Abstract For reliable face identification, the fusion process of multi-spectral vision features produces robust classification systems, this paper exploits the power of thermal facial image invariant moments features fused with the visible facial image invariant moments features to propose a new multi-spectral hybrid invariant moment fusion system for face identification. And employs Feed-forward neural network to train the moments' features and make decisions. The evaluation system uses databases of visible thermal pairs face images CARL and UTK-IRIS databases and gives an accuracy reaches 99%.

References

[1] Arnia F., Saddami K., and Munadi K., “Moment Invariant-Based Features for Jawi Character Recognition,” International Journal of Electrical and Computer Engineering, vol. 9, no. 3, pp. 2088-8708, 2019.

[2] Benamara N., Zigh E., Stambouli T., and Keche M., “Efficient Multispectral Face Recognition using Random Feature Selection and PSO-SVM,” in Proceedings of The 2nd International Conference on Networking, Information Systems and Security, New York, pp. 1-6, 2019.

[3] Bhowmik M., Bhattacharjee D., Nasipuri M., Basu D., and Kundu M., “Optimum Fusion of Visual And Thermal Face Images for Recognition,” in Proceedings of The 6th International Conference on Information Assurance and Security, Atlanta, pp. 311-316, 2010.

[4] Bhowmik M., De B., Bhattacharjee D., Basu D., and Nasipuri M., “Multisensor Fusion of Visual and Thermal Images for Human Face Identification Using Different SVM Kernels,” in Proceedings of The Long Island Systems, Applications and Technology Conference, Farmingdale, pp. 1-7, 2012.

[5] Bhowmik M., Saha K., Majumder S., Majumder G., Saha A., Sarma A., and Nasipuri M., Thermal Infrared Face Recognition-A Biometric Identification Technique For Robust Security System, Reviews, Refinements and New Ideas in Face Recognition, 2011.

[6] Celebi M. and Aslandogan Y., “A Comparative Study of Three Moment-Based Shape Descriptors,” in Proceedings of the International Conference on Information Technology: Coding and Computing, Las Vegas, pp. 788-793, 2005.

[7] Dong X., Wong K., Jin Z., and Dugelay J., “A Secure Visual-thermal Fused Face Recognition System Based on Non-Linear Hashing,” in Proceedings of The 21st International Workshop on Multimedia Signal Processing, Kuala Lumpur, pp. 1-6, 2019.

[8] El-Alfy E., Baig Z., and Abdel-Aal R., “A Novel Approach For Face Recognition Using Fused GMDH-Based Networks,” The International Arab Journal of Information Technology, vol. 15, no. 3, pp. 369-377, 2018.

[9] Espinosa-Duró V., Faundez-Zanuy M., and Mekyska J., “A New Face Database Simultaneously Acquired in Visible, Near- Infrared and Thermal Spectrums,” Cognitive Computation vol. 5, no. 1, pp. 119-135, 2013.

[10] Flusser J., Suk T., and Zitová B., 2D and 3D Image Analysis by Moments, John Wiley and Sons, 2016.

[11] Flusser J., Zitova B., and Suk T., Moments and Moment Invariants in Pattern Recognition, John Wiley and Sons, 2009.

[12] Gauch J., Multiresolution Image Shape Description, Springer Science and Business Media, 2012.

[13] Habeeb N., Hasson S., and Picton P., “Multi- Sensor Fusion Based on DWT, Fuzzy Histogram Equalization For Video Sequence,” The Internatonal Arab Journal of Information Technology, vol. 15, no. 5, pp. 825-830, 2018.

[14] Hamandi S., Rahma A., and Hassan R., “Comparative Study of Moments Shape Descriptors and Propose A New Hybrid Descriptor Technique,” in Proceedings of the 9th International Conference on Intelligent Computing and Information Systems, Cairo, pp. 194-201, 2019.

[15] Hamandi S., Rahma A., and Hassan R., “A New Hybrid Shape Moment Invariant Techniques for Face Identification in Thermal and Visible Visions,” in Proceedings of The 21st International Arab Conference on Information Technology, 6th of October City, pp. 1-9, 2020.

[16] Hamandi S., Rahma A., and Hassan R., “A New 412 The International Arab Journal of Information Technology, Vol. 18, No. 3A, Special Issue 2021 Hybrid Technique for Face Identification Based on Facial Parts Moments Descriptors,” Engineering and Technology Journal, vol. 39, no. 1B , pp. 117-128, 2021.

[17] Hammoud R., IRIS Thermal/Visible Face Database.

[Online]. Available: http://vcipl- okstate.org/pbvs/bench/index.html, Last Visited, 2021.

[18] Hu M., “Visual Pattern Recognition by Moment Invariants,” IRE Transactions on Information Theory, vol. 8, no. 2, pp. 179-187, 1962.

[19] Jasiński P. and Forczmański P., “Combined Imaging System for Taking Facial Portraits in Visible and Thermal Spectra,” in Proceedings of Image Processing and Communications Challenges, Cham, pp. 63-71, 2016..

[20] Kandasamy T. and Rajendran R., “Hybrid Algorithm with Variants for Feed Forward Neural Network,” The International Arab Journal of Information Technology, vol. 15, no. 2, pp. 240- 245, 2018..

[21] Kong S., Heo J., Abidi B., Paik J., and Abidi M., “Recent Advances in Visual and Infrared Face Recognition-A Review,” Computer Vision and Image Understanding, vol. 97, no.1, pp. 103-135, 2005.

[22] Mallikarjuna G., VijayaKumari G., and Babu G., “Face Recognition Applications Using Active Pixels,” International Journal of Engineering Research and Applications, vol. 2, no. 4, pp. 2248- 9622, 2019.

[23] Marcano-Cedeño A., Quintanilla-Dominguez J., Cortina-Januchs M., and Andina D., “Feature Selection Using Sequential Forward Selection and Classification Applying Artificial Metaplasticity Neural Network,” in Proceedings of The 36th Annual Conference on IEEE Industrial Electronics Society, Glendale, pp. 2845-2850, 2010.

[24] Mekyska J., Espinosa-Duró V., and Faundez- Zanuy M., “Face Segmentation: A Comparison Between Visible and Thermal Images,” in Proceedings of the 44th Annual International Carnahan Conference on Security Technology, pp. 185-189, 2010.

[25] Mohamed H., Negm A., Zahran M., and Saavedra O., “Assessment of Ensemble Classifiers Using The Bagging Technique for Improved Land Cover Classification of Multispectral Satellite Images,” The International Arab Journal of Information Technology, vol. 15, no. 2, pp. 270-277, 2014.

[26] Mukundan R., Ong S., and Lee P., “Image Analysis by Tchebichef Moments,” IEEE Transactions on Image Processing, vol. 10, no. 9, pp. 1357-1364, 2001..

[27] Pal A. and Singha A., “A Comparative Analysis of Visual and Thermal Face Image Fusion Based on Different Wavelet Family,” in Proceedings of the International Conference on Innovations in Electronics, Signal Processing and Communication, Shillong, pp. 213-218, 2017.

[28] Schmidhuber J., “Deep Learning in Neural Networks: An Overview,” Neural Networks, vol. 61, pp. 85-117, 2015.

[29] Shoja Ghiass R., Arandjelović O., Bendada A., and Maldague X., “Infrared Face Recognition: A Comprehensive Review of Methodologies and Databases,” Pattern Recognition, vol. 47, no. 9, pp. 2807-2824, 2014.

[30] Song X., Gao S., and Chen C., “A Multispectral Feature Fusion Network for Robust Pedestrian Detection,” Alexandria Engineering Journal, vol. 60, no. 1, pp. 73-85, 2021.

[31] Sonka M., Hlavac V., and Boyle R., Image Processing, Analysis, and Machine Vision, Cengage Learning, 2014.

[32] Viswanathan P., Krishna P., and Hariharan S., “Multimodal Biometric Invariant Moment Fusion Authentication System,” in Proceedings of The International Conference on Business Administration and Information Processing, Berlin, pp. 136-143, 2010. Multi-Spectral Hybrid Invariant Moments Fusion Technique… 413 Shaymaa Hamandi awarded her M.Sc. from Al Nahrain University, Computer science department in 2006. She worked at Baghdad Governorate as a manager of information technology department until 2011, programmed a lot of database systems for financial. Stock, and human resources departments. Then worked as a programmer in a public governorate library. Started her PhD studying in 2018 and now she is in the research stage. Her research interests include image processing, pattern recognition and biometrics. Research Gate: https://www.researchgate.net/profile/Shaymaa_Haman di EMAIL: 111797@student.uotechnology.edu.iq. Abdul Monem Rahma has an extensive background in Cryptography and Information Security Image Processing, Pattern Recognition and Biometrics. He received his PhD in Computer Science in 1984, from the Loughborough University of Technology in the United Kingdom, and become a professor in Computer Science since 2008. His main work experience involves teaching at Iraqi universities and supervising postgraduate students; He also was Deputy Dean of the Department of Computer Science, University of Technology, Iraq from 2005 to 2013. From 2013 to 2015, he became the Dean of the department. Now He is Lecturer and the head of the Department of Computer Engineering Techniques, Imam Ja’afar Al-Sadiq University. Prof. Rahma published 180 Papers, 4 Books in Computer Science; supervised 36 PhD and 66 M.Sc. students. ORCID 0000-0001-6323-9148 PHONE:+9647712890216 Research Gate: https://www.researchgate.net/profile/Abdul_Monem_R ahma Google Scholar: https://scholar.google.com/citations?user=63NQ8lcAA AAJ&hl=en&oi=ao EMAIL:110003@uotechnology.edu.iq Rehab Hassan Awarded her M.Sc. and Ph.D. degree from University of Technology, computer science department in 1995 and 2005, respectively. She taught at the University of Technology, Computer Science department. She published a lot of papers in the field of computer science and supervised Ph.D. and M.Sc. students. Her research interests include computer graphics image processing, and computer security. Research Gate: https://www.researchgate.net/profile/Rehab_Hassan EMAIL: 110019@uotechnology.edu.iq