Wyniki wyszukiwania - BazTech

1

Noisy image segmentation using a self-organizing map network

Gorjizadeh S, Pasban S, Alipour S

Advances in Science and Technology. Research Journal

|

2015

|

Vol. 9, nr 26

118–-123

EN

Image segmentation is an essential step in image processing. Many image segmentation methods are available but most of these methods are not suitable for noisy images or they require priori knowledge, such as knowledge on the type of noise. In order to overcome these obstacles, a new image segmentation algorithm is proposed by using a self-organizing map (SOM) with some changes in its structure and training data. In this paper, we choose a pixel with its spatial neighbors and two statistical features, mean and median, computed based on a block of pixels as training data for each pixel. This approach helps SOM network recognize a model of noise, and consequently, segment noisy image as well by using spatial information and two statistical features. Moreover, a two cycle thresholding process is used at the end of learning phase to combine or remove extra segments. This way helps the proposed network to recognize the correct number of clusters/segments automatically. A performance evaluation of the proposed algorithm is carried out on different kinds of image, including medical data imagery and natural scene. The experimental results show that the proposed algoise in comparison with the well-known unsupervised algothms.

2

Intelligent prediction of milling strategy using neural networks

Klancnik S., Balic J., Cus F.

Control and Cybernetics

|

2010

|

Vol. 39, no 1

9-24

EN

This paper presents the prediction of milling tool-path strategy using Artificial Neural Network (ANN), by taking the predefined technological objectives into account. In the presented case, the best possible surface quality of a machined surface was taken as the primary technological aim. This paper shows how feature extraction from a 3D CAD model, and classification using a self-organizing neural network, are done. The experimental results presented in this paper suggest that the prediction of milling strategy using the self-organizing neural network (SOM) is effective.

3

Anizotropowe modele sieci neuronowych SOM

Cader A.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2003

|

T. 7, z. 3

537-542

PL

Klasyczne sieci SOM dają się modyfikować w różny sposób. Jednym z ciekawszych rozwiązań może być nadanie anizotropii warstwie Kohonena poprzez przyporządkowanie poszczególnym jej wymiarom różnych cech znaczących, a to z kolei stwarza podstawy dla kategoryzacji wielowymiarowej. Zaproponowano różne konstrukcje algorytmu prowadzącego do takich modeli sieci SOM oraz dokonano wstępnej oceny efektywności przyjętych rozwiązań.

EN

Classical Self Organizing Maps networks are easy to be modified in a different ways. One of the interesting solutions can be an anisotropy given to a Kohonen layer. It can be done by assigning various features to its different dimensions. This assignment is a basis of multidimensional optimization. In this paper various algorithms leading to such SOM networks models were proposed. Also some introductory estimates of assumed solutions were established.