Investigation on colour sensor denoising

• Main Author: Koh, Hui Guo.
• Other Authors: Yu Yajun
• Format: Final Year Project
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Computer science and engineering::Computer applications::Arts and humanities
• Online Access: http://hdl.handle.net/10356/44272
• Institution: Nanyang Technological University

Bilateral filtering is a popular denoising technique that smoothes away noise while preserving edges by nonlinear averaging of similar adjacent pixel values. The original filter does not remove salt and pepper noise effectively and textures of the image are not well preserved. Thus, we propose a modified form of bilateral filter that separately operates on high frequency and low frequency sub-band to extend the classical bilateral filtering for image noise removal. A new low frequency noise suppressor is incorporated into the modified bilateral filter framework. The proposed filter is shown to perform better than the traditional bilateral filter. The filter is implemented in Matlab into a graphical user interface with noise level estimation function and image blending function to target different noise level in the digital image.