Rapid accurate human face detection method

Abstract

The invention discloses a rapid accurate human face detection method. The rapid accurate human face detection method comprises steps that step 1: skin color segmentation thresholds are respectively set in CMYK color space, HSV color space, and YCbCr color space, and three thresholds are acquired for combination operation, and a threshold after the combination operation is used as the threshold for the skin color detection; step 2: the threshold after the combination operation is used for skin color segmentation pretreatment of an input image, and a human face detection candidate area is acquired; step 3: an MWR-AdaBoost algorithm is used for the human face detection of the candidate area, and the human face area is marked in the image. The combination operation of the skin color segmentation thresholds of the CMYK color space, the HSV color space, and the YCbCr color space is used for the pretreatment of the image to acquire the candidate area, and the problem of the skin color segmentation of easy missing of the human face candidate area in a complicated scene caused by using the single color space is solved; the MWR-AdaBoost algorithm is used for the human face detection of the candidate area, and the degradation phenomenon of the image after the skin color treatment caused by using the AdaBoost algorithm is inhibited. By using the method provided by the invention, the human face detection is completed rapidly and accurately.

Description

Technical field: [0001] The invention relates to a fast and accurate human face detection method, which belongs to the technical field of image pattern recognition. Background technique: [0002] Face is the most distinctive feature of a person. Even if two people are twins, their faces will still have subtle differences. Therefore, in today's era of intelligent information, faces provide a lot of valuable information. In recent years, more and more attention has been paid to the research on face recognition. Due to the natural advantages of face recognition and the characteristics of not being detected by the tested individual, it has been widely used in access control systems, camera surveillance systems, etc. [0003] Face detection is the key link of face recognition. The premise of face recognition is to accurately locate the area where the face is located in the background image. Since the human face is a kind of natural structural object with quite complex detail cha...

AI Technical Summary

Problems solved by technology

Since the human face is a kind of natural structural object with quite complex detail changes, the facial features "eyes, ears, nose, mouth, and eyebrows" of the human face affect the facial features, and the shape of the facial features will vary greatly depending on the emotion , Different faces have different contours and other factors also bring great challenges to face detection

The AdaBoost algorithm proposed by Paul Viola and Michael Jones is very representative in the field of face detection. However, due to its complex algorithm calculation and many redundant calculations, the detection speed is relatively low in complex scenes.

Although the subsequent skin color segmentation preprocessing method based on a single color space has improved the detection speed of the AdaBoost algorithm to a certain extent, it is easy to miss the face candidate area, and the AdaBoost algorithm has a certain degree of detection ability for the candidate area obtained by skin color segmentation. The degradation phenomenon, that is, the accuracy of detection decreases, and false detection is prone to occur

Images