Abstract
Today, digital cameras are widely used in taking photos. However, some photos lack detail and need enhancement. Many existing image enhancement algorithms are patch based and the patch size is always fixed throughout the image. Users must tune the patch size to obtain the appropriate enhancement. In this study, we propose an automatic image enhancement method based on adaptive patch selection using both dark and bright channels. The double channels enhance images with various exposure problems. The patch size used for channel extraction is selected automatically by thresholding a contrast feature, which is learned systematically from a set of natural images crawled from the web. Our proposed method can automatically enhance foggy or under-exposed/backlit images without any user interaction. Experimental results demonstrate that our method can provide a significant improvement in existing patch-based image enhancement algorithms.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Assefa M, Poulie T, Kervec J, et al., 2014. Correction of overexposure using color channel correlations. IEEE Global Conf on Signal and Information Processing, p.1078–1082. https://doi.org/10.1109/GlobalSIP.2014.7032287
Cai B, Xu X, Jia K, et al., 2016. DehazeNet: an end–to–end system for single image haze removal. IEEE Trans Image Process, 25(11):5187–5198. https://doi.org/10.1109/TIP.2016.2598681
Celik T, 2014. Spatial entropy–based global and local image contrast enhancement. IEEE Trans Image Process, 23(12):5298–5308. https://doi.org/10.1109/TIP.2014.2364537
Chang YC, Chang CM, 2010. A simple histogram modification scheme for contrast enhancement. IEEE Trans Consum Electron, 56(2):737–742. https://doi.org/10.1109/TCE.2010.5505995
Chen Y, Lin W, Zhang C, et al., 2013. Intra–and–interconstraint–based video enhancement based on piecewise tone mapping. IEEE Trans Circ Syst Video Technol, 23(1):74–82. https://doi.org/10.1109/TCSVT.2012.2203198
Fattal R, 2008. Single image dehazing. ACM Trans Graph, 27(3):1–9. https://doi.org/10.1145/1360612.1360671
Gonzalez RC, Wintz P, 1987. Digital Image Processing (2nd Ed.). Addison–Wesley, Boston, USA, p.484–486.
He K, Sun J, Tang X, 2011. Single image haze removal using dark channel prior. IEEE Trans Patt Anal Mach Intell, 33(12):2341–2353. https://doi.org/10.1109/TPAMI.2010.168
He K, Sun J, Tang X, 2013. Guided image filtering. IEEE Trans Patt Anal Mach Intell, 35(6):1397–1409. https://doi.org/10.1109/TPAMI.2012.213
Jain AK, 1989. Fundamentals of Digital Image Processing. Prentice–Hall, Inc., Upper Saddle River, NJ, USA.
Kopf J, Neubert B, Chen B, et al., 2008. Deep photo: modelbased photograph enhancement and viewing. ACM Trans Graph, 27(5):1–10. https://doi.org/10.1145/1409060.1409069
Li N, Liu Z, Lei J, et al., 2016. Automatic color image enhancement using double channels. Pacific–Rim Conf on Multimedia, p.74–83. https://doi.org/10.1007/978-3-319-48896-7_8
Liu Z, Zhang C, Zhang Z, 2007. Learning–based perceptual image quality improvement for video conferencing. IEEE Int Conf on Multimedia and Expo, p.1035–1038. https://doi.org/10.1109/ICME.2007.4284830
Nakai K, Hoshi Y, Taguchi A, 2013. Color image contrast enhancement method based on differential intensity/saturation gray–levels histograms. Int Symp on Intelligent Signal Processing and Communication Systems, p.445–449. https://doi.org/10.1109/ISPACS.2013.6704591
Narasimhan SG, Nayar SK, 2003. Contrast restoration of weather degraded images. IEEE Trans Patt Anal Mach Intell, 25(6):713–724. https://doi.org/10.1109/TPAMI.2003.1201821
Oakley JP, Bu H, 2007. Correction of simple contrast loss in color images. IEEE Trans Image Process, 16(2):511–522. https://doi.org/10.1109/TIP.2006.887736
Pizer SM, Amburn EP, Austin JD, et al., 1987. Adaptive histogram equalization and its variations. Comput Vision Graph Image Process, 39(3):355–368. https://doi.org/10.1016/S0734-189X(87)80186-X
Podpora M, Korbaś GP, Kawala–Janik A, 2014. YUV vs RGB—choosing a color space for human–machine interaction. Federated Conf on Computer Science and Information Systems, p.29–34. https://doi.org/10.15439/2014F206
Singh K, Kapoor R, 2014. Image enhancement using exposure based sub image histogram equalization. Patt Recogn Lett, 36(1):10–14. https://doi.org/10.1016/j.patrec.2013.08.024
Sugimura D, Mikami T, Yamashita H, et al., 2015. Enhancing color images of extremely low light scenes based on RGB/NIR images acquisition with different exposure times. IEEE Trans Image Process, 24(11):3586–3597. https://doi.org/10.1109/TIP.2015.2448356
Wang Y, Zhuo S, Tao D, et al., 2013. Automatic local exposure correction using bright channel prior for underexposed images. Signal Process, 93(11):3227–3238. https://doi.org/10.1016/j.sigpro.2013.04.025
Xie J, Lin W, Li H, et al., 2011. A new temporal–constraintbased algorithm by handling temporal qualities for video enhancement. IEEE Int Symp of Circuits and Systems, p.2789–2792. https://doi.org/10.1109/ISCAS.2011.5938184
Yuan L, Sun J, 2012. Automatic exposure correction of consumer photographs. European Conf on Computer Vision, p.771–785. https://doi.org/10.1007/978-3-642-33765-9_55
Author information
Authors and Affiliations
Corresponding author
Additional information
Project supported by the Zhejiang Provincial Natural Science Foundation of China (Nos. LY17F020009 and LQ14F020003), the National Natural Science Foundation of China (No. 61303143), and the Professional Development Project for Domestic Visiting Scholars in Universities of Zhejiang Provincial Education Department (Research on Image Stylization Based on Samples)
A preliminary version of this paper has been presented at the Pacific-Rim Conference on Multimedia, 2016
Rights and permissions
About this article
Cite this article
Li, N., Zhang, J. Automatic image enhancement by learning adaptive patch selection. Frontiers Inf Technol Electronic Eng 20, 206–221 (2019). https://doi.org/10.1631/FITEE.1700125
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.1700125