13-08-2012, 05:00 PM
DENOISING OF DIGITAL IMAGES
DENOISING OF DIGITAL IMAGES .docx (Size: 1.71 MB / Downloads: 32)
INTRODUCTION
An image [15 ] may be defined as two–dimensional function f (x,y) where the amplitude of f at any pair of coordinates (x, y) is called the intensity or gray level of the image at that point and x and y are spatial coordinates. When the x, y and the amplitude values of f are all finite , discrete quantities ,image is called as digital image .
Images are often corrupted with noise during acquisition, transmission, and retrieval from storage media. Many dots can be spotted in a Photograph taken with a digital camera under low lighting conditions. A noise is also introduced in the transmission medium due to a noisy channel, errors during the measurement process and during quantization of the data for digital storage. Each element in the imaging chain such as lenses, film, digitizer, etc. contribute to the degradation [15,23,22]. The purpose of the denoising algorithm is to remove noise. Image de-noising is used to remove the additive noise while retaining as much as possible the important signal features. Image denoising finds applications in fields such as astronomy where the resolution limitations are severe, in medical imaging where the physical requirements for high quality imaging are needed for analyzing images of unique events, and in forensic science where potentially useful photographic evidence is sometimes of extremely bad quality
SURVEY OF LITERATURE
There are many different kinds of image denoising algorithms [12]. They can be broadly classified into two classes
• Spatial Domain Filtering [1,12]
• Transform Domain Filtering [8,10]
Spatial domain filtering refers to filtering in the spatial domain, while transform domain filtering refers to filtering in the transform domain. Image denoising algorithms which use wavelet transforms fall into transform domain filtering.
Spatial Domain Filtering
Spatial domain filtering can be further divided on the basis of the type of filter used:
• Linear filters [1]
• Non-Linear filters [12]
Mean Filter :
Mean filter [12,23] is an example of a linear filter.This filter replaces each pixel value in the images with the average value of its neighbours including itself. We select a odd size window with center element as the processing pixel & then replace the processing pixel with the average of the window pixels. This filter is mainly used for removal of Salt & Pepper noise but results some blurring at the edges.
Median Filter :
Median filter [1,23] is an example of a non-linear filter . Median filtering is quite useful in getting rid of Salt and Pepper type noise. In median filter denoising firstly select an odd size window with center element as the processing pixel & then store the elements in 1-D array. Then sorted the pixel value in ascending or descending order. Then replace the processing pixel with the midpoint of the 1-D array. With Spatial filters tend to cause blurring in the denoised image.