Image Style Transfer with Feature Extraction Algorithm using Deep Learning
Yuan Liu, Francisco Emmanuel T. Munsayac, Nilo T. Bugtai, Renann G. Baldovino · 2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) · 2021
Image style transfer, as one of significant image editing tasks, uses existing artistic works for the purpose of image recreation. This imaging technology can integrate well a given stylistic image into the given content image, so as to create new artworks with certain characteristics. In recent years, the emergence of deep learning neural network, especially the convolutional neural network (CNN), has greatly accelerated the development of image style transfer algorithm, making it one of the most widely used in artworks creation, font style transfer, movie special effects rendering and mobile device photo rendering. This paper introduces a new algorithm based on the concept of deep learning in achieving image style transfer by merging content image and style image to obtain the stylized image.