SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators
This work addresses data augmentation for handwritten text recognition systems, but it appears incremental as it builds on existing patch loss methods.
The paper tackles the problem of generating realistic handwritten text by proposing SmartPatch, a technique that improves current state-of-the-art methods by mitigating pen-level artifacts, resulting in more realistic and higher-quality generated handwritten words.
As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation. The generation of realistic-looking hand-written text is important because it can be used for data augmentation in handwritten text recognition (HTR) systems or human-computer interaction. We propose SmartPatch, a new technique increasing the performance of current state-of-the-art methods by augmenting the training feedback with a tailored solution to mitigate pen-level artifacts. We combine the well-known patch loss with information gathered from the parallel trained handwritten text recognition system and the separate characters of the word. This leads to a more enhanced local discriminator and results in more realistic and higher-quality generated handwritten words.