Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revisionBoth sides next revision
lirec:faceident [2009-04-15 10:06] davegriffithslirec:faceident [2009-04-15 16:26] davegriffiths
Line 21: Line 21:
 You can also drive the program via yarp with the following input messages: You can also drive the program via yarp with the following input messages:
  
-^ Input port ^ Bottle contents ^ Meaning+^ Input port ^ Bottle contents ^ Meaning ^
 | /faceident-ctrl | "train" ID | Train for this user | | /faceident-ctrl | "train" ID | Train for this user |
-| /faceident-ctrl | "detect" | Switch out of training mode |+| /faceident-ctrl | "detect" | Switch to detection mode |
 | /faceident-ctrl | "save" sessionname | Save the detected faces  | | /faceident-ctrl | "save" sessionname | Save the detected faces  |
 | /faceident-ctrl | "load" sessionname | Load previously detected faces  | | /faceident-ctrl | "load" sessionname | Load previously detected faces  |
 | /faceident-ctrl | "clear" | Clears all faces | | /faceident-ctrl | "clear" | Clears all faces |
 +| /faceident-ctrl | "idle" | Switch to idle mode, mostly frees up cpu |
  
 Faces are saved in png format along with a text file to map them to id numbers. The sessionname  Faces are saved in png format along with a text file to map them to id numbers. The sessionname 
Line 51: Line 52:
 Todo: Todo:
   * Try normalised cross correlation instead of image differencing   * Try normalised cross correlation instead of image differencing
 +  * Expose image size and error threshold via yarp
 +  * Use tinyxml or something better for the serialisation
  
 Source code: [[http://svn.lirec.eu/foam/trunk/simple-faceident/]] Source code: [[http://svn.lirec.eu/foam/trunk/simple-faceident/]]
  
  
  • lirec/faceident.txt
  • Last modified: 2009-05-27 10:50
  • by davegriffiths