Vous êtes sur la page 1sur 1

Image Enhancement via Adaptive Unsharp Masking

Isha Jha
9030263454
11/21/06

My project is on Adaptive unsharp masking, which is a way to enhance contrast in


images. I will be doing this project alone.

The problem with linear unsharp masks is that the high pass filter makes the system very
sensitive to noise. Also it enhances high contrast areas much more than areas with lower
image dynamics.

This new approach allows sharpening in high detail areas but little or no sharpening in
flat or smooth areas.

In this approach, the enhanced image y(n,m) is obtained from the original image x(n,m)
using the following mapping.

y(n.m) = x(n,m) +z(n,m)

where z(n,m) is the correction signal computed at the output of the highpass filter and
is the scaling factor that is varied in this adaptive technique, in order to control the level
of contrast enhancement at the output.

I plan to implement this new approach of doing Unsharp Masking adaptively. I will then
proceed to compare it with the current way of doing Unsharp masking, where the high
passed version of the image is added to the original image to obtain an enhanced version.

References:

1) Gonzalez and Woods, Digital Image Processing, Second Edition

2) Andrea Polesel, Giovanni Ramponi and V. John Matthews, Image enhancement


via Adaptive Unsharp Masking, IEEE Trans. on Image Processing, vol. 9, no. 3,
2000, pp. 505-510

3) M.A. Badamchizadeh, A, Aghagolzadeh, Comparitive Study of Unsharp making


Menthods for Image Enhancement, Proc. 3rd Int’l conference on Image and
Graphics, 2004, pp. 27-30.

4) Lecture Notes

Vous aimerez peut-être aussi