[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vr / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / asp / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / qst / sci / soc / sp / tg / toy / trv / tv / vp / wsg / wsr / x] [Settings] [Search] [Home]
Settings Home
/wsr/ - Worksafe Requests

Thread archived.
You cannot reply anymore.

File: YuushaShisu.png (144 KB, 220x280)
144 KB
144 KB PNG
Do there exist any text hookers that can read and display text from a video stream? Like a YouTube video, video file, or just something that reads a portion of my PC screen and displays it as plain text? Everything I've found is for PC VNs that "works by intercepting program calls of system text functions" or something like that.
If you are talking about text embedded into the video stream, and not just subtitles, there's no realistic way to do that.
You're looking for a kind of https://en.wikipedia.org/wiki/Optical_character_recognition

In theory:
You can automate taking screenshots, pipe them into an OCR library and then dump the text wherever.

In practice:
How well OCR does will obviously depend on how easy it is to isolate the text from wherever it appears. Black text on white background is easy and already widely available. Rainbow-coloured flashing text crawls on top of buisy and blurry dashboard cam footage is probably still out of reach for consumer-grade systems. I also have no idea how computationally expensive such an OCR stack would be and what kinds of framerates you could feasibly achieve with it.

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.