Binary Document Image Super Resolution for Improved Readability and OCR Performance
This work addresses the problem of retrieving information from low-resolution binary document images in digital libraries, particularly for Tamil documents, but it is incremental as it applies existing super-resolution techniques to a specific domain.
The paper tackled super-resolution of low-resolution binary Tamil document images to enhance readability and OCR performance, proposing multiple deep neural network architectures that achieved improved OCR accuracies and human evaluator scores compared to the original low-resolution images.
There is a need for information retrieval from large collections of low-resolution (LR) binary document images, which can be found in digital libraries across the world, where the high-resolution (HR) counterpart is not available. This gives rise to the problem of binary document image super-resolution (BDISR). The objective of this paper is to address the interesting and challenging problem of super resolution of binary Tamil document images for improved readability and better optical character recognition (OCR). We propose multiple deep neural network architectures to address this problem and analyze their performance. The proposed models are all single image super-resolution techniques, which learn a generalized spatial correspondence between the LR and HR binary document images. We employ convolutional layers for feature extraction followed by transposed convolution and sub-pixel convolution layers for upscaling the features. Since the outputs of the neural networks are gray scale, we utilize the advantage of power law transformation as a post-processing technique to improve the character level pixel connectivity. The performance of our models is evaluated by comparing the OCR accuracies and the mean opinion scores given by human evaluators on LR images and the corresponding model-generated HR images.