http://in.mathworks.com/matlabcentral/fileexchange/39701-gaussian-high-pass-filter

High pass filtering is used to sharpen an image.

If you want to remove noise/smooth the image then you need to use some kind of low pass filter.

Low pass filters (Smoothing)

Low pass filtering (aka smoothing), is employed to remove high spatial frequency noise from a digital image. The low-pass filters usually employ moving window operator which affects one pixel of the image at a time, changing its value by some function of a local region (window) of pixels. The operator moves over the image to affect all the pixels in the image.

High pass filters (Edge Detection, Sharpening)

A high-pass filter can be used to make an image appear sharper. These filters emphasize fine details in the image - the opposite of the low-pass filter. High-pass filtering works in the same way as low-pass filtering; it just uses a different convolution kernel.

Code to do Gaussian high pass filtering is below:

http://in.mathworks.com/matlabcentral/fileexchange/39701-gaussian-high-pass-filter

There are many methods much more powerful than linear filtering the image to remove the noise. If you use Matlab, you may want to try BLS-GSM, my code (in collaboration with Prof. Simoncelli). It is open and free. There are many others, some of them more modern and powerful (like Dabov's BM3D, or Siwei&Simoncelli FoGSM, etc.) but most of them are not simultaneously open code and free.  

http://www.io.csic.es/PagsPers/JPortilla/software

Everything depends on the problem you want to solve. I have not worked with forensic images but, as every solution for digital image processing, there are many filters designed in the image domain and in the Fourier domain. I suggest to make a code with these filters (you can find them in the book: "Digital Image Processing using Matlab" from Gonzalez, Woods & Eddins as a beginning) and make a test in the two domains. You will find how these filters works, and eventually, they will be the first step to find the solution wanted (¡your solution!)

By the way, depending on your forensics problem, applying a de-noising stage to your observation may have a disastreous effect on your possibilities of correctly characterizing it. For instance, if you are trying to locate and characterize the mosaic of the camera with which the photo was taken, filtering the image may destroy a lot of useful invisible information in the picture.

As you and others know there are several (perhaps many) methods that can be used to remove noise from a digital image whether it is a satellite or forensic image or some other type of image.  The key is going to be on the characteristics of the noise pattern that you want to remove with a major concern being if it is a 'high or low frequency' that needs to be removed.  I developed procedures to remove various types of noise patterns from satellite, airborne, and shipborne images (including radar and sonar) in the 1970s and 1980s using a combination of spatial filtering options.  Noise removal using spatial filtering methods (boxcar filtering in my case) typically requires the combination of high and low pass filtering with options to include and/or not include valid dn values.  I have used these types of methods to remove bit errors, speckle, quasi-coherent noise patterns, stripping (from Landsat 1 / ERTS 1 back in those days), shading in radar and sonar images (low frequency patterns), and camera lens patterns.

My suggestion would be to consider both spatial and frequency filtering methods to see which might be best, and easiest, for your case. Depending on the information that you are interested in extracting from the image you might get away with applying a simple high pass filter and not need to combine it with a low frequency filter option.  Any chance of you posting an example of an image with the noise pattern you want to remove?

Pat Chavez

 I am working on Image forensic i need matlab code for research paper as i am begineer in matlab can anyone help me 

i will mail the research paper for which matlab code is required. if any one can please tell me 

Hello sir can i get ur mail id please to have communication regarding image forensics