Due to the influence of objective factors such as insufficient ambient light and uneven brightness, images collected in low-light environments are prone to loss of details and low contrast. Existing enhancement algorithms are likely to cause problems such as overexposure and inadequate detail processing and so on. In view of the above problems, an image enhancement algorithm combining global tone mapping and local contrast processing is proposed. First, the low-illuminance image is converted from the RGB color space to the HSI color space; second, the adaptive global tone mapping enhancement method is used to enhance the luminance component I of the HSI space image; finally, the details of the image are enhanced by local contrast processing, in order to enhance the global brightness while maintaining the image details. Experimental results show that the proposed algorithm can effectively improve the overall brightness and contrast of low-illuminance images, enhance image details, reduce noise, and obtain clear images with good visual effects.
为了客观评价本文算法和以上3种对比算法对低照度图像的增强效果,利用各增强图像与参考图像的平均亮度[10]、PSNR(peak signal to noise ratio)[7]、SSIM(structural similarity,结构相似性) [21]以及图像的信息熵[10]对图像增强效果进行质量评价。
WONGC Y, JIANGG, RAHMANM A, et al. Histogram equalization and optimal profile compression-based approach for color image enhancement[J]. Journal of Visual Communication & Image Representation, 2016, 38:802-813. DOI: 10.1016/j.jvcir.2016.04.019 .
[3]
CHIUC, TINGC. Contrast enhancement algorithm based on gap adjustment for histogram equalization [J]. Sensors, 2016, 16(6):936-954. DOI: 10.3390/s16060936 .
[4]
LEE S L, TSENGC. Color image enhancement using histogram equalization method without changing hue and saturation[C]// IEEE International Conference on Consumer Electronics-Taiwan. New York: IEEE, 2017:305-306. DOI: 10.1109/ICCE-China.2017.7991117 .
[5]
MAKINANAS, KHANYILEP N, KHUTLANGR. Latent fingerprint wavelet transform image enhancement technique for optical coherence tomography [C]// International Conference on Artificial Intelligence and Pattern Recognition. New York: IEEE, 2016:1-5. DOI: 10.1109/ICAIPR.2016.7585203 .
SHENK, CAIY F. Radiographic image enhancement algorithm based on wavelet fusion [J]. Application Research of Computers, 2009, 26(8):3137-3139. DOI: 10.3778/j.issn.1002-8331.2010.23.048(Ch ).
[8]
WANGY F, WANGH Y, YINC L, et al. Biologically inspired image enhancement based on Retinex[J]. Neurocomputing, 2016, 177:373-384. DOI: 10.1016/j.neucom.2015.10.124 .
[9]
LIY H, ZHOUX Y. Multi-resolution and multi-scale Retinex for color image enhancement [J]. Computer Engineering & Applications, 2017,53(16): 193-198. DOI: 10.1117/12.791027 .
[10]
LINH N, SHIZ W. Multi-scale retinex improvement for nighttime image enhancement [J]. Optik, 2014, 125(24):7143-7148. DOI: 10.1016/j.ijleo.2014.07.118 .
ZHAOJ H, WUY F, HUK R,et al. Color image enhancement algorithm based on Lab color space and tone mapping [J]. Computer Science, 2018, 45(2):297-300. DOI: 0.11896/j.issn.1002-137X.2018.02.051(Ch ).
[13]
WANGL, JUNGC. Tone-preserving contrast enhancement in images using rational tone mapping and constrained optimization[C]// 2016 Visual Communications and Image Processing (VCIP). New York: IEEE, 2016: 1-4. DOI: 10.1109/VCIP.2016.7805525 .
[14]
DRAGOF, MYSZKOWSKIK, ANNENT, et al. Adaptive logarithmic mapping for displaying high contrast scenes[J]. Computer Graphics Forum,2003, 22(3): 419-426. DOI: 10.1111/1467-8659.00689 .
[15]
BENNETTE P, MCMILLANL. Video enhancement using per-pixel virtual exposures [J]. ACM Transactions on Graphics (TOG), 2005, 24(3):845-852. DOI: 10.1145/1186822.1073272 .
[16]
HUJ H, HUR M, WANGZ Y, et al. Kinect depth map-based enhancement for low light surveillance image[C]// IEEE International Conference on Image Processing. New York: IEEE, 2013:1090-1094. DOI: 10.1109/ICIP.2013.6738225 .
[17]
赵海法.协同创新中心低照度图像数据库[DB/OL].[2016-12-29].
[18]
ZHAOH F. Collaborative Innovation Center Low Illumination Image Database[DB/OL].[2016-12-29].
[19]
LEE B J, SONGB C. Local tone mapping using sub-band decomposed multi-scale retinex for high dynamic range images[C]//2014 IEEE International Conference on Consumer Electronics (ICCE). New York : IEEE, 2014: 125-128. DOI: 10.1109/ICCE.2014.6775937 .
[20]
JUNGC. Power constrained contrast enhancement based on brightness compensated contrast-tone mapping operation [J]. Journal of Electronic Imaging, 2016, 25(5): 40-45. DOI: 10.1117/1.JEI.25.5.053027 .
[21]
GONZALEZR C, WOODSR E, EDDINSS L. Digital Image Processing Using MATLAB [M]. New Jersey: Prentice Hall Press, 2007. DOI:10.9774/GLEAF.978-1-909493-38-4_2 .
[22]
LIUJ P, HUANGB K, WEIG. A fast-effective single image dehazing algorithm[J]. Acta Electronica Sinica, 2017, 45(8):1896-1901. DOI: 10.1007/s00371-016-1305-1 .
[23]
HUAIW J, SHANGL, SUP G. MMW Image Enhancement Based on Gray Stretch Technique and SSR Theory [M]. Berlin: Springer, 2012. DOI: 10.1007/978-3-642-31588-6_49 .
[24]
WANGZ, BOVIKA C, SHEIKHH R, et al. Image quality assessment: From error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. DOI: 10.1109/TIP.2003.819861 .