This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
Yes.For example in the FACE ICAO field for skin color validity in the first you have to specific the skin region of face.If you do this with range of Hue,Saturation,Intensity or RGB the final result is not accurate because our method is linear but our problem is nonlinear.
To obtain an accurate result you can train a classifier with color features for example H-S-I-R-G-B .You can use MLP or SVM for classify it.
| | 2 | No.2 Revision |
Yes.For example in the FACE ICAO field for skin color validity in the first you have to specific the skin region of face.If you do this with by controlling the range of colors( Hue,Saturation,Intensity or RGB RGB) the final result is not accurate because our method is linear but our problem is nonlinear.
To obtain an accurate result you can train a classifier with color features for example H-S-I-R-G-B .You can use MLP or SVM for classify it.
| | 3 | No.3 Revision |
Yes.For example in the FACE ICAO field for skin color validity compute of light balance in the face in the first you have to specific the skin region of face.If you do this by controlling the range of colors( Hue,Saturation,Intensity or RGB) RGB)by rules the final result is not accurate because our method is linear but our problem is nonlinear.
To obtain an accurate result you can train a classifier with color features for example H-S-I-R-G-B .You can that be specified by the user(for select colors use the flood fill).In the final use the MLP or SVM for classify it.
