Top all-time · #13043
Free Won't
Personal blog · laplacian.wordpress.comprogrammingscience
Free Won't is a personal blog at laplacian.wordpress.com about programming and science. Since 2009, 6 different Hacker News readers have linked it 6 times, most often “How Shazam Works”. The last post was in 2011, but the archive is still widely read.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link these posts as plain-language explanations of how Shazam's audio fingerprinting works, and as a summary of the 2003 Shazam research paper. Commenters cite them as sources rather than judging them.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
A curious engineer attempts to deconstruct everything
Most-linked posts?
- How Shazam Works6 people · 6 mentions · first linked 2009-10-28
What Hacker News says?
http://www.redcode.nl/blog/2010/06/creating-shazam-in-java/ http://laplacian.wordpress.com/2009/01/10/how-shazam-works/
Comment linking /2009/01/10/how-shazam-works/
on “You can't do that”Submitted How Shazam Works as a story · 6 points
HN discussionIt's unfortunate that the patent language is mired in obtuse legalese rather than understandability by actual programmers. For example, take a Shazam-like song id algorithm. Technical blog post explaining the technology: http://laplacian.wordpress.com/2009/01/10/how-shazam-works/ Patent covering such an algo(is it the same? I can't even tell!): http://www.google.com/patents/US6941275?dq=.+6,941,275 From http://en.wi…
Comment linking /2009/01/10/how-shazam-works/
on “Transform any text into a patent application”Submitted How Shazam Works as a story · 4 points
HN discussionI'm actually guessing not. It's probably something similar algorithm-wise to what Shazam does. Probably not a crypto-hash, but more likely a hashing of robust features (in a relative as opposed to absolute location form) detected from the image to give a "fingerprint." Such features would be robust to scaling and most compression artifact issues. EDIT: Here's a good example: http://laplacian.wordpress.com/2009/01/10…
Comment linking /2009/01/10/how-shazam-works/
on “Google tips off cops after spotting child abuse images in email”you might want to take a look at the Shazam song classification system, which essentially does a 'brute force' search like the one you sketched out, except with a lot of cleverness to make it run super-fast research paper: http://www.ee.columbia.edu/~dpwe/papers/Wang03-shazam.pdf blog entry summarizing paper: http://laplacian.wordpress.com/2009/01/10/how-shazam-works/
Comment linking /2009/01/10/how-shazam-works/
on “Ask HN: Completely crazy idea for an image classification system?”