Chandra Shekhar

Learn More
We describe a framework for aligning images without needing to establish explicit feature correspondences. We assume that the geometry between the two images can be adequately described by an aane transformation and develop a framework that uses the statistical distribution of geometric properties of image contours to estimate the relevant transformation(More)
MaTra is a fully automatic system for indicative English-Hindi Machine Translation (MT) of general-purpose texts. This paper discusses the strengths of the MaTra approach, especially focusing on the robust strategy for parsing and the intuitive intermediate representation used by the system. This approach allows convenient enhancement of the linguistic(More)
Reconfigurable computing is an emerging paradigm of research that offers cost-effective solutions for computationally intensive applications through hardware reuse. There is a growing need in this domain for techniques to exploit parallelism inherent in the target application and to schedule the parallelized application. This leads to the need for(More)
1 Summary In this paper, we address the problem of registering two images obtained using diierent sensors, elds of view and/or lighting conditions, where conventional approaches relying on feature correspondence or area correlation are likely to fail. The approach presented in this paper eliminates the need for feature matching, and is robust to variations(More)
In this paper we present the results of a comparative study of linear and kernel-based methods for face recognition. The methods used for dimensionality reduction are Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), Linear Discriminant Analysis (LDA) and Kernel Discriminant Analysis (KDA). The methods used for classification(More)