Face detection method

Abstract

The invention relates to the field of biological characteristic identification, in particular to a face detection method. The method comprises the following steps of reading an original face image, conducting face irradiation preprocessing on the original face image, detecting a candidate face area by adopting AdaBoost, computing a similarity figure, and confirming a face area image. The method ensures the detection speed, greatly reduces a false detection rate of a target area, and increases an accuracy rate of face detection.

Description

technical field [0001] The invention relates to the field of biological feature identification, in particular to a face detection method. Background technique [0002] There are different face detection methods, which can be roughly divided into: methods based on skin color features and face verification, methods based on heuristic models, and methods based on statistical models. Since the face is non-rigid and has a high degree of freedom of change, It is difficult to explicitly describe the facial features. For this reason, methods based on statistical models have received more attention, such as artificial neural networks, AdaBoost, feature space methods, and methods based on probability models. Applying one method alone often cannot obtain accurate detection results, and more and more researchers pay more and more attention to improving the accuracy of target detection by combining multiple feature information and methods. [0003] The face detection system implemented ...

AI Technical Summary

Problems solved by technology

However, skin color information is easily affected by changes in illumination, which leads to a serious decline in the accuracy of face detection.

Images