TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Unsure which image extraction techniques to utilise

1 pointsby zemanelabout 6 years ago
For a side project i’m taking a look at how to extract information from Apex Legends (for starters) game play videos. Example screenshot:<p>https:&#x2F;&#x2F;www.gameprime.org&#x2F;wp-content&#x2F;uploads&#x2F;2019&#x2F;02&#x2F;gp-apexlegends-6.jpg<p>There is a log on top right corner and player status on bottom left corner (health&#x2F;shields).<p>Id like to:<p>- extract &lt;player A username&gt; killed &lt;player B username&gt; with &lt;weapon name&gt; (at time mm:ss) from log, and other information displayed on that log<p>- from player health extract health&#x2F;shields percentage (at what time)<p>Also detect game start&#x2F;end screens and possibly extract info from them like which characters compose the current player squads.<p>Apart from OCR, what kind or specific techniques should i learn to implement this ?

1 comment

PaulHouleabout 6 years ago
If the text is in a predictable position on the screen, this should be easy.<p>An image processing pipeline like this usually has a filter up front that drops out the environment and leaves a monochrome image of just the text and associated graphics. The text is white and is usually on a background that provides a lot of contrast since it designed to be readable by you!
评论 #19477384 未加载