yantrams

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

Good one. Frameworthy this! Thank you.

Improved results using icons with higher resolution, for those who are following this conversation and waiting with bated breath :)

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

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

:) Please feel free to share the SVGs. I will convert them to PNGs and test them out. I will add SVG support real soon. Right now I've put an exception handler that passes an empty array as query if an image format that can't be decoded is thrown at it :|

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 suspect it has to do with the lower resolution. I'm using nearest neighbors interpolation for resizing images and have noticed similar behaviour before. Would be great if you can try with higher resolution versions(preferably > 200px) of the same images and let me know the results.

A closer inspection of the results actually shows some of the results aren't that bad a match. Results ordered 1, 4, 5, 7 and 7 in particular vaguely have the same outline as that of the query image. If I have to score this result, I wouldn't give it more than a 3 out of 10 for sure.

Glad you liked it and wow are you sure you are not confusing me with someone else ? :) I have a suspicion you are mistaking with Anil Battula from http://sovietbooksintelugu.blogspot.com/ maybe.

Speaking of Telugu, I recently got hold of a treasure trove(about 700GB) of scanned copies of Telugu magazines and newspapers some of them as old as 1880! Gonna upload them on archive.org very soon.

If you are referring to entering those words in the searchbox, yes I should've put in some warnings/checks there to enter a valid image URL. Will fix it soon. And yes I should make the site secure too. Thanks for letting me know.

PS: You can explore company logos here http://compute.vision/brands/index.html . It's implemented using an older iteration of the algorithm and performance isn't that great compared to the one used with the icons database.

Been meaning to do a blog post on this forever now :/ I will do it at some point for sure at http://linkdot.link

This is a great starting point in case you are interested in knowing more -- http://www.staff.science.uu.nl/~kreve101/asci/smi2001.pdf More recently, I've been exploring some ideas of Tversky.

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

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

Author here. Happy to answer any questions, hear feedback.

Just checked your personal website. So glad to have stumbled upon it. Been a while since I've some come across something so refreshing. Thank you!

You're welcome and I'm glad you loved it.

Cheers!

Thanks a ton for letting me know about it and sharing the fix as well. Fixed it now. Will spend sometime soon and sort the other Firefox issues that I discovered as well.

Cheers!

Here are some relatively lesser known blogs that I can recommend, apart from the usual suspects (worrydream, John Baez etc.)

https://jeremykun.com

http://colah.github.io

https://mathwithbaddrawings.com

https://www.allendowney.com/blog/

And yeah I finally decided to inject some character into my personal website and spent a couple of days wrangling with css and made this --- http://linkdot.link . Not much content really though and it is mostly probability puzzles that I solve every now and then.

Edit: Formatting

Quite impressed with the way this handled some edge cases I tried out. (Four word company name with the third word having 20 characters, twenty word string etc.) I'm sure a lot of thought went into algorithmizing how to best represent a string of unbroken text in a given space and make it look good at the same time.

Edit: Grammar

[Selfplug]

If you want to see how similar your logo is compared to stock icons from the noun project database or logos of the top million websites, you can try these services that I built as part of my research into shape similarity.

http://compute.vision/nouns/index.html

http://compute.vision/brands/index.html

These aren't the latest iterations of the algorithm but they fare pretty well most of the times.

Here are the results for the logo of Mybrandnewlogo:

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

http://compute.vision/brands/logo-results.html?uhash=HTH0LBU...

Edit: Formatting

Great job! Thank you. I'll see if I can add support to this for the last.fm scrobbler extension that I use.

PS: For those of you who use Apple music and are into Indie / Alternative music, here's a 2018 mixtape I made recently.

http://linkdot.link/2018-mixtape.html

Edit: Added playlist

Interesting. Came across this recently on David Lynch / Angelo Badalamenti's free-jazz record's album cover.

https://thoughtgang.bandcamp.com/

If I had to choose just one blog or a twitter account for that hypothetical deserted island question(what is the one x-item you'd choose if stranded on a deserted island?), it would be that of John Baez without a second thought. His personal blog and tweets are absolute treasure troves for anyone interested in Math.

https://johncarlosbaez.wordpress.com https://twitter.com/johncarlosbaez

The recent breakthrough in finding the smallest Lebesgue cover [1] was triggered by one of his blog posts about it a few years back.

1 -- https://www.quantamagazine.org/amateur-mathematician-finds-s...

Thank You! I'll explore it soon when I get some time.

Nice. A spiral with decreasing radius essentially. On a side note, I wonder what configuration/distribution of magnetic force will make a charged particle move like this.

On a somewhat unrelated and maybe tangential note, I felt the logo of Torrent Freak reminded me of Techcrunch quite a bit and ran it against the logo database I have and indeed found Techcrunch show up in the results.

http://compute.vision/brands/logo-results.html?hash=CD1POO56...

Edit: Updated Link

Great piece this. The Ex is a Dutch band I'd recommend to anyone who is into Fugazi. They have a similar philosophy towards music production with a more noise/post-punk aesthetic.

Sad to hear that. Didn't know about it.

Have just ordered the e-book. Didn't expect to find a chapter on Hyperbolic tessellations. Nice!

I am a huge fan of Jeremy's blog. Found his primers on a multitude of topics very useful - https://jeremykun.com/primers/

As a Math guy who got into the world of programming relatively recently, I am on the opposite side of the spectrum I suppose but I'm gonna order this nonetheless to support him.

Hey man where you heading ? :) I can never get enough of their song Lesbian Eskimo left-handed midget albino.

World of Mathematics - An amazing compendium of accessible content straight from the masters - Poincare, Jonathan Swift, Neumann, Bishop Berkeley, Cayley etc https://www.amazon.com/World-Mathematics-James-Newman-Hardco... I believe it is available on archive.org

What Is Mathematics? by Richard Courant and Herbert Robbins published in 1941. One of the most beginner friendly yet rigorous books out there for a survey of many areas in mathematics.

You can find hundreds of gems here from erstwhile Soviet Union - https://mirtitles.org/