Style Transfer using CNN

Style Transfer using CNN

Author Name : Yash Dusing, Vamsi Krishna Reddy Bayyapureddy Sarugari, Sujay Damodar Thakur, Manan Bhand, Rishi Rajani, Harsh Talreja

ABSTRACT

Convolutional Neural Networks (CNNs) are a category of Neural Network that have proven very effective in areas such as image recognition and classification. CNNs have been successful in computer vision related problems like identifying faces, objects and traffic signs apart from powering vision in robots and self-driving cars.

CNN is shown to be able to well replicate and optimise these key steps in a unified framework and learn hierarchical representations directly from raw images. If we take a convolutional neural network that has already been trained to recognize objects within images then that network will have developed some internal independent representations of the content and style contained within a given image.

Hence This can be violated and used for style transfer.

Objectives -

• Use neural style transfer to randomize texture, contrast, and color
• Allow users to create their own artwork using certain content and style images
• Transferring the style of the source image