Development of a Segmentation Method for Dermoscopic Images Based on Color Clustering
GRIN Verlag, 2007 - 88 pages
Doctoral Thesis / Dissertation from the year 2003 in the subject Computer Science - Applied, grade: Pass grade, Kobe University (Faculty of Engineering, Department of Computer & Systems Engineering, Kitamura Lab), course: Doctor Course Information and Media Science, 41 entries in the bibliography, language: English, abstract: Malignant melanoma is a very dangerous kind of skin cancer. In order to treat malignant melanoma it must be detected as early as possible. However, when looking at a malignant melanoma by the naked eye, it can be mistaken as a nevus (benign skin lesion). Therefore, dermatologists use a microscope that shows the pigmented structure of the skin. This microscope is called "dermoscope." An irregular overall structure, an irregular border and several colors indicate that a skin lesion is malignant. A homogeneous structure, a regular border and few colors indicate that a lesion is benign. However, even when using a dermoscope a melanoma can be mistaken as a nevus. Therefore it is desirable to analyze dermoscopic images by a computer in order to classify them as malignant or benign. Before a dermoscopic image is classified, usually the skin lesion border is extracted. For this purpose, previously developed methods segment the image into regions of the same color (color segmentation) or into regions that fulfill a homogeneity criterion (region based segmentation). Color segmentation can be done using fuzzy c-means. When applying fuzzy c-means, the number of cluster centers corresponds to the number of distinguished colors and must be specified. However, the number of colors in dermoscopic images can vary and is not known in advance. The goal of this research is developing a method that automatically determines the number of clusters in color space. The clustering accuracy is evaluated by cluster validity index. Cluster validity indices describe how well a partition (cluster center set) represents the "natural" clusters of a data set. The method prop
What people are saying - Write a review
We haven't found any reviews in the usual places.
Color Clustering Methodology _______________
Color Clustering by SelfOrganizing Maps _____
Objective Functions for Color Clustering ______
Classification of Dermoscopic Images _________
Other editions - View all
2D center split adjusted grid applied calculated chapter classification performance cluster validity index clustering method co-occurrence matrix color clustering color statistics color vectors components Davies-Bouldin index dermoscopic images Euclidean distance Experimental settings fitness scaling Fukuyama-Sugeno index genetic algorithm given in Tab gray level image greedy algorithm Harald Galda histogram image segmentation initial population initial weight vectors input vector inputs of number irregularity Kohonen map local optimum maximum minimum number normalized power spectrum number of clusters number of colors number of features number of individuals number of neurons number of offspring number of pixels optimal number partition Penergy perceptually uniform pigmented structures possible number probability density function quadratic quantization error region RGB image RGB space roulette wheel selection sampling without replacement segmentation method proposed segmented image selection strategy self-organizing map sensitivity and specificity skin lesion standard deviation stochastic remainder sampling texture u*max v*min weight vector initialization winning neuron Xie-Beni index
Page 70 - Lee: On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques.
Page 69 - BINDER, M, KITTLER, H, SEEBER, A, STEINER, A, PEHAMBERGER, H, WOLFF, K. Epiluminescence microscopy-based classification of pigmented skin lesions using computerized image analysis and an artificial neural network.
Page 69 - Digital epiluminescence microscopy: usefulness in the differential diagnosis of cutaneous pigmentary lesions. A statistical comparison between visual and computer inspection. Melanoma Res 2000; 10: 345-9.
Page 69 - P. Schmid-Saugeon. Symmetry axis computation for almost-symmetrical and asymmetrical objects: Application to pigmented skin lesions.
Page 69 - Dermoscopy (epiluminescence microscopy) of pigmented skin lesions. Current status and evolving trends.
Page 70 - T. Pavlidis, Algorithms for Graphics and Image Processing, Computer Science Press, Rockville, 1982.
Page 68 - Annual Conference of the Institute of Systems, Control and Information Engineers, pp. 427 — 428, May 15...
Page 69 - Neural networks and artificial intelligence for biomedical engineering", IEEE Press, New York, 1999 [51 W.
Page 70 - M. Jackowski, A. Goshtasby, D. Roseman, S. Bines, C. Yu, A. Dhawan, and A. Huntley, Segmentation of skin cancer images, Image and Vision Computing, 17:65-7 '4 (1999).