Adversarial Generation of Handwritten Text Images Conditioned on Sequences

We propose a system based on Generative Adversarial Networks (GAN) to produce synthetic images of handwritten words. We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network. We also modify the standard GAN by adding an auxiliary network for text recognition. The system is then trained with a balanced combination of an adversarial loss and a CTC loss. Together, these extensions to GAN enable to control the textual content of the generated word images yielding realistic-looking images on both French and Arabic languages. State-of-the-art offline handwriting text recognition systems tend to use neural networks and therefore require a large amount of annotated data to be trained. In order to partially satisfy this requirement, we could use those synthetic images to increase the amount of training data. We show that integrating generated images into the existing training data of a text recognition system can slightly enhance its performance.