The perceptron Training Process Optimization for Recognizing Graphic Objects in an Image

The training process of a single-layer perceptron to recognize graphic objects on a pre-segmented image is considered and proposals for the most saving neural network structure are formulated. To describe the images, descriptors invariant to the full group of affine transformations were used, their...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Systems of Signals Generating and Processing in the Field of on Board Communications (Online) S. 1 - 4
Hauptverfasser: Yakubovich, A. N., Shashina, E. V., Yakubovich, I. A.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 15.03.2022
Schlagworte:
Character recognition
Complexity theory
effective perceptron training parameters
error back-propagation algorithm
Graphics
Image recognition
neural network
Neurons
optimal perceptron structure
Safety
Training
training quality
ISSN:2768-0118
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The training process of a single-layer perceptron to recognize graphic objects on a pre-segmented image is considered and proposals for the most saving neural network structure are formulated. To describe the images, descriptors invariant to the full group of affine transformations were used, their values were the inputs of a neural network. At the perceptron outputs, the number of graphic objects of each type identified in the image was formed. The training procedure was based on the error back-propagation algorithm. Based on the results of the numerical experiment, the minimum number of the perceptron hidden layer neurons was determined, which guarantees the convergence of the training process, and the training sample volume influence on this amount was revealed. It is shown that for any volume of the training sample, there is a corresponding number of neurons in the perceptron hidden layer, which guarantees a minimum amount of computational work in the process of achieving zero training error.
ISSN:2768-0118
DOI:10.1109/IEEECONF53456.2022.9744256