The algorithm of formation of a training set for an artificial neural network for image segmentation
This is an incremental approach for researchers in image segmentation, focusing on reducing training data requirements.
The authors tackled the problem of image segmentation by proposing an algorithm that forms a training set using only one image, with impulse noise to generate the set and a three-layer perceptron for decision-making. The method was tested in computer experiments in automatic and interactive modes, but no concrete performance numbers were provided.
This article suggests an algorithm of formation a training set for artificial neural network in case of image segmentation. The distinctive feature of this algorithm is that it using only one image for segmentation. The segmentation performs using three-layer perceptron. The main method of the segmentation is a method of region growing. Neural network is using for get a decision to include pixel into an area or not. Impulse noise is using for generation of a training set. Pixels damaged by noise are not related to the same region. Suggested method has been tested with help of computer experiment in automatic and interactive modes.