Transformation Invariant Reverse Image Search
AI
reverse image search
SHOW HN2017
Transformation Invariant Reverse Image Search
Transformation Invariant Reverse Image Search
pippy360.github.io#reverse image search#affine invariant#image hashing#perceptual hash
How HN took it
7 positive, 9 neutral or asking, 0 mixed, 0 critical, out of 16 comments about the project. Thread score +0.42.
Idea: 6 for, 0 againstPerformance: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive, simple approach using equilateral triangle normalisation
From 3 comments
Good in its simplicity. Basically, they construct not-quite-but-local hyperfeatures using edge triangles and then compute a descriptor (perceptual hash) for all these…
ansgri on HNI'm amazed at how simple this is! Making the triangles equilateral is one of those things which seems so simple in hindsight but I doubt it was easy to think of, were you…
Sean1708 on HNThis is really impressive. What I particularly like is how the demo demonstrates the usefulness of the algorithm - an article about it would be interesting, but after I cropped,…
onion2k on HN
Objections
Number of triangles grows cubically with keypoints, so large images are too slow
From 2 comments
Good in its simplicity. Basically, they construct not-quite-but-local hyperfeatures using edge triangles and then compute a descriptor (perceptual hash) for all these…
ansgri on HNUnfortunately it needs a huge amount of work to be production ready. I'd love to see it wrapped up in python though and I'll be continuing to work on it. The main issue you will…
pippy360 on HN
Requests
Wrap it as a Python library
From 1 comment
This is pretty neat. I've been using pHash to find duplicate photos across my personal library, but this seems significantly better. I'd like to wrap it as a Python library -…
rcarmo on HN
Support colour and compression/filter transformations
From 2 comments
This is great, I was toying with this kind of image recognition a year or two ago and I am impressed with this. Have you considered doing other common transformations like…
jboggan on HNVery impressive indeed. I was wondering, how did you determine your criteria for matching (i.e. the hash distance at which two triangles are considered different)? Also, could…
osrec on HN
Questions
How hashes are stored and matched
From 1 comment
That is really gorgeous, do you have anything quick written up about how your hashes are stored? I spent far too much of a few months optimizing phash to hell (I can do fuzzy…
deevnull on HN
Why triangles are transformed to equilateral
From 1 comment
Hey Tom, Great work there! One question - Why are we transforming the triangles to equilateral triangles? Just throwing out a few ideas and wanted to discuss what potential flaws…
activatedgeek on HN
Alternatives named
pHash
From 2 comments
This is pretty neat. I've been using pHash to find duplicate photos across my personal library, but this seems significantly better. I'd like to wrap it as a Python library -…
rcarmo on HNThat is really gorgeous, do you have anything quick written up about how your hashes are stored? I spent far too much of a few months optimizing phash to hell (I can do fuzzy…
deevnull on HN
ASIFT (Affine SIFT)
From 2 comments
Hey Tom, Great work there! One question - Why are we transforming the triangles to equilateral triangles? Just throwing out a few ideas and wanted to discuss what potential flaws…
activatedgeek on HNASIFT or Affine SIFT is one of the Affine invariant versions of SIFT. Take a look here - http://www.cmap.polytechnique.fr/~yu/research/ASIFT/demo.html.
activatedgeek on HN
Google reverse image search
From 1 comment
Hey guys, I'm the guy who made this. Let me know if anything isn't clear or if you have any questions. *I developed this after I saw how poor google (and any other reverse image…
pippy360 on HN