Foundation - About Us. Raspberry Pi. Retrieved 23 August 2020.

Sheikh, Protik Parvez et al. Analysis of patient health using arduino and monitoring system. Journal of Engineering Research and Reports. 2024;26(3):25-33.

Available:https://www.elecrow.com/wiki/index.php?title=3.5_Inch_480x320_TFT_Display_with_ Touch_Screen_for_Raspberry_Pi#Feature

Available:https://github.com/raspberrypi/documentation/blob/master/hardware/raspberrypi/power/ README.md

Available:https://www.electronics.com.bd/rasberry-pi-camera-module-board-rev-28mp webcam-video-1080p-720p-also-for-raspberry

Available:https://bdspeedytech.com/index.php?route=product/product&product_id=214

Available:https://bdspeedytech.com/index.php?route=product/product&product_id=675

A review paper on face recognition techniques; 2023. Available:10.1109/icaccs57279.2023.10112907