Publications

Abstract : With the recent improvement in machine learning and deep learning technologies due to an increase in computation power, its uses for image processing and computer vision have also increased. The style of the image, through orthodox methods, has been changed with the help of filters that are not capable of applying the style from only a few sets of options, with no consideration for semantic or contextual data. The transfer of style is also limited to the entire image, with no provisions for applying style to only a selected portion of it. Through advanced deep learning technologies, style transfer can be achieved with semantic and contextual accuracy while also providing the ability to apply to a selected portion of the image. The style can also be generated through the use of images generated for the text using deep learning.