International Journal of Scientific Research in Computer Science, Engineering and Information Technology CSEIT195121 | Received : 10 Jan 2019 | Accepted : 23 Jan 2019 | January-February -2019 [ 5 (1) : 116-122 ] International Journal of Scientific Research in Computer Science, Engineering and Information Technology © 2019 IJSRCSEIT | Volume 5 | Issue 1 | ISSN : 2456-3307 DOI : https://doi.org/10.32628/CSEIT195121 116 Image Dehazing Technique Based On DWT Decomposition and Intensity Retinex Algorithm 1Sunita Shukla, 2Prof. Silky Pareyani 1M. Tech Scholar, Gyan Ganga College of Technology Jabalpur, Madhya Pradesh, India 2Assistant Professor, Gyan Ganga College of Technology Jabalpur, Madhya Pradesh, India ABSTRACT Conventional designs use multiple image or single image to deal with haze removal. The presented paper uses median filer with modified co-efficient (16 adjacent pixel median) and estimate the transmission map and remove haze from a single input image. The median filter prior(co-efficient) is developed based on the idea that the outdoor visibility of images taken under hazy weather conditions seriously reduced when the distance increases. The thickness of the haze can be estimated effectively and a haze-free image can be recovered by adopting the median filter prior and the new haze imaging model. Our method is stable to image local regions containing objects in different depths. Our experiments showed that the proposed method achieved better results than several state-of-the-art methods, and it can be implemented very quickly. Our method due to its fast speed and the good visual effect is suitable for real-time applications. This work confirms that estimating the transmission map using the distance information instead the color information is a crucial point in image enhancement and especially single image haze removal. Keywords : AF: Adaptive filter, AHE: Adaptive Histogram Equalization, LOE: Lightness Order Error I. INTRODUCTION Restoration of hazy image is an important issue in outdoor vision system. Image enhancement and dehazing remain a challenging problem as well as an important task in image processing. Image enhancement is really an important issue in image processing applications such as digital photography, medical image analysis, remote sensing and scientific visualization [1]. Image dehazing and enhancement is the process by which the appearance and the visibility of an image are improved such that the obtained image is suitable for visual perception of human beings or for machine analysis. It is useful not only from an aesthetic point of view but also helps in image analysis and object recognition, etc. Image captured under bad visibility often has a contrast and many of its features are difficult to see. II. METHODOLOGY In this paper, we proposed a new method for single image dehazing using the NAM (Non-symmetry and Anti-packing Model)-based decomposition and contextual regularization. We estimated the airlight by decomposing the image using non-symmetry and anti-packing model [11] to eliminate the false estimation at the boundary or the over-bright object. Then, the scene transmission was calculated using the combination of the boundary constraints, the contextual regularization and the optimization proposed by Meng et al. [12]. The proposed method had better color visual and haze-free image when it http://ijsrcseit.com/ Volume 5, Issue 1, January-February-2019 | http:// ijsrcseit.com Sunita Shukla, Prof. Silky Pareyani Int J Sci Res CSE & IT. January-February-2019 ; 5(1) : 116-122 117 comes to the image dehazing problem, a dehazing model called Atmospheric Scattering Model is widely used in I (x) =J (x)t(x) + A(1-t(x)) where I(x) represents the hazy image, and J(x) denotes the origin haze-free image(also called scene radiance). A is the airlight which is the global light in the atmosphere while t(x) denotes scene transmission function (0