I'm a student, and currently into image processing project and coding using OpenCV. Recently, I watched Sebastian Thrun from Udacity in TedTalks talked about AlphaGo and I'm totally interested in the idea. I have read this question too : Merged Neural Network in AlphaGo. I was wondering if same approaches can be used in my project.

I'm going to perform color enhancement method for any natural images. And of course, color sampling is a tricky task now. It's a lot of work, I have to prepare condition for each key-color sampling given and also prepare & pick the best enhancement function for it. I'm able to do it already using OpenCV.

But I was wondering if I could load tons of sample pictures instead, have my system test them against each other, and figure out its own enhancement rules from all testing.

I'm not that familiar with Deep Learning, we don't even have deep learning course at my university, but I'm interested in the idea and ready to learn. I'm not even sure if this can be done or not, but I wonder what kind of approaches should I learn to achieve my goal ? Is Deep Learning --> Neural Network a good start ? In my case, to which method in Deep Learning should I go with ? Any reference / advice will be highly appreciated. Thanks.



You must log in to answer this question.

Browse other questions tagged .