Double Classification Face Detection Algorithm Based On Successive Mean Quantization Transform
Abstract
Face detection refers to the determination of whether there are faces in the target image. If so, the location and number of faces should be determined. In the face detection process, there may be adverse effects such as different postures, changeable expressions, uneven shopping, obstructions and so on, which will reduce the accuracy of face detection. Therefore, this paper proposes a double classification face detection algorithm based on Successive Mean Quantization Transform (SMQT), which uses SMQT to extract face features, and then uses SNOW classifier and SVM classifier to locate the face region twice, so as to accurately identify the face position. After the usage, the accuracy and robustness of detection is effectively improved; the false detection rate is reduced; the operation speed of the algorithm is improved, and the robustness and accuracy of the algorithm is greatly improved.