An Effective Image Feature Classiffication using an improved SOM

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.

A Contemporary Review of High Voltage Partial Discharge Detection and Recognition Techniques

“…Back in 1990, Kohonen discovered the Self-Organizing Maps (SOMs) known as the Kohonen Map. [107,108]. Kohonen Map or SOM was based on unsupervised learning neural network that falls into the self-learning category.…”

“…Self-Organized is described as the capacity to cluster and visualise data that is arranged on a low-dimensional neuron. Simultaneously, the maps specified the features to examine the degree of accuracy of the finished mapping's foundation input data [107,109,110]. Currently, the SOM maps are depicted by Unified Matrix to facilitate further on the classified data as shown in Figure 7.…”

“…(1) Based on four main PD recognition methods reviews, the SOM classification method possessed substantial benefits such as; solving the problem via iterative training, being easy to interpret and implement using a simple two dimensional (2D) structure, and being capable of organizing complexity input data and massive data mapping [107,109]. These are the important attributes that are desirable for an efficient and crucial PD recognition method.…”