Thank you for sharing my site! I built this a number of years ago as I was starting to learn about Japanese prints. I wanted a single place where I could find them across all of the various museums and universities that hold them. I use computer vision analysis to cluster prints together (using TinEye). A bunch more technical details from the last time this was posted: https://news.ycombinator.com/item?id=18344979
I’m working on a new site now that’s focused on prints that are for sale from dealers and auctions. Much more technically complex as it needs to be continuously updated. Hope to have a public beta soon!
Uh - woah! This is incredibly unexpected. I'm really glad people are interested in my database and in Japanese prints!
From a technical perspective there've been a lot of interesting open source projects that I've made to support this site:
https://johnresig.com/projects/ukiyoe/
I've also written a number of papers and given presentations on the work that I've done here (and elsewhere in the digital humanities).
https://johnresig.com/research/
I've since worked on a number of other projects like a database for a consortium of Art History Photo Archives: http://images.pharosartresearch.org/
And I'm building another one now on Japanese Picture Books (from the 19th century and older).
These are all my "spare time" fun hobby projects, my day job is still at Khan Academy as a Frontend Architect. I just enjoy getting to explore other types of applications and problem spaces!
Just to clarify: YUI and ExtJS both came out after jQuery, jQuery came out in 2006, and jQuery is actually more popular now than it was a year ago (or in 2010 - see the figures cited in the blog post).
Not exactly. It's linking to the old SAT practice material that's for the old (current) SAT exam. The new material, for the upcoming 2016 exam, which was just launched today, is available at:
After doing some more poking it appears as if Avisynth (and thus NNEDI3) is Windows-only. Do you happen to know if there are ways to run it in Linux or OSX? Or if there's a comparable set of software for those platforms?
NNEDI3 is fantastic - thank you for providing a link and some samples!
You're absolutely right that I shouldn't have said "normal". I update the post to clarify that this was using "OSX Preview". I did some hunting but didn't find any obvious pointers as to which algorithm they're using. If anyone knows offhand I'll be happy to include it!
Great point. FWIW, I've updated the post to include some of the cartouches, along with a cartouche at the "low noise reduction" level. The two lines in the fourth character appear to still be relatively distinct in this case.
Yeah, on second thought, after seeing the low noise reduction result again, I suspect that may be an even better result for what I'm looking to achieve. Many of the details in his rope are preserved and the calligraphy appears to be in better shape.
I have not - although that's an interesting idea, thank you! Relative to my other projects this is a very low-priority exploration. I was very interested to see if there could be a "cheap win" for this particular sub-problem that I will be dealing with, should I get around to digitizing these books.
One thing I should note is that when looking at prints (at least for when it comes to technical analysis) being able to see accurate representations of the lines is far more important than the uniformity of colored regions. Color is almost always at the whim of the printer on any given day, whereas the black lines (from the keyblock) should always remain the same. Granted you're going to have issues either way (using this tool or doing normal scaling) as the source material is inherently compromised.
Although it's not clear what scenes exactly the upscaler was trained up, I suspect that it's currently best suited towards scenes that have lots of large bold lines and not lots of tiny details.
Yeah - the background looking like crumpled-up wrapping paper is definitely not ideal. I suspect that it's having trouble with mostly-uniform areas of color that have slight variations. It appears to be extrapolating and creating these larger effects.
I completely agree. I tried to make a bunch of notes on the (poor) code quality, inline. This is mostly an attempt at archaeology, if you will. Naturally the current release (or even 1.0 release) of jQuery is substantially better code in every respect.
I don't have any links off-hand but I know that there was a Nintendo.com sub-site that was using a pre-1.0 version of jQuery. Even though the overall code quality is rather low it did have decent browser support - unless browsers actively begin breaking their APIs (unlikely) those old versions of jQuery will probably keep working forever!