Email this article Automatic Detection and Correction for Glossy Reflections in Digital Photograph
Abstract
The popularization of digital technology has made shooting digital photos and using related applications a part of daily life. However, the use of flash, to compensate for low atmospheric lighting, often leads to overexposure or glossy reflections. This study proposes an auto-detection and inpainting technique to correct overexposed faces in digital photography. This algorithm segments the skin color in the photo as well as uses face detection and capturing to determine candidate bright spots on the face. Based on the statistical analysis of color brightness and filtering, the bright spots are identified. Finally, bright spots are corrected through inpainting technology. From the experimental results, this study demonstrates the high accuracy and efficiency of the method.
Keywords
References
[1] R.T. Tan, K. Ikeuchi, “Seperating Reflection Components of Textured Surfaces Using a Single Image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, 2005, pp. 178 – 193.
doi:10.1109/TPAMI.2005.36
PMid:15688556
[2] Robby T. Tan, Katsushi Ikeuchi, “Reflection Components Decomposition of Textured Surfaces using Linear Basis Functions,” The 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), Vol. 1, 2005, pp. 125 – 131.
[3] S. Lin, Y. Li, S.B. Kang, X. Tong, H.-Y. Shum, “Diffuse-Specular Separation and Depth Recovery from Image Sequences,” Proceedings of European Conference on Computer Vision, 2002, pp. 210–224.
[4] S.P. Mallick, T.E. Zickler, D.J. Kriegman, P.N. Belhumeur, “Beyond Lambert: Reconstructing Specular Surfaces Using Color,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 2005, pp. 619–626.
[5] H.L Shen, Q.Y. Cai, “Simple and Efficient Method for Specularity Removal in an Image,” Applied Optics, Vol. 48, No. 14, 2009, pp. 2711–2719.
doi:10.1364/AO.48.002711
PMid:19424394
[6] J. S. Schildkraut, and R. Gray, “A Fully Automatic Redeye Detection and Correction Algorithm,” IEEE International Conference on Image Processing, Vol. I, 2002, pp. 801 – 803.
[7] A. Mufit Ferman, “Automatic Detection of Red-Eye Artifacts in Digital Color Photos,” 15th IEEE International Conference Image Processing, 2008, pp.617 – 620.
doi:10.1109/ICIP.2008.4711830
[8] Duan-Sheng, Chen and Zheng-Kai, Liu, “A Novel Approach to Detect and Correct Highlighted Face Region in Color Image,” Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS’03), 2003, pp. 7 – 12.
[9] P. Kakumanu, S. Makrogiannis, N. Bourbakis, “A Survey of Skin-Color Modeling and Detection Methods,” Pattern Recognition, Vol. 40, 2007, pp. 1106-1122.
doi:10.1016/j.patcog.2006.06.010
[10] Vezhnevets V, Sazonov V, Andreeva A, “A Survey on Pixel based Skin Color Detection Techniques,” In GraphiCon, 2003, pp.85-92.
[11] Georgy Kukharev, Adam Nowosielski, “Visitor Identification Elaborating Real Time Face Recognition System”, The 12th Winter School on Computer Graphics (WSCG), 2004, pp. 157-164.
[12] Nobuyuki Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on System, Man, and Cybernetics. SMC-9(1), 1979, pp. 62-66.
[13] T. Lui, E. Izquierdo, “Automatic Detection of Human Faces in Natural Scene Images by Use of Skin Colour and Edge Distribution,” The International Workshop on Image Analysis for Multimedia Interactive Services, 2004, pp. 112 – 117.
[14] Rong-Chi Chang and Timothy K. Shih, “Multilayer Inpainting on Digitalized Artworks,” Journal of Information Science Engineering, Vol.24, 2008, pp.1241-1255.
[15] M. Bertalmío, “Strong-continuation, Contrast-invariant Inpainting with a Third-order Optimal PDE,” IEEE Transactions Image Processing, Vol. 15, 2006, pp. 1934 – 1938.
doi:10.1109/TIP.2006.877067
PMid:16830913
[16] Pesal Koirala, Markku Hauta-Kasari, and Jussi Parkkinen, “Highlight Removal from Single Image,” 11th International Conference on Advanced Concepts for Intelligent Vision Systems, 2009, pp. 176-187.
doi:10.1007/978-3-642-04697-1_17
Full Text: PDF