Y.V. Venkatesh

Learn More
We integrate the advantages of SOM- and snake-based ACMs in order to extract the desired contour from images. We employ: (i) the feature points to guide the contour, as in the case of SOM-based ACMs; (ii) the gradient and intensity variations in a local region to control the contour movement. However, in contrast with the snake-based ACMs, we do not use an(More)
Adaptive filtering of damped sinusoids is considered in this paper. Damped sinusoids include sinusoids as a special case. The recently proposed instantaneous matched filter (IMF) approach, its limitation, and a remedy, are discussed. Its recursive implementation that circumvents the limitation is shown to consist of the same equations as those of recursive(More)
We deal with the problem of determining disparity in gray-level stereoimage-pairs, by treating it as a nonlinear classification problem, and invoking Marr and Poggio's (October 1976) neighborhood criterion. To this end, we propose the application of an artificial neural network (ANN). The main contribution of the paper is believed to be the use of neurons(More)
  • 1