I. Astrov, S. Tatarly, and E. Rüstern (Estonia)
Image processing and analysis, neural networks,simulation, and two-rate.
This paper presents the two-rate hybrid Kohonen neural network (TRHKNN) for recognition and restoration of blurred images of complex structure. The illustrative examples - recognition and restoration for images of noised irregular figures were carried out using the TRHKNNs. The received TRHKNNs have not only high speed of image processing, but also high speed of image restoration. These examples demonstrate that the proposed TRHKNNs are capable not only to distinguish the noisy input, but also to restore reference images. The simulation results with use the software package Simulink show the computing procedure and applicability of TRHKNNs for fast-acting image processing and analysis in real-time conditions.
Important Links:
Go Back
