Results 1 to 3 of 3

Thread: Art with Manga Pages and Math/Data Visualization

  1. #1
    overthink.exe
    kittyray's Avatar
    Joined
    Sep 2013
    Posts
    5,623
    Pronouns
    she/they
    Userbars
    117
    Thanks
    13,412
    Thanked
    18,704/5,242
    DL/UL
    40/0
    Mentioned
    1,155 times
    Time Online
    550d 23h 7m
    Avg. Time Online
    3h 26m

    Art with Manga Pages and Math/Data Visualization

    I stumbled across this the other day and I've been wanting to share it with people. This guy named Lev Manovich used one million (yes, million) pages from various Manga that had been scanned and translated online. It used pages from over 800 series, and over 1,000,000 unique pages. It used machine learning to analyze and categorize the images based on things like level of detail and amount of contrast, and charted them along two axes, with the most textural (high detail, high contrast) being in the top right.




    Here's a writeup on it:
    (you need an account to see links)
    In the Fall 2009, we have downloaded 883 Manga series containing 1,074,790 unique pages from this site. We then used our custom software system running on a supercomputer at National Department of Energy Research Center (NERSC) to analyze visual features of these pages (funded by Humanities High Performance Award from NEH Digital Humanities Office.) To match the scale of the data, we are using 287 megapixel The Highly Interactive Parallelized Display Space (HIPerSpace) with a a custom software for interactive exploration of large image sets developed between our lab (softwarestudies.com) and Gravity lab at Calit2.

    Visualization below shows our complete data set - 1 million Manga pages organized in 2D space according to their visual characteristics. The pages in the bottom part of the visualization are the most graphic (they have the least amount of detail). The pages in the upper right have lots of detail and texture. The pages with the highest contrast are on the right, while pages with the least contrast are on the left. In between these four extremes, we find every possible stylistic variation.



    and high-res images from the project (altho the final graph seems to not be online in full resolution due to sheer size), plus some other cool charts and graphs and shit!
    (you need an account to see links)



    The person behind it:
    (you need an account to see links)





    Posted some pictures here because I know it will get people reading, but out of respect for the sheer effort that went into this, I don't want to repost too many here and encourage you to take a look at those links, especially the flickr if you wanna see cool stuff but don't feel like reading!



    thanks stardust for base Thanks Sugarbee Thanks Wooloo
    Kyo (Nov 13 2020)

    thanks honeycomb
    and hearts! <3
    +Zenitsu

    THANK YOU FAB



  2. The Following 3 Users Say Thank You to kittyray For This Useful Post:

    Erik. (01-10-2022),TsUNaMy WaVe (01-08-2022),Zenitsu (01-07-2022)

  3. #2
    *hair toss*
    Flordibel's Avatar
    Joined
    Jun 2017
    Posts
    2,388
    Pronouns
    She/her/hers
    Userbars
    82
    Thanks
    2,905
    Thanked
    9,598/1,913
    DL/UL
    58/0
    Mentioned
    401 times
    Time Online
    82d 1h 11m
    Avg. Time Online
    47m
    Whoa, this is really cool!! That's such a massive effort? I love it!

  4. The Following User Says Thank You to Flordibel For This Useful Post:

    kittyray (01-08-2022)

  5. #3
    Hollow's Avatar
    Joined
    Feb 2016
    Posts
    2,268
    Userbars
    82
    Thanks
    3,451
    Thanked
    5,123/1,871
    DL/UL
    6/0
    Mentioned
    230 times
    Time Online
    70d 56m
    Avg. Time Online
    34m
    Whoa, I wonder what gave them this idea? That's an insane amount of manga pages!



    *that's rough buddy*





    (you need an account to see links)




    thank you Dita ;u; & thank you sugarbee *u* thank you Lyrichord for the ub *O* thank you Kibba for the dp eue





  6. The Following User Says Thank You to Hollow For This Useful Post:

    kittyray (01-08-2022)

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •