Face detection method based on Adaboost algorithm

Abstract

The invention relates to a face detection method based on an Adaboost algorithm, which comprises the steps of preprocessing a face image, performing skin color segmentation in an YCbCr color space, acquiring a face candidate region, further performing face detection according to the Adaboost algorithm, and matching a screened face region with a face template, wherein face image preprocessing comprises grayscale normalization, light compensation, filtering and noise reduction and geometric normalization; skin color segmentation comprises color space conversion, skin color segmentation performed by using a color scale model, and further face candidate region screening according to the area of a skin color connected region and the length-width ratio of an external rectangle; the Adaboost face detection algorithm comprises that weak classifiers are trained, the weak classifiers are combined into strong classifiers, and the strong classifiers are connected in series to form a cascade classifier; and face template matching comprises that the matching degree between the candidate face region acquired through processing and a face template is measured by using the weighted Euclidean distance. The face detection method improves the face detection speed and accuracy, and is easy to implement and operate, stable and reliable.

Description

technical field [0001] The invention relates to a face detection method based on an Adaboost algorithm, belonging to the technical field of face detection. Background technique [0002] With the development of mobile Internet and smart phone market, Android system, as the most popular mobile device operating system in the whole world, has a greater potential in the big stage of mobile Internet. However, there are few transplantation applications of face detection technology on mobile devices, and face detection based on mobile devices will have greater development. [0003] Although the current Adaboost face detection algorithm has a high detection speed, the training of the algorithm itself is time-consuming, which makes the entire face detection time relatively long. Therefore, it is necessary to optimize the traditional Adaboost algorithm. At the same time, currently existing smartphones based on the Android platform generally use a method based on the distance between ...

AI Technical Summary

Problems solved by technology

However, the limitation of the binocular positioning algorithm is that the eyes of the face image are requir

Images