Improving Document Binarization via Adversarial Noise-Texture Augmentation
This addresses document image analysis for improved binarization, but it is incremental as it builds on existing adversarial methods.
The paper tackled the problem of binarizing degraded document images by introducing an adversarial learning approach that generates noisy-texture augmented images to enlarge datasets, achieving superior performance on DIBCO datasets.
Binarization of degraded document images is an elementary step in most of the problems in document image analysis domain. The paper re-visits the binarization problem by introducing an adversarial learning approach. We construct a Texture Augmentation Network that transfers the texture element of a degraded reference document image to a clean binary image. In this way, the network creates multiple versions of the same textual content with various noisy textures, thus enlarging the available document binarization datasets. At last, the newly generated images are passed through a Binarization network to get back the clean version. By jointly training the two networks we can increase the adversarial robustness of our system. Also, it is noteworthy that our model can learn from unpaired data. Experimental results suggest that the proposed method achieves superior performance over widely used DIBCO datasets.