Tata Consultancy Services Limited

Narendra N

Achanna Anil Kumar

Balamuralidhar Purushothaman

Girish Mariswamy Chandra

M Girish Chandra

Balamuralidhar P

Systems and methods for reconstructing super-resolution images under total aliasing based upon translation values. Traditional systems and methods provide for extracting super-resolution (SR) image/s from low-resolution (LR) image/s but include aliasing as a background noise which degrades the performance or include aliasing into an image model which leads to an enormously high computational complexity. Embodiments of the present disclosure provide for reconstructing super-resolution images based upon translation values by taking aliasing in consideration by capturing a set of LR images, estimating, using a Fast Fourier Transformation, a set of translation values based upon the set of LR images, obtaining, using a multi-signal classification technique, one or more optimized frequency spectrums based upon the set of translation values and reconstructing one or more SR images based upon the set of translation values.

Systems and methods for reconstructing super-resolution images under total aliasing based upon translation values

This disclosure relates generally to image processing, and more particularly to generate a high resolution image from multiple low resolution images. In an embodiment, the system collects a plurality of low resolution images as input, processes the collected images, and generates a high resolution image as output. During this process, the system pre-processes the collected low resolution images, and during this process, at least one characteristic of each of the low resolution image is changed with respect to a reference image. After the pre-processing stage, the images are then enhanced based on a plurality of final enhancement factors that are dynamically determined. Further, the enhanced images are fused to generate the high resolution image.

Growing community of inventors

Bengaluru, India

Narendra N