Multifractal-Based Features for Medical Images Classification
Journal: International Journal of Computer Techniques (Vol.2, No. 3)Publication Date: 2015-05-01
Authors : Saad Al-Momen; Loay E. George; Raid K. Naji;
Page : 6-13
Keywords : Texture Classification; Texture Analysis; Fractal; Multifractal; Wavelet Features;
Abstract
This paper presents a method to classify colored textural images of skin tissues. Since medical images have highly heterogeneity, the development of reliable skin-cancer detection process is difficult, and a mono fractal dimension is not sufficient to classify images of this nature. A multifractal-based feature vectors are suggested here as an alternative and more effective tool. At the same time multiple color channels are used to get more descriptive features. Two multifractal based set of features are suggested here. The first set measures the local roughness property, while the second set measure the local contrast property.A combination of all the extracted features from the three color models gives a highest classification accuracy with 99.4048% for training and 95.8333% for testing
Other Latest Articles
- A Review on 3-D Digital Video Water Marking
- A SOCIOLOGICAL REVIEW ON SOCIO-CULTURE IMPACTS OF TOURISM
- A CONTRASTIVE STUDY OF SPEECH ACTS OF GREETING IN TWO PERSIAN AND ENGLISH SOAP OPERAS WITH REGARD TO THE LEVEL OF FORMALITY, STRUCTURE AND FREQUENCY
- WILFRED AND SIEGFRIED’S PROJECTION OF WAR-PHOBIA AND CONFLICT BETWEEN FRONTLINE’S BRUTAL REALITY AND RELIGION AND SPIRITUALISM
- METALLIC RESIDUES CONCENTRATION IN MUSCLE, LIVER AND KIDNEYS OF CATTLE SLAUGHTERED IN PUDUCHERRY REGION
Last modified: 2015-07-09 14:49:55