<abstract xmlns="http://www.w3.org/1999/xhtml"><p> Accurate classification of images is essential for the analysis of mammograms in computer aided diagnosis of breast cancer. We propose a new approach to classify mammogram images based on fractal features. Given a mammogram image, we first eliminate all the artifacts and extract the salient features such as Fractal Dimension (FD) and Fractal Signature (FS). These features provide good descriptive values of the region. Second, a trainable multilayer feed forward neural network has been designed for the classification purposes and we compared the classification test results with K-Means. The result reveals that the proposed approach can classify with a good performance rate of 98%.</p></abstract>

Accurate classification of images is essential for the analysis of mammograms in computer aided diagnosis of breast cancer. We propose a new approach to classify mammogram images based on fractal features. Given a mammogram image, we first eliminate all the artifacts and extract the salient features such as Fractal Dimension (FD) and Fractal Signature (FS). These features provide good descriptive values of the region. Second, a trainable multilayer feed forward neural network has been designed for the classification purposes and we compared the classification test results with K-Means. The result reveals that the proposed approach can classify with a good performance rate of 98%.

A New Approach for Mammogram Image Classification Using Fractal Properties

School of Computer Science and Engineering, Konkuk University Sciences, Hwayang-dong, Seoul, 133-701, Korea

Department of Computer Science, University of Kerala, Trivandrum, India

School of Business IT, Kookmin University, Jeongneung-dong, Seongbuk-gu, Seoul, 136-792, Korea

Cybernetics and Information Technologies

{"article-title":"A New Approach for Mammogram Image Classification Using Fractal Properties"}

Accurate classification of images is essential for the analysis of mammograms in computer aided diagnosis of breast cancer. We propose a new approach to...

A New Approach for Mammogram Image Classification Using Fractal Properties

Publicado en línea: 16 mar 2013

Páginas: 69 - 83

DOI: https://doi.org/10.2478/cait-2012-0013

Palabras clave
Fractal Dimension, Fractal Signature, mammograms, self-similarity, classification

This content is open access.

A New Approach for Mammogram Image Classification Using Fractal Properties

Publicado en línea: 16 mar 2013

Páginas: 69 - 83

DOI: https://doi.org/10.2478/cait-2012-0013

Palabras claveFractal Dimension, Fractal Signature, mammograms, self-similarity, classification

This content is open access.

Palabras clave
Fractal Dimension, Fractal Signature, mammograms, self-similarity, classification