A system based on a neural network framework is considered. We used two neural networks, an Elman network [1][2] and a Kohonen (concurrent) network [3], for a categorization task. The input of the system are objects derived from three general prototypes: circle, square, polygon. We varied the size and orientation of the objects in a continuous way. The system is trained using a new algorithm, b...

Automatic identification and localization of cartographic objects in aerial and satellite images have gained increasing attention in recent years in digital photogrammetry and remote sensing. Although the automatic extraction of man made objects in essence is still an unresolved issue, the man made objects can be extracted from aerial photos and satellite images. Recently, the high-resolution s...

We present a Self-Organizing Kohonen Neural Network for quantizing colour graphics images. The network is compared with existing algorithmic methods for colour quantization. It is shown experimentally that, by adjusting a quality factor, the network can produce images of much greater quality with longer running times, or slightly better quality with shorter running times than the existing metho...

The aim of this work is to use Self Organizing Map (SOM) for clustering of locomotion kinetic characteristics in normal and Parkinson’s disease. The classification and analysis of the kinematic characteristics of human locomotion has been greatly increased by the use of artificial neural networks in recent years. The proposed methodology aims at overcoming the constraints of traditional analysi...

One of the most frequently used methods in image processing is thresholding. This can be a highly efficient means of aiding the interpretation of images. A new technique suitable for segmenting both gray-level and color images is presented in this paper. The proposed approach is a multithresholding technique implemented by a Principal Component Analyzer (PCA) and a Kohonen Self-Organized Featur...

This paper presents a new algorithm for the deinterleaving of radar signals, based on the direction of arrival (DOA), carrier frequency (RF), and time of arrival (TOA). The algorithm is applied to classic (constant), jitter, staggered, and dwell switch pulse repetition interval (PRI) signals. This algorithm consists of two stages. In the first stage, a Kohonen neural network clusters the receiv...

Dimension-reducing feature extraction neural network techniques which also preserve neighbourhood relationships in data have traditionally been the exclusive domain of Kohonen self organising maps. Recently, we introduced a novel dimension-reducing feature extraction process, which is also topographic, based upon a Radial Basis Function architecture. It has been observed that the gener-alisatio...