Human face detection and tracking method based on Gaussian skin color model and feature analysis

Abstract

The invention relates to a human face detection and tracking method based on a Gaussian skin color model and feature analysis. The method comprises the following steps of: firstly, conducting statistics to a large quantity of human face image data and constructing a Gaussian skin color model in a YCbCr color space; then, shifting a video image sequence to the YCbCr space from an RGB (Red, Green and Blue) space, working out a skin color likelihood graph by using the Gaussian model, selecting adaptive threshold values to conduct skin color segmentation and using the geometric features and the structural features of human faces on the basis to realize accurate human face detection; and finally, adopting an improved CAMShift algorithm to track the human faces to realize the rapid detection ofthe human faces in a video. The human face detection and tracking method provided by the invention has obvious advantages in aspects of recognition accuracy, tracking speed and robustness, and can effectively solve the problem in the human face tracking under complex conditions such as the posture change and distance change of the human faces in the video, the likely skin color interference existing in a background and the like.

Description

technical field [0001] The invention relates to a face detection and tracking method in a video sequence, in particular to a detection method based on a Gaussian skin color model and feature analysis and an improved CAMShift tracking method. Background technique [0002] Face analysis technology, including face detection, face tracking, face recognition and expression analysis, is a major research topic in the field of computer vision and image processing in recent years. Face detection refers to the process of determining the position, size and posture of all faces (if present) in the input static or dynamic image; face tracking refers to the process of determining the movement track and size change of the face in the input image sequence Condition. As a key link in face analysis technology, face detection and tracking has broad development prospects and application value in intelligent human-computer interaction, security monitoring, video conferencing, medical diagnosis,...

AI Technical Summary

Problems solved by technology

[0005] The current face detection method based on the skin color model is easy to implement, but it is sensitive to changes in ambient brightness and is easily disturbed by background skin color objects, which reduces the accuracy of the detection results; the template-based method has a strong Robustness, but the template matching process has a large amount of computation and the detection speed is slow. In addition, when the face pose changes (such as head up or side face), the recognition accuracy will be greatly reduced; when dealing with video target detection problems, commonly used The CAMShift algorithm performs target tracking to improve processing speed, but due to the particularity of video face detection, there are higher requirements for the positioning accuracy of the search window of the tracking algorithm, and the traditional CAMShift algorithm is difficult to meet the requirements

Images