Abstract
Image fusion is widely used in many fields, such as medical research and remote sensing nowadays. To better address thermal human face image recognition problem in surveillance field, extensive research is done using advanced fusion techniques such as Gabor Filtering and Genetic Algorithm. While traditional fusion techniques are often neglected in most cases. For efficient industrial usage, we compared the recognition rates of six conventional image fusion techniques using the benchmark Tufts Face Databases as data source and using recent iteratively reweighted regularized robust coding (IR3C) algorithm as evaluation method. Final results showed a great improvement in thermal image recognition rates even compared with advanced methods. Especially the Weighted Average technique and Principal Component Analysis (PCA) shows 99.488% and 98.721% recognition accuracy with a stable performance in relatively small-scale dataset. Discrete Wavelet Transform (DWT), Pyramid Fusion and Select Maximum technique also maintained over 93% recognition rates. Discussions of those high-performance fusion techniques for particular conditions in surveillance field and certain limitations of our work are proposed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blum, R.S., Liu, Z.: Multi-Sensor Image Fusion and Its Applications. Taylor & Francis, Boca Raton (2005)
Thomas, C., Ranchin, T., Wald, L., et al.: Synthesis of multispectral images to high spatial resolution: a critical review of fusion methods based on remote sensing physics. IEEE Trans. Geosci. Remote Sens. 46(5), 1301–1312 (2008)
Simone, G., Farina, A., Morabito, F.C., et al.: Image fusion techniques for remote sensing applications. Inf. Fusion 3(1), 3–15 (2002)
James, A.P., Dasarathy, B.V.: Medical image fusion: a survey of the state of the art. Inf. Fusion 19, 4–19 (2014)
Zhou, Z.Q., Wang, B., Li, S., et al.: Perceptual fusion of infrared and visible images through a hybrid multi-scale decomposition with Gaussian and bilateral filters. Inf. Fusion 30, 15–26 (2016)
Kao, W.C., Hsu, C.C., Kao, C.C., et al.: Adaptive exposure control and real-time image fusion for surveillance systems. In: 2006 IEEE International Symposium on Circuits and Systems (2006)
Sadhasivam, S.K., Keerthivasan, M.B., Muttan, S.: Implementation of max principle with PCA in image fusion for surveillance and navigation application. ELCVIA: Electron. Lett. Comput. Vis. Image Anal. 10, 1–10 (2011)
Cai, Y., Huang, K., Tan, T., et al.: Context enhancement of nighttime surveillance by image fusion. In: 18th International Conference on Pattern Recognition (ICPR 2006), vol. 1, no. 1 (2006)
Hanif, M., Ali, U.: Optimized visual and thermal image fusion for efficient face recognition. In: 2006 9th International Conference on Information Fusion. IEEE (2006)
Singh, S., Gyaourova, A., Bebis, G., et al.: Infrared and visible image fusion for face recognition. In: Biometric Technology for Human Identification, vol. 54, no. 4 (2004)
Panetta, K., Wan, Q.W., Agaian, S., et al.: A comprehensive database for benchmarking imaging systems. IEEE Trans. Pattern Anal. Mach. Intell. 42, 509–520 (2018)
Yang, M., Zhang, L., Yang, J., et al.: Regularized robust coding for face recognition. IEEE Trans. Image Process. 22(5), 1753–1766 (2012)
Sahu, D.K., Parsai, M.P.: Different image fusion techniques–a critical review. Int. J. Mod. Eng. Res. (IJMER) 2(5), 4298–4301 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, C., Li, X., Wang, W. (2021). Image Fusion for Improving Thermal Human Face Image Recognition. In: Sun, F., Liu, H., Fang, B. (eds) Cognitive Systems and Signal Processing. ICCSIP 2020. Communications in Computer and Information Science, vol 1397. Springer, Singapore. https://doi.org/10.1007/978-981-16-2336-3_39
Download citation
DOI: https://doi.org/10.1007/978-981-16-2336-3_39
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2335-6
Online ISBN: 978-981-16-2336-3
eBook Packages: Computer ScienceComputer Science (R0)