Haze Removal using Matlab

SKU: PAN_IPM_018 Categories: ,


Image enhancement technology is one of the basic technologies in image processing field. The aim of image enhancement is to improve the interpretability or perception of information in images for human viewers, or to provide `better’ input for other automated image processing techniques. Image Segmentation is one of the vital steps satellite Image processing for gathering information from the satellite images. To study the effectiveness of noise in satellite images, different type of noise like Gaussian, poisson, salt & pepper and speckle noise are added to the original image. The discrete wavelet transform (DWT) and Bayes Shrink soft thresholding is then applied for the removal of noisy pixels and smoothen the image. The proposed technique, computationally more efficient than the spatial domain based method, is found to provide better enhancement compared to other compressed domain based approaches. In the final stage, the fuzzy based modified FCM clustering is performed on the denoised images to produce clusters or segmented result.


Haze-removal algorithms are used to obtain clean, haze-free images with enhanced saturation and contrast.Haze or fog is caused by microscopic aerosols distributed in the air. Cameras and the human eye lack the sensitivity to make out these aerosols; however, airborne particles can affect radiance in other ways, such as Rayleigh scattering, Mie scattering, and the Tyndall effect. Researchers have observed that these effects obey Koschmieder?s Law in proposed a model for the removal of haze from video clips obtained using a fixed camera position, wherein some of the unknown variables can be eliminated using a clip containing time series data. In contrast, single image de-hazing methods focus more on image enhancement than a restoration based on strict physical laws. Most of these methods are based on augmenting the attenuated signal with a priori knowledge related to dynamic range, saturation, or contrast. Based on the observation that atmospheric light reduces contrast, Tan ?sought to restore images by maximizing in-patch contrast defined as the sum of the gradient using an energy maximization framework. For removing these types of noises inside the image we are going to use such techniques which are mentioned in the abstract of this project these techniques provide a very good clear output image without haze that is simply called dehazed image.

Existing Method:

  • Based Gaussian Filter Kernel function they have done enhancement for image
  • CWT-Based Image Resolution Enhancement
  • Threshold Segmentation

Drawback of Existing Technique:

  • Loses in edges in the final sharper image.
  • The edges of the color image could not be handled well.
  • Gaussian Filter leads to the inaccurate background Image
  • The edges of the color image could not be handled well

Proposed Method:

  • DWT-based resolution enhancement
  • Bayes Shrink soft Thresholding
  • Fuzzy C-Means Clustering

Advantages of Proposed Method:

  • Superior Resolution, when compared to existing techniques.
  • Greater performance Ratio.

Block diagram

Haze Removal using Matlab

Block diagram explanation

Input image

Image Acquisition is to collect a digital photograph. To collect this requires an picture sensor and the functionality to digitize the sign produced thru the sensor. The sensor might be monochrome or coloration TV camera that produces an entire photo of the trouble area each 1/30 sec. The photograph sensor may also be line test virtual digital camera that produces a single photo line at a time. In this project we are using satellite images as an input. Normally satellite images have some inbuilt nose so that we take that image as an input and going to process it.


A photo is a -dimensional photograph, which has a similar look to three subject typically a physical item or someone.

?????????? Image is a -dimensional, which includes a image, display screen display, and further to a three-dimensional, which incorporates a statue. They can be captured thru way of optical devices?together with cameras, mirrors, lenses, telescopes, microscopes, and so forth. A herbal gadgets and phenomena, on the aspect of the human eye or water surfaces. The word picture is likewise used in the broader experience of any -dimensional determine such as a map, a graph, a pie chart, or a summary portray. In this wider experience, pictures moreover may be rendered manually, which incorporates thru way of drawing, portray, carving, rendered mechanically through printing or laptop pictures technology, or advanced with the beneficial resource of a aggregate of techniques, especially in a pseudo-photo.

?DWT ?

Discrete Wavelet Transform (DWT)

The discrete wavelet remodel (DWT) became superior to use the wavelet rework to the digital international. Filter banks are used to approximate the behaviour of the non-prevent wavelet remodel. The sign is decomposed with a immoderate-skip smooth out and a low-bypass clear out. The coefficients of these filters are computed using mathematical evaluation and made to be had to you. See Appendix B for more records about those computations.

2.2 Discrete Wavelet Transform


LP d: Low Pass Decomposition Filter

HP d: High Pass Decomposition Filter

LP r: Low Pass Reconstruction Filter

HP r: High Pass Reconstruction Filter

The wavelet literature offers the filter coefficients to you in tables. An example is the Daubechies filters for wavelets. These filters rely upon a parameter p called the vanishing 2nd

Soft Thresholding

The soft-thresholding step can be intuitively understood as a denoising operation that?decreases the ? 1 norm of the wavelet representation of the image. This step has the effect of pushing to zero wavelet coefficients that are very small and consolidating the energy of the signal about a sparse set of coefficients.

Requirement Specifications

Hardware Requirements

  • system
  • 4 GB of RAM
  • 500 GB of Hard disk



  • [1]Efficient image dehazing with boundary constraint and contextual regularization ,G. Meng, Y. Wang, J. Duan, S. Xiang, and C. Pan, 2013
  • [2] Improved visibility of road scene images under heterogeneous fog, J.-P. Tarel, N. Hauti?re, A. Cord, D. Gruyer, and H. Halmaoui, 2010
  • [3]Chromatic framework for vision in bad weather, S. G. Narasimhan and S. K. Nayar,2000
  • [4]Single image haze removal using dark channel prior, K. He, J. Sun, and X. Tang, 2011
  • [5]Bayesian defogging, K. Nishino, L. Kratz, and S.2012
  • [6] M. Almeida and L. Almeida, ?Blind and semi-blind deblurring of natural images,? IEEE Transactions on Image Processing, vol. 19, no. 1, pp. 36?52, Aug. 2010.
  • [7] Q. Shan, J. Jia, and A. Agarwala, ?High-quality motion deblurring from a single image,? ACM Trans. Graph., vol. 27, no. 3, pp. 721?730, Aug. 2008.
  • [8] N. Joshi, R. Szeliski, and D. Kriegman, ?Psf estimation using sharp edge prediction,? in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, AL, USA, 2008.
  • [9] A. Levin, Y. Weiss, F. Durand, and W. Freeman, ?Ef?cient marginal likelihood optimization in blind deconvolution,?inProc.IEEEConf.ComputerVisionandPattern Recognition, Colorado Springs, CO, USA, 2011.
  • [10] D. Krishnan, T. Tay, and R. Fergus, ?Blind deconvolution using a normalizaed sparsity measure,? in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011.


Customer Reviews

There are no reviews yet.

Be the first to review “Haze Removal using Matlab”

Your email address will not be published. Required fields are marked *