Hao Wang
ABSTRACT
Underwater resource development is more and more important, but some underwater operations, such as scientific exploration and construction work depending on underwater observation, are with visual difficulties because of the turbid water. To improve underwater visual quality, we propose a comprehensive image enhancement algorithm in this paper, which consists of four sections. The first section is Bilateral Filter used to reduce image noise, then the image is dehazed based on Dark Channel Prior (DCP). Thirdly, we propose one White Balance method to adjust colors in underwater images. At the end of the algorithm, Contrast Limited Adaptive Histogram Equalization (CLAHE) is adopted to improve the contrast in images. Besides, to verify this algorithm, a series of underwater image experiments are conducted on the turbid water test platform. More than 300 turbid underwater images are captured and some of them are processed through the proposed algorithm. By using Image Quality Evaluate Metrics and comparing degraded images with result images, we evaluate the algorithm in subjective and objective aspects, and conclude that the proposed algorithm can comprehensively improve the quality of images with better color, contrast and more details, which has a great significance to underwater operations.
- J. Lu, N. Li, S. Zhang, H. Zheng, B, Zheng. "Multi-scale adversarial network for underwater image restoration," Opt. Laser Technol., vol. 110, pp. 105--113, 2019.Google Scholar
Cross Ref
- Y. Fan, S. Wang and T. Yu, "Underwater image enhancement algorithm based on RGB channels histogram equalization," in Proc. Conference on Optical Sensing and Imaging Technologies and Applications / International Symposium on Optoelectronic Technology and Application (OTA), May. 2018, Proceedings of SPIE, vol. 10846.Google Scholar
- C. O. Ancuti, C. Ancuti and C. D. Vleeschouwer, "Color Balance and Fusion for Underwater Image Enhancement," IEEE Trans. Image Process., vol. 27(1), pp. 379--393, 2017.Google ScholarCross Ref
- Rashkevych Y, Peleshko D, et al. "Single-frame image super-resolution based on singular square matrix operator," In Proc. IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON). 2017: 944--948.Google Scholar
- Peleshko D, Rak T, et al. "Two-frames image superresolution based on the aggregate divergence matrix," In Proc.IEEE First International Conference on Data Stream Mining & Processing (DSMP). 2016: 235--238.Google Scholar
- Y. Li, Y. Zhang, X. Xu, L. He, S. Serikawa and H. Kim, "Dust removal from high turbid underwater images using convolutional neural networks," Opt. Laser Technol., vol. 110, pp. 2--6, 2019.Google ScholarCross Ref
- H. Lu, Y. Li, L. Zhang, S. Serikawa, "Contrast enhancement for images in turbid water," Journal of the Optical Society of America A, vol. 32(5), pp. 886--893, 2015.Google ScholarCross Ref
- T. M. Nimisha, S. Karthik and A. N. Rajagopalan, "Color Restoration in Turbid Medium", in Proc. 10th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), Dec. 2016, Assam India.Google Scholar
- F. Bonin, A. Burguera, G. Oliver. "Imaging systems for advanced underwater vehicles," Journal of Maritime Research, vol. 8(1), pp. 65--86, 2011.Google Scholar
- K. Zhang, W. Zuo, Y. Chen and D. Meng. "Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising." IEEE Trans. Image Process., vol. 26(7), pp. 3142--3155, 2017.Google ScholarDigital Library
- H.C. Burger, C.J. Schuler. "Image denoising: Can plain neural networks compete with BM3D?" In Proc. IEEE conference on computer vision and pattern recognition(CVPR). IEEE, 2012, pp. 2392--2399.Google Scholar
- C. Tomasi, R. Manduchi. "Bilateral filtering for gray and color images," in Proc. IEEE International Conference on Computer Vision (ICCV). 1998. vol. 98(1).Google Scholar
- S. Paris, F. Durand. "A fast approximation of the bilateral filter using a signal processing approach." In Proc. European conference on computer vision. Springer, 2006, Berlin, Heidelberg, pp. 568--580.Google Scholar
- K. He, J. Sun and X. Tang. "Single image haze removal using dark channel prior," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33(12), pp. 2341--2353, 2010.Google ScholarDigital Library
- C.O. Ancuti, C. Ancuti. "Single image dehazing by multi-scale fusion." IEEE Trans. Image Process., vol. 22(8), pp. 3271--3282, 2013.Google ScholarCross Ref
- R. Fattal. "Dehazing using color-lines." ACM transactions on graphics (TOG), vol. 34(1), pp. 13, 2014.Google ScholarDigital Library
- K. He, J. Sun and X. Tang. "Guided image filtering," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25(6), pp. 1397--1409, 2012.Google ScholarDigital Library
- J. Ma, X. Fan, S.X. Yang, X. Zhang. "Contrast limited adaptive histogram equalization-based fusion in YIQ and HSI color spaces for underwater image enhancement," Int. J. Pattern Recognit. Artif. Intell., vol.32(07), pp. 1854018, 2018.Google ScholarCross Ref
- L. Zheng, H. Shi, S. Sun. "Underwater image enhancement algorithm based on CLAHE and USM," in Proc. IEEE International Conference on Information and Automation (ICIA). 2016. IEEE, pp. 585--590.Google ScholarCross Ref
- W. J. Zhang, L. L. Zhang and Y.H. Wang, "SSIM image quality assessment based on nonlocal structure tensor," Application Research of Computers, vol.34(10), pp. 3162--3164, 2017.Google Scholar
- H. TIAN, S. LI, "Objective Evaluation Method for Image Quality Based on Edge Structure Similarity," ACTA PHOTONICA SINICA, vol. 42(10), pp. 110--114, 2013.Google Scholar
Index Terms
- An image enhancement algorithm for turbid underwater image based on multiple methods
Recommendations
Underwater image enhancement based on color restoration and dual image wavelet fusion
AbstractDue to the severe light absorption and scattering, underwater images often exhibit problems such as low contrast, detail blurring, color attenuation, and low illumination. To address these issues, this paper presents a two-step ...
Highlights- The paper presents an approach by integrating data-driven deep learning and hand-crafted image enhancement for the single underwater image enhancement. We ...
An Underwater Color Image Enhancement Model Based on Comprehensive Processing
ICNSER2020: Proceedings of the 2nd International Conference on Industrial Control Network And System Engineering ResearchThe propagation of light in water is affected by the absorption of water and the scattering of particles in water, which leads to the problems of low contrast, blur, color distortion and so on, the traditional underwater image enhancement algorithm is ...
Enhancement of low quality underwater image through integrated global and local contrast correction
A method of integration global and local contrast stretching is proposed to increase underwater image quality.The integrated modification of RGB and HSV color model is applied in the proposed method.Resultant image outperforms the current state-of-the-...
Comments