International Journal of Innovative Research in Computer and Communication Engineering

ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines

| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |


TITLE Face Recognition Using Visible, Thermal and Fused Images with LBP, PCA, SVM and Naive Bayes
ABSTRACT Visible face recognition can be affected by illumination and shadows, while thermal images capture emitted radiation and fused images provide complementary appearance information. This study evaluates a lightweight classical framework for unknown-ID face verification across Visible, Thermal and Fusion image conditions. Images are processed at 128 × 128 pixels with grayscale conversion and CLAHE. Local Binary Pattern (LBP) and Principal Component Analysis (PCA) representations are evaluated with linear Support Vector Machine (SVM) and Gaussian Naive Bayes, yielding twelve configurations. The updated experiment uses a subject-disjoint protocol: S01–S13 are used for training and S14–S17 are held out for testing, with zero subject overlap. Each reported modality is evaluated on 258 verification pairs. The strongest configuration is Visible LBP–SVM at 80.23% accuracy, followed by Visible PCA–SVM at 74.03% and Visible LBP–Naive Bayes at 70.93%. Thermal LBP–SVM reaches 68.60%, while Fusion LBP–SVM reaches 61.63%. These results describe the current saved unknown-ID test run and should not be compared as if they were the earlier image-level, subject-overlapping classification experiment.
AUTHOR KOMAL GADEKAR, SANGEETA N. KAKARWAL, NITIN S. MAGAR Master of Engineering, Department of Computer Science and Engineering, International Centre of Excellence in Engineering and Management, Chhatrapati Sambhajinagar, Maharashtra, India Professor, Department of Computer Science and Engineering, International Centre of Excellence in Engineering and Management, Chhatrapati Sambhajinagar, Maharashtra, India Assistant Professor, Department of Computer Science and Engineering, International Centre of Excellence in Engineering and Management, Chhatrapati Sambhajinagar, Maharashtra, India
VOLUME 189
DOI DOI: 10.15680/IJIRCCE.2026.1410013
PDF pdf/13_Face Recognition Using Visible, Thermal and Fused Images with LBP, PCA, SVM and Naive Bayes.pdf
KEYWORDS
References [1] D. Anghelone, C. Chen, A. Ross, and A. Dantcheva, “Beyond the visible: A survey on cross-spectral face recognition,” arXiv:2201.04435, 2022.
[2] X. Wang, J. Peng, S. Zhang, B. Chen, Y. Wang, and Y. Guo, “A survey of face recognition,” arXiv:2212.13038, 2022.
[3] S. Hu et al., “A polarimetric thermal database for face recognition research,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), 2016, pp. 119–126.
[4] D. Poster et al., “A large-scale, time-synchronized visible and thermal face dataset,” in Proc. IEEE/CVF Winter Conf. Applications of Computer Vision (WACV), 2021, pp. 1559–1568.
[5] M. S. Sarfraz and R. Stiefelhagen, “Deep perceptual mapping for thermal to visible face recognition,” arXiv:1507.02879, 2015.
3. PROPOSED METHODOLOGY
[7] D. A. Socolinsky and A. Selinger, “Thermal face recognition in an operational scenario,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2004, pp. 1012–1019.
[8] R. S. Ghiass, O. Arandjelović, A. Bendada, and X. Maldague, “Infrared face recognition: A comprehensive review of methodologies and databases,” Pattern Recognition, vol. 47, no. 9, pp. 2807–2824, 2014.
[9] X. Chen, P. J. Flynn, and K. W. Bowyer, “Infrared and visible face recognition,” Computer Vision and Image Understanding, vol. 99, no. 3, pp. 332–358, 2005.
[10] T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971–987, 2002.
[11] M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991.
[12] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995.
[13] K. Zuiderveld, “Contrast limited adaptive histogram equalization,” in Graphics Gems IV, P. S. Heckbert, Ed. Academic Press, 1994, pp. 474–485.
[14] X. Zhang et al., “VIFB: A visible and infrared image fusion benchmark,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, 2020.
[15] A. George and S. Marcel, “Lightweight cross-spectral face recognition via contrastive alignment and distillation,” arXiv:2605.04769, 2026.
[16] S. N. Kakarwal and R. R. Deshmukh, “Analysis of retina recognition by correlation and covariance matrix,” in Proc. Third International Conference on Emerging Trends in Engineering and Technology, Goa, India, 2010, pp. 496–499.
[17] S. N. Kakarwal and R. R. Deshmukh, “Face recognition using supervised learning,” in Proc. WorldComp 2012, Las Vegas, USA, July 2012.
[18] M. M. Ambekar, S. N. Kakarwal, and S. S. Khedgikar, “Design, acquisition and collection of multiple-source databases to increase accuracy and level of security,” in Proc. IEEE International Conference ICSIDEMPC, 2020.
[19] S. R. Choudhari and S. N. Kakarwal, “Analysis of musical string instruments using k-NN,” in Proc. IEEE International Conference ICSIDEMPC, 2020.
[20] S. N. Kakarwal, K. P. Choudhari, and R. B. Patil, “Face recognition based on supervised learning,” in Proc. IEEE International Conference ICSIDEMPC, 2020.
[21] S. N. Kakarwal and A. S. Gawali, “Context aware human activity prediction in videos using hand-centric features and dynamic programming-based prediction algorithm,” Journal of Integrated Science and Technology, vol. 10, no. 1, pp. 11–17, 2022.
[22] S. N. Kakarwal and P. M. Paithane, “Automatic pancreas segmentation using ResNet-18 deep learning approach,” System Research and Information Technologies, no. 2, pp. 104–116, 2022, doi: 10.20535/SRIT.2308-8893.2022.2.08.
[23] A. Gawali and S. N. Kakarwal, “Enhancing early action prediction in videos through temporal composition of sub-actions,” Multimedia Tools and Applications, vol. 84, no. 8, pp. 4253–4281, published online 18 Mar. 2024, doi: 10.1007/s11042-024-18870-0.
[24] S. N. Kakarwal, R. Mapari, A. K. Jain, V. Sharma, P. P. Mane, J. R. Raja Kumar, and R. K. Pradhan, “Enhanced detection and segmentation of brain tumors using a Dense BW-CNN approach,” Journal of Engineering, vol. 2024, Article 1622294, 14 pages, 2024, doi: 10.1155/2024/1622294.
Each input image is converted to grayscale when needed, resized to 128 × 128 pixels using area interpolation, and enhanced with CLAHE (clipLimit 2.0; tileGridSize 8 × 8). Keeping these operations consistent across modalities reduces differences caused by preprocessing choices.
[26] S. N. Kakarwal, C. M. Gaikwad, and A. N. Ghule, “Classification based on soil attributes using non-imagery spectroscopic data,” in Proc. ICKE 2023, Dr. Babasaheb Ambedkar Marathwada University, Chhatrapati Sambhajinagar, India, 8–9 May 2023.
[27] F. Juefei-Xu et al., “NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops, 2015.
[28] C. Reale, N. M. Nasrabadi, H. Kwon, and R. Chellappa, “Deep heterogeneous face recognition networks based on cross-modal distillation and an equitable distance metric,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops, 2017.
[29] T. de Freitas Pereira and S. Marcel, “Heterogeneous face recognition using inter-session variability modelling,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops, 2016.
[30] K. Chaudhari, “Development of Thermal Infrared and Visible Imagery Face Database,” Copyright Office, Government of India, Copyright Diary No. 23164/2024-CO/L, Registration No. L-154687/2024, registered 27 September 2024.


Copyright © IJIRCCE 2020.All right reserved