Imitating-Artistic-Style-on-Automatically-Curated-and-Shaded-Sketches
In this project, initially we curate line-art sketch from the given Manga (Japanese Comics) charactersβ image using adaptive thresholding and then deploy Generative Adversarial Network to automatically shade the sketch, where compatible colours are learnt at pixel level from a large collection of images. Later in our experiment, we use a set of sample artistic images to transfer the style onto the shaded images previously generated to create artistic images of high perceptual quality using VGG-19 pre-trained model. The system uses neural representations to separate and recombine content and style of arbitrary images, providing a neural algorithm for the creation of artistic images.