Enhancement of Anime Imaging Enlargement using Modified Super-Resolution\n CNN

Abstract

Anime is a storytelling medium similar to movies and books. Anime images are\na kind of artworks, which are almost entirely drawn by hand. Hence, reproducing\nexisting Anime with larger sizes and higher quality images is expensive.\nTherefore, we proposed a model based on convolutional neural networks to\nextract outstanding features of images, enlarge those images, and enhance the\nquality of Anime images. We trained the model with a training set of 160 images\nand a validation set of 20 images. We tested the trained model with a testing\nset of 20 images. The experimental results indicated that our model\nsuccessfully enhanced the image quality with a larger image-size when compared\nwith the common existing image enlargement and the original SRCNN method.\n