Novel entropy-based style transfer of the object in the content image using deep learning

Abstract

Recently neural style transfer (NST) has drawn a lot of interest of researchers, with notable advancements in color representation, texture, speed, and image quality. While previous studies focused on transferring artistic style across entire content images, a new approach proposes to transfer style specifically to objects within the content image based on the style image and maintain photorealism. Recent techniques have produced intriguing creative effects, but often only work with artificial effects, leaving real flaws visible in photographs used as references for styles. The suggested approach employs a two-dimensional wavelet transform (WT) to achieve style transfer by adjusting image structure with high-pass and low pass filters (LPF). Preserving the information content and numerical attributes of VGGNet19 through WT-based style transfer using the db5 WT at level 5, we can achieve a peak signal-to-noise ratio (PSNR) value of up to 96.76725. The qualitative result of the proposed methodology is compared with other existing algorithm. Also, the time complexity of the proposed methodology on different hardware platforms has been calculated and presented in the paper. The proposed methodology able to maintains appealing and precise quality of resultant image.