Adaboost face detection method based on new Haar- like feature

Abstract

The invention discloses an Adaboost face detection method based on a new Haar- like feature. The Adaboost face detection method based on a new Haar- like feature includes the following steps: (1), training phase: utilizing a camera to collect face feature and non-face feature image samples, extracting the face feature set and non-face feature set to conduct training, constructing rectangle features which can distinguish face samples and non-face samples and a corresponding weak classifier, obtaining a strong classifier of face and non-face through training, repeating the training process from the second step to the third step, and obtaining a complete face detector, (2), detection phase: scanning the image and extracting all the detected child windows, and obtaining sub-image set to be detected, calculating the integration figure value of all rectangles of all sub-images, conducting detection with the classifier through training, merging all the detection results, outputting the detected face position. The weak classifier of the Adaboost face detection method based on the new Haar- like feature is more specific and more accurate and can effectively improve the detection efficiency of the face.

Description

technical field [0001] The invention relates to the technical field of image pattern recognition, in particular to an Adaboost face detection method based on new Haar-like features. Background technique [0002] In recent years, face detection has become one of the very active research topics in the field of computer vision. The Adaboost face detection algorithm based on Haar-like features has the advantages of fast detection speed, strong real-time performance, and good robustness, thus solving the trade-off between detection speed and detection rate to a certain extent. In 2001, Viola and Jones designed the first real-time face detection system. The system's fast detection speed and high accuracy immediately attracted the attention of many scholars. The literature mentioned three contributions they made. First, a set of Haar-like features was proposed for feature extraction of faces; second, an "integral map" was proposed to speed up the calculation of eigenvalues; Third...

AI Technical Summary

Problems solved by technology

Compared with the representative edge orientation histograms (EOH) proposed by K.Levi et al., since the extracted face features are more representative, the number of faces in the face training library required by its features is greatly reduced. In other words, only a few hundred face training sets are needed to achieve the corresponding detection rate with the Haar-like feature proposed by Viola et al., but the feature calculation is relatively complicated

Images