New M.E. Thesis Submitted from CSE Student

A NOVEL METHOD OF COLOR IMAGE ENHANCEMENT BASED ON FUZZY APPROACH By Jaskiran Kaur,cse

Abstract
Digital images are used in various applications in today’s life such as satellite television, magnetic resonance imaging as well as in geographical information systems and astronomy. Digital images are corrupted by various distortions. There are many different cases of distortions. One of the most prevalent cases is distortion due to noise which can be caused by poor image acquisition or by transferring the image data in noisy communication channels. There are different types of noise in digital images such as Salt & Pepper noise and Gaussian noise.
Image Enhancement is one of the important and pre-processing step in digital image processing. There are many types of image enhancement such as noise reduction, edge enhancement and contrast improvement. Many algorithms have been developed for enhancement of colored images as reported in the literature. Despite the significant research conducted on this topic, the development of efficient color image noise reduction method is still a big challenge for the researchers.
In the present work, new efficient and fuzzy rule based filter is proposed for noise reduction in colored images. The proposed method is developed using Fuzzy approach. The proposed method takes into consideration a π-shaped membership function. The various parameters are estimated using mean, median and range. The proposed method is compared both subjectively as well as objectively with the other noise reduction methods. The experimental results show that the proposed method is better than other noise reduction methods and reduces the noise significantly while preserving the detail features.


Leisure Readings :