Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse
Code Project
  1. Home
  2. General Programming
  3. C#
  4. Template Matching

Template Matching

Scheduled Pinned Locked Moved C#
graphicsperformancequestion
2 Posts 2 Posters 0 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • S Offline
    S Offline
    Seraphin
    wrote on last edited by
    #1

    Currently, I am working on an OCR solution where a camera push video frames into the application. One task is template matching where I try to find a bitmap within a bitmap. 1)Is template matching worth the work related to performance (Resolution 1024x768 - 24 Bit)? 2)Are there any information or resources for this subject on the web? Google show only rare information about it. thx

    C 1 Reply Last reply
    0
    • S Seraphin

      Currently, I am working on an OCR solution where a camera push video frames into the application. One task is template matching where I try to find a bitmap within a bitmap. 1)Is template matching worth the work related to performance (Resolution 1024x768 - 24 Bit)? 2)Are there any information or resources for this subject on the web? Google show only rare information about it. thx

      C Offline
      C Offline
      Curtis Schlak
      wrote on last edited by
      #2

      If you are looking for similar bitmaps contained in other bitmaps, then I suggest you start by looing at the Hausdorff distance. This can get computationally intensive. If you feel comfortable with complex analysis, though, you might want to look into Jacek Turski's Geometric Fourier Analysis of the Conformal Camera for Active Vision. You can compute the convolution of the Fourier transforms of the complex transformation that he describes to evaluate similarities. His system models a foveated camera, though; if you don't need that, maybe just vanilla Fourier transforms and convolution computation would work. "we must lose precision to make significant statements about complex systems." -deKorvin on uncertainty

      1 Reply Last reply
      0
      Reply
      • Reply as topic
      Log in to reply
      • Oldest to Newest
      • Newest to Oldest
      • Most Votes


      • Login

      • Don't have an account? Register

      • Login or register to search.
      • First post
        Last post
      0
      • Categories
      • Recent
      • Tags
      • Popular
      • World
      • Users
      • Groups