This learning machine could be trained to transfer the picture style to a totaly different one which may have the used work refreshed. This is the example given in ml5
Style transfer is a fast advancing technique that allows to transfer the visual style of one image to the content of another image. Gatys et al. created Neural Style Transfer [1] which is a method for transferring the artistic style an image to another image by iteratively updating an initial noise image.
The appication in daily life
The resulting images look like artwork (paintings), but they don’t look like photographs. Instead of painterly style transfer, Luan et al., give us photographic style transfer. Photographic style transfer is a long-standing problem that seeks to transfer the style of a reference style photo onto another input picture.
For instance, by appropriately choosing the reference style photo, one can make the input picture look like it has been taken under a different illumination, time of day, or weather, or that it has been artistically retouched with a different intent.
coding part
The following example is illustrated and supported by ml5 and Tensorflow. For more details please check the above-mentioned websites.
ml5.js aims to make machine learning approachable for a broad audience of artists, creative coders, and students. The library provides access to machine learning algorithms and models in the browser, building on top of TensorFlow.js with no other external dependencies
TensorFlow.js is a machine Learning in JavaScript. Use flexible and intuitive APIs to build and train models from scratch using the low-level JavaScript linear algebra library or the high-level layers API.
