SLP Header

Underwater Color Image Enhancement Using Wavelength Compensation and Dehazing

IJCSEC Front Page

Abstract
The paper describes underwater image enhancement methods. While capturing under-water images, the quality of the image is degraded by absorption and scattering of light. Such problems should be addressed in order to analyse the underwater images effectively. In this paper we propose histogram equalisation and contrast stretching algorithm to enhance the underwater image quality. In both the cases WCID- Wavelength compensation and image dehazing algorithm is used. Using this techniques both scattering and absorption effects are eliminated.
Keywords:Image enhancement, histogram equalization, contrast stretching, WCID.
I.Introduction
Analysis of underwater image is challenging due to the effects of scattering and absorption of light in underwater environment. These effects are addressed using technique such as image enhancement, histogram equalisation, etc. Contrast enhancement is the process of adjusting contrast and brightness of images or the process of removing undesired characteristics of image. Histogram equalisation is the process of graphical representation of number of pixels in the captured image. Today, several researches are carried out for processing and analysing of underwater images to improve underwater image quality. In aquatic environment scattering and absorption of light degrades the quality of the captured underwater image since contrast reduction and non-uniform colour cast takes place under water. KashifIqbal proposed unsupervised colour correction method (UCM) as preprocessing stage of underwater image enhancement. In underwater situations, one colour dominates the image due to scattering and absorption. In order to improve the quality of the underwater image an approach based on slide stretching is proposed. This includes contrast stretching of RGB algorithm and saturation and intensity stretching of HSI.
Segmentation of underwater image without losing object details, becomes difficult since clarity of underwater image is poor. So image segmentation approach has been developed in which contrast limited adaptive histogram equalization method is first used to enhance the image quality. Then segmentation of objects is performed using histogram thresholding.in underwater situations contrast and resolutions are low which leads to poor visibility making object identification Difficult. To find better contrast enhancement technique Balvant Singh compares contrast limited adaptive equalization method with contrast stretching and histogram equalization method using mean square error and SNR as parameters. Cosmin Ancuti proposed a strategy for underwater video and image enhancement. Using fusion principles input and weight measures are derived only from degraded version of the underwater image. In underwater images contrast varies across the scene and scene depth which disables proper operation of standard computer vision algorithms. An experiment with real underwater images with different degrees of turbidity shows that underwater scenes are reconstructed more accurately using physically-based light propagation model than by using standard stereo algorithms alone.[1] Since quality of underwater image is poor, success rate of scale-invariant feature transform (SIFT) image registration reduces while capturing underwater image. Pulung nurtantio andono proposed pre-processing of image based on the Contrast Limited Adaptive Histogram image Equalization (CLAHE) algorithm. He assumes that Rayleigh scattering dominates the distribution of pixel intensity values of recorded image. The underwater ultrasonic image includes speckle noise. Reduction of speckle noise and enhancement of image contrast has to be performed at the same time. For this purpose anisotropic diffusion model based on wavelet transform is proposed. This model provides improved speckle reduction and image enhancement. The clarity of underwater photoelectric image is reduced due to light scattering and absorption. Shuai Fang proposed single image enhancement based on image fusion strategy. He used the images to which white balance and global contrast enhancement is performed as inputs and computed weight sum of the inputs for each pixel. This improved the image enhancement.

References:

  1. Iqbal, Kashif, M. Odetayo, A. James, Rosalina Abdul Salam, and A. Z. H. Talib. "Enhancing the low quality images using Unsupervised Colour Correction Method." In Systems Man and Cybernetics (SMC), 2010 IEEE International Conference on, pp. 1703-1709. IEEE, 2010.
  2. Iqbal, Kashif, Rosalina Abdul Salam, Mohd Osman, and Abdullah Zawawi Talib. "Underwater Image Enhancement Using an Integrated Colour Model." IAENG International Journal of Computer Science 32, no. 2 (2007): 239-244.
  3. Kumar Rai, Rajesh, Puran Gour, and Balvant Singh. "Underwater Image Segmentation using CLAHE enhancement and thresholding." International Journal of Emerging Technology and Advanced Engineering 2.1 (2012): 118-123.
  4. Singh, Balvant, Ravi Shankar Mishra, and Puran Gour. "Analysis of Contrast Enhancement Techniques for Underwater Image." International Journal of Computer Technology and Electronics Engineering (IJCTEE) Volume 1.
  5. Ancuti, Cosmin, Codruta Orniana Ancuti, Tom Haber, and Philippe Bekaert. "Enhancing underwater images and videos by fusion."In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 81- 88. IEEE, 2012.
  6. Queiroz-Neto, Jose P., Rodrigo Carceroni, Wagner Barros, and Mario Campos. "Underwater stereo." In Computer Graphics and Image Processing 2004. Proceedings. 17th Brazilian Symposium on, pp. 170-177. IEEE, 2004.
  7. Andono, Pulung Nurtantio, I. PURNAMA, and Mochamad Hariadi. "underwater image enhancement using adaptiv filtering for enhanced sift-based image matching." Journal of Theoretical & Applied Information Technology 52.3 (2013).
  8. Li, Yueqin, Ping Li, Huimin Chen, and Xiaopeng Yan. "Aspeckle reduction and image enhancement anisotropic diffusion method for underwater ultrasonic imaging based on wavelet technology." In International Symposium on Photo electronic Detection and Imaging: Technology and Applications 2007, pp. 662511-662511. International Society for Optics and Photonics, 2007.
  9. Fang, Shuai, Rong Deng, Yang Cao, and Chunlong Fang. "Effective Single Underwater Image Enhancement by Fusion." Journal of Computers 8, no.4 (2013): 904-911.
  10. Kamgar-Parsi, Behzad, Lawrence J. Rosenblum, and Edward O. Belcher. "Underwater imaging with a moving acoustic lens." Image Processing, IEEE Transactions on 7, no. 1 (1998): 91-99.
  11. Padmavathi, G., P. Subashini, M. Muthu Kumar, and Suresh Kumar Thakur. "Comparison of filters used for underwater image pre-processing." IJCSNS 10, no. 1 (2010): 58.
  12. Wu, Chung-Chang, Chun-Jen Huang, and Jung-Hua Wang. "Image processing for remotely teleoperated robotic manipulator system for underwater operations." Underwater Technology,2004. UT'04. 2004 International Symposium on. IEEE, 2004.
  13. Eustice, Ryan, Oscar Pizarro, Hanumant Singh,and Jonathan Howland. "UWIT: Underwater Image Toolbox for optical image processing and mosaicking in MATLAB." In Underwater Technology, 2002. Proceedings of the 2002 International Symposium on, pp. 141-145. IEEE, 2002.
  14. Mandhouj, Imen, Hamid Amiri, Frederic Maussang, and Basel Solaiman. "Sonar Image Processing for Underwater Object Detection Based on High Resolution System." In SIDOP 2012: 2nd Workshop on Signal and Document Processing, vol. 845, pp. 5-10. 2012.
  15. Kim, Jin-Hwan, Jae-Young Sim, and Chang-Su Kim. "Single image dehazing based on contrast enhancement." Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. IEEE, 2011.