a). Document Image Quality Enhancement Using Deep Neural Network: In this project, we are working on improving the quality of low resolution, degraded, binary document images for better readability and OCR accuracy. As seen in Fig. (a), our technique is able to fill in most of the missing pixels. In terms of OCR recognition, there is a huge increase in the character level accuracy.
b). Computationally Efficient Approaches to Natural Image Super-resolution: In this project, we are developing computationally efficient deep neural network models to obtain generalized super-resolution of natural images. Our models are lightweight in terms of the number of parameters used. Figure (b) shows that the perceptual quality of the images generated by our methods is better than that of the state-of-the-art technique, SRGAN.
c). Indian patent under examination: Method and System for enhancing binary document image quality for improving readability and OCR performance.