Suprava Patnaik

Learn More
Motion blur caused by relative motion between the camera and the object being captured is an everyday situation that deteriorates the quality of the images largely. Even a photograph captured in low light conditions or that of a fast moving object undergo motion blur and cause significant degradation of the image and demands for deblurring the same to(More)
The objective of voice conversion system is to formulate the mapping function which can transform the source speaker characteristics to that of the target speaker. In this paper, we propose the General Regression Neural Network (GRNN) based model for voice conversion. It is a single pass learning network that makes the training procedure fast and(More)
— Image registration is an important and fundamental task in image processing used to match two different images. Given two or more different images to be registered, image registration estimates the parameters of the geometrical transformation model that maps the sensed images back to its reference image. A feature-based approach to automated(More)
In this paper an image fusion technique is developed to remove clouds from satellite images. The proposed method involves an auto associative neural network based PCAT (principal component transform) and SWT (stationary wavelet transform) to remove clouds recursively which integrates complementary information to form a composite image from multitemporal(More)
The application of the level set method in image segmentation has been very popular due to its capability of automatically handling changes in topology. However, a re-initialization procedure, which leads to expensive computation, is required in the traditional level set method to keep the level set function as a signed distance function to its interface. A(More)
A near accurate method for extracting blur parameters from a non-uniformly motion blurred images; in a blind image deconvolution scheme is proposed. In case of a non-uniform motion blur, we should be able to extract both the blur parameters and the combination of their extent fairly accurate, in order to improve the quality of the restored image. Initially,(More)
— This paper addresses an intrinsic rule-based license plate localization (LPL) algorithm. It first selects candidate regions, and then filters negative regions with statistical constraints. Key contribution is assigning image inferred weights to the rules leading to adaptability in selecting saliency feature, which then overrules other features and the(More)
In a vehicle license plate extraction system, plate region detection is the key step before the final recognition. This paper presents a license plate detection algorithm from complex background based on gradient analysis and prolonged haar wavelet transform. First the license plate region is approximately detected using gradient analysis and top hat(More)