Statistical Restoration Techniques on Melanoma Images

Author Name(s): Reshma. M, Dr. B Priestly Shan
Author Email: reshma.m03@gmail.com

Abstract

In this paper, a comparative study of image restoration on color images of skin cancer is presented as it plays an important role in the study of images. Image restoration is the process of convalescing an image from a tarnished version—usually a blurred and noisy image. Image restoration is an elementary problem in image processing, and it also provides a test bed for more universal converse problems. Key issues that must be addressed are the quality of the restored image, the computational efficiency of the algorithm, and the performance parameters such as the Peak signal to noise ratio (PSNR), Mean square error (MSE). Image noise is unwanted signal which comes in image from sensor such as thermal or electrical signal and Environmental condition such as rain, snow etc. Researchers have proposed many methods in this regard and in this paper we will examine and discuss different restoration methods and performance parameters for Melanoma images.

Introduction

Skin diseases are the most common diseases in humans and its frequency is ever-increasing noticeably. Therefore early diagnosing the skin cancer is a crucial issue for patient. However, a highly qualified and skilled doctor is able to categorize the skin cancer from other normal skin diseases. Therefore it is very essential to develop the computer based skin cancer detection so that it would become easy for non-specialized doctors to identify the disease. It is wellknown that early detection of skin cancer and its treatment can reduce the mortality and morbidity of patients. Digital Dermoscopy is one of the most extensively used methods to identify and classify skin-cancer. An automatic medical images analysis system has usually three stages: (1) Proper restoration & Enhancement, (2) feature extraction and selection (3) Classification. The proper restoration is the most important, since it affects the precision of the subsequent steps.

Conclusion

In this paper, the observations are made by applying statistical filters on different real time images. Determined different image quality metrics and by estimating these values analyzed the improvement in image quality.

825 total views, no views today

Download PDF File

About the author: admin