Deep Deformable Artistic Font Style Transfer

The essence of font style transfer is to move the features an image into a while maintaining font’s glyph structure. At present, generative adversarial networks based on convolutional neural play important role in generation. However, traditional that recognize images suffer from poor adaptability unknown changes, weak generalization abilities, and texture feature extractions. When structure very complex, stylized cannot be effectively recognized. In this paper, deep deformable network proposed for artistic transfer, which can adjust degree deformation according realize multiscale text. new model consists sketch module learning mapping, features, fusion textures. module, Deform-Resblock encoder designed extract convolution introduced size residual changed achieve information at different scales, preserve better, enhance controllability text deformation. Therefore, our has greater control over text, processes produce more exquisite fonts.