Content and Style Aware Generation of Text-line Images for Handwriting Recognition
This addresses the labor-intensive data collection for handwriting recognition, offering a way to augment training data with style-diverse synthetic images, though it is incremental as it builds on existing generative methods for data augmentation.
The paper tackles the problem of generating synthetic handwritten text-line images to reduce the need for manually labeled training data in Handwritten Text Recognition, proposing a generative method conditioned on visual appearance and textual content that outperforms current state-of-the-art approaches in boosting recognition performance.
Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter- and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of manually labeled training data. To alleviate this labor-consuming problem, synthetic data produced with TrueType fonts has been often used in the training loop to gain volume and augment the handwriting style variability. However, there is a significant style bias between synthetic and real data which hinders the improvement of recognition performance. To deal with such limitations, we propose a generative method for handwritten text-line images, which is conditioned on both visual appearance and textual content. Our method is able to produce long text-line samples with diverse handwriting styles. Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content. Extensive experiments have been done on making use of the generated samples to boost Handwritten Text Recognition performance. Both qualitative and quantitative results demonstrate that the proposed approach outperforms the current state of the art.