Fig 2 - uploaded by Sergejs Kodors
Content may be subject to copyright.
Download
View publication
The hexagonal SOM to generate RGB images with noise

The hexagonal SOM to generate RGB images with noise

Source publication
Fig. 1. The association of RGB image with neurons weights
Fig. 2. The hexagonal SOM to generate RGB images with noise
Fig. 3. The coordinates of the hexagonal lattice Than RGB images with...
Fig. 9. The adaptation time. (a) – the first RI neuron from SI, (b) –...
+1 Fig. 10. The effective width. (a) – the first RI neuron from SI, (b) –...
The Analysis of Noise Level of RGB Image Generated Using SOM
Article
Full-text available
  • Jan 2012
The article discusses how to generate RGB images with noise using Kohonen’s self-organizing map (SOM). The article also describes the adaptation process and structure of SOM, which can be used to generate RGB images with noise. The authors of the article evaluate the influence of SOM parameters (a learning coefficient, adaptation time, effective wi...
Cite
Download full-text

Context in source publication

Context 1
... of the images, which are inclined to some colour, a hexagonal type of the lattice with the predefined winning neurons can be used: the central neuron weights are equal to the generated image colour values (to input signal RGB), the corner neuron weights are equal to inputs {R, RG, G, GB, B, RB}. Other neuron weights have the random values (see Fig. 2). The distance between two neurons of the hexagonal SOM is calculated by the formula ...

Similar publications

Fig. 1. Illustration of a feature extractor to generate an image...
Fig. 2. An example using Thumbnails to reduce by 4 the foot image  
Fig. 3. Schematic example of SOM image representation  
Fig
Fig
Image Representation Using the Self-Organizing Map
Article
Full-text available
  • Jan 2013
This paper introduces a new approach to image representation for multimedia databases based on the Self-Organizing Map (SOM) neural network. The distance between each image from a database and the SOM weight vectors trained on the same database is used as a representation for the image. In order to assess the performance of this proposal we compare...
View

Citations

... 2. The artificial neural network has the ability to filter out noise and get the correct conclusion in the case of noisy [6]. It can train the artificial neural network to identify the fault information, so that it can effectively operate in noisy environments, the noise filtering capability such that the artificial neural networks for fault detecti 3. Artificial neural network has the ability to distinguish fault causes and fault types [2] on and diagnosis line. ...
View