An Effective Image Feature Classiffication using an improved SOM

TL;DR

This paper introduces an improved Self Organizing Map (iSOM) with a novel node structure and adaptive learning for more accurate mammographic image classification based on texture features.

Contribution

The paper proposes a new node structure and a class-reliability based learning technique for SOM, enhancing image classification performance.

Findings

Higher accuracy than classical SOM

Effective in mammographic texture classification

Outperforms state-of-the-art classifiers

Abstract

Image feature classification is a challenging problem in many computer vision applications, specifically, in the fields of remote sensing, image analysis and pattern recognition. In this paper, a novel Self Organizing Map, termed improved SOM (iSOM), is proposed with the aim of effectively classifying Mammographic images based on their texture feature representation. The main contribution of the iSOM is to introduce a new node structure for the map representation and adopting a learning technique based on Kohonen SOM accordingly. The main idea is to control, in an unsupervised fashion, the weight updating procedure depending on the class reliability of the node, during the weight update time. Experiments held on a real Mammographic images. Results showed high accuracy compared to classical SOM and other state-of-art classifiers.