Show HN: Search icons visually

Well it did suggest 2 icons of presumably corporate scrum meetings...

Ah yes. This has to do with the thresholding 'bug' I discovered sometime ago. I will update the algorithm soon. Happens with color images in the preprocessing stage during the conversion of query image to a binary image, especially in images with flat/palette colours.

I eventually came up with a contrived set of heuristics to tackle this problem as you can see in the example below and managed to get more get accurate thresholding more than 90% of the times for pathological cases like these with the right set of weights. --- https://imgur.com/a/XMhdnjH

Traditional algorithms and image vectors. I used a conconction of existing region and contour based techniques and threw in some original ideas as well.

One way is to scale the images down and threshold to black and white. At smaller scale they should be identical or much closer.

Great idea. I'll definitely look into it. Thanks for the suggestion. Cheers

Thanks for the share! These icons are golden! I did something similar for logos that could be of interest to you - http://compute.vision/brands/colorpicker.html

I found the running horse to be an adoring touch. The author's site is also worth checking out: http://linkdot.link

https://en.wikipedia.org/wiki/Sallie_Gardner_at_a_Gallop

It was the other way for me, I linked it to the duckduckgo icon svg and the horse started. I thought it was a loading animation (and took more than a few seconds) so I threw it to another monitor and continued reading HN.

...30 minutes later the horse is still running and I'm like 'wtf? what does a horse have to do with the DDG logo?' close tab. read comments...

It turns out the app doesn't handle svg (it is actually in the to do list) and returned a 500, but the failure was never presented to the user.

I scraped it from their website and then asked for their permission by sharing this link with them. They appreciated that I linked all the icons to their website and gave their consent to make this public.

The MPEG-7 dataset[0] is what most researchers use to benchmark shape similarity algorithms. There are couple of other datasets that I used that I can't recollect now. These datasets are relatively simple with a single shape as opposed to logos, icons that comprise multiple elements in different configurations.

I would test on the MPEG-7 dataset to begin with and once the precision and recall values are good enough go ahead with testing on logos and icons. I must've manually tested the algorithm more than a 100,000 times probably because that was the only way to do with untagged datasets. Quite tedious indeed. This version gives out pretty decent results about 7-8 out of 10 times I'd say.

[0] - http://www.dabi.temple.edu/~shape/MPEG7/dataset.html

I just realised the "download" icons aren't meant to be "similar icons"... they allow you to download the one above. Doh!

I've re-tried the "remove user" one but uploaded an SVG instead of a PNG (so technically the resolution is unlimited). Uploaded it both circled and not circled.

Here are the results: https://imgur.com/a/OT8Spjt

Also tried this "in-out" icon. I can kinda see how the algorithm got the results. Happy to send you a bunch of SVGs if want for testing BTW.

https://imgur.com/a/hDdDHED

Thanks a ton for testing it quite exhaustively! Would really appreciate it if you can share the second image.

I spent a lot of time working on a hack for 'normalizing' white on black and black on white backgrounds and also between choosing adaptive vs gaussian thresholds dynamically during preprocessing.

Here is an example with white on black and black on white variations of Nike logo that works as intended.

http://compute.vision/nouns/index.html?barnacles=https://s3....

http://compute.vision/nouns/index.html?barnacles=https://s3....

Edit: Grammar