Java-Oriented Approach to Image Understanding through Artificial Neural Networks

The Image Processing and Computer Vision research provides a focus for the development of techniques for image recognition and the analysis of image structures. The main area of our research activity currently includes the development of high performance algorithms and a study of appropriate processing architectures and implementation strategies for their realization. Our approach is based on artificial neural networks, which are often used as classifiers in pattern-recognition applications because of the ters will be included in order to obtain a hard copy of any window.

2.Generation of some Java libraries to aid in multiple visualization, in choice of NN parameters and NN architectures.

3.Design of segmentation algorithms which concentrate on developing new features, which are invariant to a range of transformations including scale and orientation.