Skip to content

Simple program written in C++ with Qt UI to detect faces in school year group photos and automatically add a number for each faces detected.

License

Notifications You must be signed in to change notification settings

catree/QFaceDetectionAndLabelling

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Face Detection + Auto Labelling (Alpha version)

Face Detection on school year group photo and automatic labelling.

Demo

« Condorcet 1897 » by Pierre Petit — Travail personnel. Licensed under CC BY-SA 3.0 via Wikimedia Commons.

Usage

  • File > Open: Open a dialog to select the desired images
  • When an image is loaded, a double left click will delete (after a confirmation) the label located under the mouse cursor (known issue: it is sometimes buggy, retry multiple times).
  • When an image is loaded, a right click will add a label. A dialog will show and ask for the label number.
  • Use the "<" and ">" buttons to load the previous and next images.
  • File > Save to directory: Open a dialog to select the directory where will be saved the images. If a file with the same name already exists, it will be asked if we want to overwrite or not the file.

Development environment

  • Windows 7 64 bits
  • Visual Studio 2010
  • OpenCV 2.4.10
  • Qt 5.5.0
  • binarie(Alpha version) compiled in 32 bits release mode

Known issues

  • The deletion of a label by a left double click seems to be sometimes buggy and require to try many times

TODO

  • Add a setting dialog to allow the modification of some parameters (Cascade classifier learning file, size of the label box, etc.)
  • Try to find a way to use more classical fonts than those provided by OpenCV
  • Try to find a way to display a better image than the raw RGB888

About

Simple program written in C++ with Qt UI to detect faces in school year group photos and automatically add a number for each faces detected.

Resources

License

Stars

Watchers

Forks

Packages

No packages published