Re:Computational Synesthesia: Audio Analysis with Image Proc...
by doctoboggan on Tuesday October 01, 2013 @12:50PM
(#6477338)
I used the spectrogram just to get the audio in a 2d representation that was insensitive to timeshifts. The image processing part was the `match_template` function from skimage.
Although normalized correlation (which is what `match_template` uses) has been applied outside of image processing before. I also tried other image processing techniques like harris corner detection and SURF feature detection. I didn't write them up but you can see the code on github:
Although normalized correlation (which is what `match_template` uses) has been applied outside of image processing before. I also tried other image processing techniques like harris corner detection and SURF feature detection. I didn't write them up but you can see the code on github:
https://github.com/jminardi/audio_fingerprinting