Analysis of skin images using texture descriptor by a combined statistical and structural approach

Abstract

In this article, an attempt has been made to analyze various skin (textured) images. They are caused because of hot water, chemical, electrical, thermal, cigarette, etc. These images are analyzed using our texture representation scheme. Our approach uses a set of 92 texture primitives. They are tested for the presence of texture by a statistical design of experiments based approach [Ganesan and Bhattacharyya, Pattern Recogn 28 (1995), 99-105]. These texture primitives are concluded as the local descriptor and their distribution over the entire image is the global representation called texture primitive spectrum. The set of texture primitives and the texture primitive spectrums are successful for a number of Bench mark images (Brodatz, Texture-A photographic album for artists and designers, Reinbold, New York, 1968; Vistex, Available at http://www.white.media. mit.edu\vismod\imgery\Vision Texture, MIT Media Lab, 1995). Using the texture primitive spectrum, several texture images have been categorized as micro, macro, fine, and coarse and a trend is obtained. Similarly, a set of skin images affected by severe burn with many causes are analyzed. The severity has been quantified and concluded based on simple and weighted mean computed for the texture primitive spectrums. The extent of burn and hence the curing duration can be approximated from the results. The outcome of our experimentation with ground truth and the opinion from the experts are closely matching.