ABSTRACT
Skin lesion segmentation is one of the crucial steps for an efficient non-invasive computer-aided early diagnosis of melanoma. This paper investigates how to use colour information, besides saliency, for determining the pigmented lesion region automatically. Unlike most existing segmentation methods using only the saliency to discriminate against the skin lesion from the surrounding regions, we propose a novel method employing a binarization process coupled with new perceptual criteria, inspired by the human visual perception, related to the properties of saliency and colour of the input image data distribution. As a means of refining the accuracy of the proposed method, the segmentation step is preceded by a pre-processing aimed at reducing the computation burden, removing artefacts, and improving contrast. We have assessed the method on two public databases, including 1497 dermoscopic images. We have also compared its performance with classical and recent saliency-based methods designed explicitly for dermoscopic images. The qualitative and quantitative evaluation indicates that the proposed method is promising since it produces an accurate skin lesion segmentation and performs satisfactorily compared to other existing saliency-based segmentation methods.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Giuliana Ramella
Giuliana Ramella is a researcher of the Italian National Research Council (CNR) since 1994, where is currently working at the Institute for the Applications of Calculus ‘M. Picone’. Since the year 2000, she has had many teaching contracts in the field of Computer Science with three universities in Naples. Currently, she is a contract professor at the University of Naples ‘Federico II’.
Her scientific interests are mainly focused on Image Processing, Pattern Recognition, Computer Vision, Data Compression, and Digital Geometry and Topology. Her research is methodologically centred on Human Perception Theory, addressing in particular image compression, shape representation and description, image segmentation, multiresolution analysis, colour image processing, image forgery detection, image resizing. The research is oriented towards real applications, dealing with a variety of actual problems in several areas, ranging from Biomedicine, Cultural Heritage, Agricultural, Future Internet, Environment to Security.