Generative Adversarial Network for Handwritten Text
This work addresses the problem of generating synthetic handwritten data for applications in document analysis or data augmentation, though it appears incremental as it adapts GANs to a specific domain.
The paper tackles the challenge of generating realistic handwritten text by proposing a handwriting generative adversarial network (HWGANs) that synthesizes sequential stroke data, with results showing it produces more natural and realistic text compared to existing generators.
Generative adversarial networks (GANs) have proven hugely successful in variety of applications of image processing. However, generative adversarial networks for handwriting is relatively rare somehow because of difficulty of handling sequential handwriting data by Convolutional Neural Network (CNN). In this paper, we propose a handwriting generative adversarial network framework (HWGANs) for synthesizing handwritten stroke data. The main features of the new framework include: (i) A discriminator consists of an integrated CNN-Long-Short-Term- Memory (LSTM) based feature extraction with Path Signature Features (PSF) as input and a Feedforward Neural Network (FNN) based binary classifier; (ii) A recurrent latent variable model as generator for synthesizing sequential handwritten data. The numerical experiments show the effectivity of the new model. Moreover, comparing with sole handwriting generator, the HWGANs synthesize more natural and realistic handwritten text.