Our group has previously used machine learning techniques to develop computational systems to automatically analyse fluorescence microscope images and classify the location of the ...
This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape...
We present a robust method for 3D reconstruction of closed surfaces from sparsely sampled parallel contours. A solution to this problem is especially important for medical segment...
Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a g...
Optical character recognition of cursive scripts present a number of challenging problems in both segmentation and recognition processes and this attracts many researches in the fi...