I have some questions regarding image processing and sonification. I've only recently started learning Max/MSP/Jitter for my project. For my project - I'm planning to sonify an image. Mapping will be between colour to sound as well image edges to sound for visually impaired people.
I know they are a lot researches out there trying to directly sonify the image data.. Focussing on the mapping of image edges to sound.. I've tried to do in C++ in which I managed to do Sobel and Robert filters to transform the image into something that contains data more descriptive of the actual content of the image. I have yet to try using jit.robcross or jit.sobel.. as I haven't reached that part of tutorial ..but I assume the results would be similar.
I was also told to try to use something like neural networks to sonify 'features' rather than the image data..where I can sonify whatever parameters my neural network puts out.
I've been trying to figure how do I go about and do this in Max/Msp.. or is it not possible? I also have been looking into Processing for this project.
Looking forward to your inputs