This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
Haar Classifier is a simple approach you can use for this task.
| | 2 | No.2 Revision |
Haar Classifier is a simple approach you can use for this task. recognizing the facial parts.
As for "getting the coordinates", what do you mean by "coordinates"? Image coordinates or 3D real world coordinates? You need to calibrate your camera if you want to get the real world coordinates. Also, if you mean 3D coordinates this is not possible with monocular setup. If you mean, however, simply the image coordinates, then after getting the bounding box (resulting from Haar), simply use the width and height information of the rectangle to get its center coordinates.
| | 3 | No.3 Revision |
Haar Classifier is a simple approach you can use for recognizing the facial parts.
As for "getting the coordinates", what do you mean by "coordinates"? Image coordinates or 3D real world coordinates? You need to calibrate your camera if you want to get the real world coordinates. Also, if you mean 3D coordinates this in that case it is not possible with a monocular setup. You need to employ another camera and use stereo-vision techniques to achieve that.
If you mean, however, simply the image coordinates, then after getting the bounding box (resulting from Haar), simply use the width and height information of the rectangle to get its center coordinates.
