In this study, we try to implant chaotic features into the learning algorithm of self-organizing map. We call this concept as Chaotic SOM (CHAOSOM). As a first step to realize CHAOSOM, we consider the case that learning rate and neighboring coefficient of SOM are refreshed by chaotic pulses generated by the Hodgkin-Huxley equation. We apply the CHAOSOM to solve a traveling salesman problem and ...

Handwritten signatures are the most natural way of authenticating a person’s identity. An offline signature verification system generally consists of four components: data acquisition, preprocessing, feature extraction, recognition and verification. This paper presents a method for verifying handwritten signature by using NN architecture. In proposed methods the multi-layer perceptron (MLP), mo...

pucker grade is one of the most important quality parameters in garments manufacturing industry. At present, seam pucker is usually evaluated by human inspectors, which is subjective, unreliable and time-consuming. Instead of subjective evaluation, this paper presents an objective method by using image analysis and pattern recognition. The evaluation system consists of image acquisition, image ...

We propose a two-stage hierarchical arti®cial neural network for the segmentation of color images based on the Kohonen self-organizing map (SOM). The ®rst stage of the network employs a ®xed-size two-dimensional feature map that captures the dominant colors of an image in an unsupervised mode. The second stage combines a variable-sized one-dimensional feature map and color merging to control th...

It is often reported in the technique literature that the success of the self-organizing feature map (SOM) formation is critically dependent on the initial weights and the selection of main parameters of the algorithm, namely, the learning-rate parameter and the neighborhood set. In this paper, we propose a healing mechanism to repair feature maps that are not well topologically ordered. The he...

This paper presents two variations of the Self-Organizing Map in order to adapt it for special input signal attributes. The first one improves the properties concerning outliers and clusters with low feature density within the provided training data set by changing the neighbourhood function while training the net. In the second introduced modification the originally twodimensional feature map ...