Abstract
Digital image forensics is a trending research domain that validates the authenticity of the digital images. The traditional methods invested time on detecting the device used for capturing and identifying the traces. Nowadays, it is interesting to note that the illumination deviations in the image provide an effective trace for detecting the forgeries in the image. Accordingly, a method is developed for detecting the spliced image based on the illumination features. Initially, the human faces in the composite image are detected, and the three-dimensional model of all the faces is derived using the landmark-based 3D morphable model (L3DMM). The light coefficients are determined using the 3D shape model for extracting the features. To identify the spliced/pristine images in the input composite image, neural network (NN) is used, which is trained using the standard back-propagation algorithm. The experiments were conducted on DSO-1 and DSI-1 datasets. Performance metrics such as accuracy, true positive rate (TPR), true negative rate (TNR) and ROC are used to prove the efficiency of the proposed method.
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
Zhou, J., Ni, J., & Rao, Y. (2017). Block-based convolutional neural network for image forgery detection. In International Workshop on Digital Watermarking (pp. 65–76). Springer, Berlin.
Redi, J. A., Taktak, W., & Dugelay, J.-L. (2011). Digital image forensics: A booklet for beginners. Multimedia Tools and Application, 51(1), 133–162.
Carvalho, T., Faria, F. A., Pedrini, H., Da Torres, R. S., & Rocha, A. (2016). Illuminant-based transformed spaces for image forensics. IEEE Transactions on Information Forensics and Security, 11(4), 720–733.
Liu, Q., Cao, X., Deng, C., & Guo, X. (2011). Identifying image composites through shadow matte consistency. IEEE Transactions on Information Forensics and Security, 6(3), 1111–1122.
Bermano, A. H., et al. (2014). Exposing photo manipulation from shading and shadows. Siggraph, 1(212), 1–12.
Peng, B., Wang, W., Dong, J., & Tan, T. (2017). Optimized 3D lighting environment estimation for image forgery detection. IEEE Transactions on Information Forensics and Security, 12(2), 479–494.
Viola, P., Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR, December 8–14, 2001.
Peng, B., Wang, W., Dong, J., Tan, T. (2016). Automatic detection of 3d lighting inconsistencies via a facial landmark based morphable model. In IEEE International Conference on Image Processing (ICIP), September 2016.
Tahmasebi, P., & Hezarkhani, A. (2012). A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation. Computers & Geosciences, 42, 18–27.
Sapna, S., Tamilarasi, A., Pravin Kumar, M. (2012). Backpropagation learning algorithm based on Levenberg Marquardt algorithm. CS & IT-CSCP, pp. 393–398.
DSO-1 and DSI-1 dataset, https://recodbr.wordpress.com/code-n-data/#dso1_dsi1. Accessed on December 2018.
Kee, E., Farid, H. (2010). Exposing digital forgeries from 3-D lighting environments. In 2010 IEEE International Workshop on Information Forensics and Security (WIFS), IEEE, Conference Proceedings (pp. 1–6).
Wei, F., Kai, W., Cayre, F., Zhang, X. (2012). 3D lighting-based image forgery detection using shape-from-shading. In Signal Processing Conference (EUSIPCO), 2012 Proceedings of the 20th European, Conference Proceedings (pp. 1777–1781).
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
Vinolin, V., Sucharitha, M. (2021). Spliced Image Detection in 3D Lighting Environments Using Neural Networks. In: Satapathy, S., Bhateja, V., Janakiramaiah, B., Chen, YW. (eds) Intelligent System Design. Advances in Intelligent Systems and Computing, vol 1171. Springer, Singapore. https://doi.org/10.1007/978-981-15-5400-1_15
Download citation
DOI: https://doi.org/10.1007/978-981-15-5400-1_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5399-8
Online ISBN: 978-981-15-5400-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)