Wound assessment in pedobarography using image segmentation and classification techniques

Abstract

Assessment of a diabetic wound is very much important to determine the healing status. Foot ulcer is most commonly observed problem of diabetic patients. A diabetic wound is observed for approximately 15 per cent of diabetic patients. Diabetic wound is a major concern of diabetes mellitus. The foot ulcer is the very much harm full problem related to diabetes mellitus. A huge number of previous techniques consist of manually tuning the parameters as per the various input images that are highly impossible in the clinical aspect for segmentation. Even though a majority of brain tumor segmentation algorithms yield comparatively better results in the domain of medical image analysis, clinical applications face a little hurdle. To avoid these problems, image segmentation in Diabetic Foot Ulcers (DFU) images is focused in first work and developed four algorithms such as adaptive K- means, FCM, clustering K means and region growing, also results are evaluated between them to find effective segmentation method. It is inferred from this graph, that the discussed FCM help in the efficient selection of the cluster centre having improved accuracy of 94% for cluster centre selection. But, the earlier techniques including K-means, adaptive K-means and region growing yields reduced accuracy compared to the FCM in terms of superior clustering results for wound segmentation with increased accuracy rate. Though existing clustering methods performing the segmentation of the input image provided into lab colour regions with identical homogeneous features effectively, a wound identification technique is needed for understanding the classification yielding useful decision on wound boundary and it can be easily understood by the users of the wound determination system. newline newline newline