LAUSR

This paper presents an outline of methods that have been proposed for the analysis of chronic wound images. This paper indicates the details of four different ulcerous cases, provides good treatment policy, enhances quality of patient’s life, improves evidence based clinical outcomes and suggests best possible issues. This paper investigates efficient filtering techniques for chronic wound image pre-processing under Tele-wound network. The aim of this work is to accurately access the healing status of chronic wound with improved image processing techniques by proper filtering. Efficient filtering techniques help to reduce the noise for wound images. The simulation results are presented by comparing different parameters. Performance parameters are peak signal to noise ratio (PSNR), mean square error (MSE), signal to noise ratio and mean absolute error. Results shows adaptive Median filtering provides better performances with respect to high PSNR and reduced MSE between original and filtered image. This work proposes the Particle Swarm Optimization (PSO) method for segmentation of wound areas via suitable color space selection. The PSO algorithm in Db channel provided good accuracy (98.93%) for chronic wound segmentation. Here proposed Linier discriminant analysis classifier provides 98% overall tissue prediction accuracy. The aim is to develop telemedicine framework for wound diagnosis by improving good interaction between health experts, patients, and tele-medical agents who belongs to rural/urban areas that are involved in the provision of care to resolve the delayed treatment.