Our newest improvements to style transfer have improved results even further, with better quality results that are both artistically more distinctive and more recognizable in content. The first improvement used an additional color transformation step to remove color differences before style transfer, and re-add the difference afterwards using an inverted transformation; without it, the best results would require the style and content inputs have similar color schemes. The second improvement is much more involved, but essentially involves identifying regions of a given image.
Good morning fellow code monkeys! Today I’d like to talk about computer vision, and how it can be used in a fairly basic fashion to process whiteboard images and improve them. This technology is fairly mainstream, but the reader should be warned that Microsoft holds a patent on rectifying whiteboard images, but I doubt it would stand up in court. There are also many other patents that seem similar. As always, make your millions at your own risk.
Blurred Image Deblurred Image Recently, Google open-sourced a toolkit called TensorFlow which provides a platform for neural networks. It provides a native core written in C, and many examples written in Python. Although the architecture is extensible and will hopefully will be usable from Java/Scala application code in the future, I took some time recently to evaluate it using Python to perform deconvolutions (a.k.a. deblurring), the same task I recently wrote about using my own NN library.
I’ve gotten to an interesting point in my latest project, inspired by Google’s fascinating recent work with convolutional neural networks. The project can now apply inverse convolution operations using multiple fitness functions. I wanted to explore the technology of image processing neural networks from the ground-up, so I started by building the fundamentals of a backpropagation neural network library. Building the basic components and solving the initial problems has been interesting, and surprisingly complex.