This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
I think detecting the box would be much simple (for both cases: empty/with-baby). Once you are able to detect the box, you can use HaarTraining's sample cascade classifier of faces, to the detection Rect of the box. Additionally you can specify max size limit to the face detection to make it more accurate (for dolls/baby's face).
| | 2 | No.2 Revision |
I think detecting the box would be much simple (for both cases: empty/with-baby). Once you are able to detect the box, you can use apply HaarTraining's sample cascade classifier of faces, to the detection Rect of the box. Additionally you can specify max size limit to the face detection to make it more accurate (for dolls/baby's face).
