M.S. Project Defense: Greeshma Kothireddy
Image Style Transfer Using Convolutional Neural Networks
Advisor: Dr. Yanqing Zhang
Neural style transfer is a striking, recently-developed technique that uses neural networks to artistically redraw an image in the style of a source image. Here I use image representations derived from convolutional neural networks optimized for object recognition, which make high-level image information explicit. A neural algorithm of artistic style is used that can separate and recombine the image content and style of natural images. The algorithm allows us to produce new images of high perceptual quality that combine the content of an arbitrary photograph with the appearance of numerous well-known artworks. Here, the results provide new insights into the deep image representations learned by convolutional neural networks and demonstrate their potential for high-level image synthesis and manipulation.
Transferring the style from one image onto another can be considered a problem of texture transfer. In texture transfer, the goal is to synthesize a texture from a source image while constraining the texture synthesis in order to preserve the semantic content of a target image. It was proven that convolutional neural networks—once trained with sufficient labeled data on specific tasks such as object recognition—can learn to extract high-level image content in generic feature representations that generalize across datasets and even to other visual information processing tasks, including texture recognition and artistic style classification. Here, I show how the generic feature representations learned by high-performing convolutional neural networks can be used to independently process and manipulate the content and style of natural images.
TensorFlow is used for the implementation of the image style transfer. VGG-19, a pre-trained convolutional neural network model, is used for extracting content from the content image. A deep neural network texture model is used for extracting the texture.
Dr. Yanqing Zhang (chair)
Dr. Saeid Belkasim