Multidirectional face detection method
A multidirectional face detection method is for detecting a face in a picture under detection at different positions. The face detection method includes the steps. A selecting window sets to sequentially select different sub-image patterns from the picture under detection. A facial feature weight calculates and it is calculated according to a feature value of the pixels in a sub-image pattern selected by the selecting window, thereby determining if the sub-image pattern has any features similar to the face. A facial edge weight calculates for made on the picture under detection according to a boundary value of the pixels in the sub-image pattern selected by the selecting window, so as to determine if the part of area of the picture under detection has any facial-boundaries. Profile detection is performed to respectively mark the facial-boundaries in the sub-image patterns with arc segments respectively for the sub-image patterns having the facial-boundaries.
1. A multidirectional face detection method for selecting a face in a picture under detection at different transposed positions, comprising:
setting a selecting window to sequentially select a different sub-image pattern from the picture under detection;
calculating a facial feature weight according to a feature value of each of pixels in the sub-image pattern selected by the selecting window, thereby determining if the sub-image pattern contains a face;
calculating a facial edge weight according to a color value of each of the pixels in the sub-image pattern selected by the selecting window to determine if the sub-image pattern selected by the selecting window has any facial boundaries; and
performing a profile detection to respectively mark the facial boundaries in the sub-image patterns with a plurality of arc segments respectively for the sub-image patterns having the facial boundaries, wherein some of the plurality of arc segments have a different major focus.
2. The multidirectional face detection method according to claim 1 , wherein the facial feature weight calculation comprises:
performing a training to determine a priority value of the feature value of each of the pixels in the selecting window.
3. The multidirectional face detection method according to claim 2 , wherein the training is a boosting algorithm.
4. The multidirectional face detection method according to claim 1 , wherein the selecting window has a size of an area of m*n pixels.
5. The multidirectional face detection method according to claim 1 , wherein a combined area of the arc segments constitutes an elliptic area.