International Journal of Engineering and Technical Research (IJETR) ISSN: 2321-0869 (O) 2454-4698 (P), Volume-7, Issue-3, March 2017 20 www.erpublication.org Abstract— Numerous underwater image enhancement schemes are being used for improving an image, which includes gray scale manipulation, filtering and Histogram Equalisation. Histogram Equalisation has become a popular technique because this method is simple and effective. Another significant technique in underwater image enhancement is Discrete cosine transform. Discrete cosine transform is a fast transform that has excellent compaction for highly correlated data. DCT gives good compromise between information package ability and computational complexity. In this paper underwater image enhancement is proposed based on discrete cosine transform and Unsharp Mask Filtering, which gives the significant results as compared to previous techniques. Index Terms— Discrete Cosine Transform, Unsharp Mask Filtering. I. INTRODUCTION Getting clear images in underwater environments is an important issue in Ocean engineering. Image enhancement is a process of changing an image so that the result is more suitable than the original image for a particular application. Image enhancement commonly used in computer graphics and it is the subarea of image processing. Image enhancement techniques can be divided into two broad categories: Spatial domain methods and Frequency domain methods. Spatial domain is the collection of pixels composing an image. Spatial domain techniques are procedures that work directly on the pixels. Spatial domain processing is denoted such as g(x, y) =T [f(x, y)]. Point processing is the processing of contrast enhancement. This process produces an image of higher contrast than the one by darkening a particular level. Hitam et al. (2013) [1] have discussed a new method specifically developed for enhancing the underwater images called mixture Contrast Limited Adaptive Histogram Equalization (CLAHE) color model. Galdran et al. 2014[2] proposed a Red Channel method, where colors associated to short wavelengths are recovered, as expected for underwater images. G.Padmavathi et al. 2010[3] have compared and evaluated three filters performance. These filters are homomorphic filter, anisotropic diffusion and wavelet denoising by average filter. All these filters are helpful in pre-processing of underwater image. Chiang et al. 2012[4] have proposed a fresh efficient approach based on dehazing algorithm, used to enhance underwater images. Erturk et al. S.V.S.Sai.Sravya, Final year B.Tech ECE Students, ANUCET, Acharya Nagarjuna University, Guntur, A.P. India B.Gopi Naik, Final year B.Tech ECE Students, ANUCET, Acharya Nagarjuna University, Guntur, A.P. India P.Bhavani, Final year B.Tech ECE Students, ANUCET, Acharya Nagarjuna University, Guntur, A.P. India G.Prathibha, Assistant Professor, Dept of ECE, ANUCET, Acharya Nagarjuna University, Guntur, A.P. India 2012 [5] have presented a new algorithm based on an Empirical Mode Decomposition (EMD) which is used to improve visibility of underwater images. Sowmyashree et al. 2014[6] have presented a relative study of the different image enhancement methods used for enhancing images of the bodies under the water. Hung Yu Yang et al.2011 [7] worked on "Low complexity under water image enhancement based on dark channel prior”. bt.Shamsuddin et al. 2012[8] developed a technique on Significant level of image enhancement techniques for underwater images. Jinbo Chen et al. 2011[9] proposed A detection method based on sonar image for underwater pipeline tracker. Haochng Wen and Yonghong Tian (2013) [10] proposed a new underwater optical model which describe the formation of an underwater image in the true physical process. BASIC METHODOLOGY Dark-channel prior method (a scene-depth derivation method) is used first to calculate the distances of the scene objects to the camera as shown in fig 1. First an image is kept in an array. Next it is compared to the image of the other camera by taking square regions of pixels and comparing the intensity between the two cameras images. Third the depth of a given pixel region is calculated and kept in an array. Finally this array of depths is changed into color for maximum clarity, with bright colors being closer and dull colors being more far. Large blocks of solid color will produce black or nearly indiscriminate results. Now the depth value (between 0 and 255) is converted to a colour to better show how far away the object is. Red is the closest in colour list to black as the furthest. The real depths these colours symbolize is dependent upon your cameras and their distance from each other. Fig.1. Natural light enters from air to an underwater scene point BASIC ALGORITHM The distance between object and camera is known and image segmentation is done based on the depth map as shown in Under Water Image Enhancement Using Discrete Cosine Transform S.V.S.Sai.Sravya, B.Gopi Naik, P.Bhavani, G.Prathibha