Non-rigid face detection and tracking positioning method

Abstract

The invention discloses a non-rigid face detection and tracking positioning method. The method comprises the following steps that: a camera shoots a photographic image or a video image; and face detection and tracking are carried out. According to the method of the invention, a shape information mechanism of an object is created through using a model similar to an active appearance model (AAM); an active shape model (ASM) adopts a parametric sampling shape to form an object shape model; a PCA method is adopted to construct a motion model of control points for describing a shape; and a group of parameters is utilized control the position change of the shape control points, so that the shape described by the shape control points can be approximate the shape of a current object. The method simply uses the shape of the object and the shape-based training model, so that the method can be implemented more easily.

Description

technical field

[0001] The present invention relates to the field of face tracking and face detection, in particular to a non-rigid face detection and tracking positioning method, specifically to the realization of face detection and tracking in real-time environment, in the field of face tracking and face detection A newer method is proposed, which has more advantages in the fields of accuracy and training time, and optimizes the application of face detection and tracking in computer vision and human-computer interaction. Background technique

[0002] Activeshapemodels (ASM: Active Shape Model) and activeappearancemodels (AAM: Active Appearance Model) are two of the most widely used local feature description models. In current computer vision applications, the algorithm for face tracking is very complicated, and detection is time-consuming and expensive. low accuracy issues. Moreover, embedded platforms such as home appliance systems are limited by storage space resources,...

Examples

Embodiment

[0028] Such as figure 1 As shown, a non-rigid face detection and tracking positioning method, the method steps are as follows;

[0029] A. The camera takes a picture or a video picture, and shoots the face through the camera and obtains the picture or video picture;

[0030] B. Face detection and tracking, through the detail improvement module to detect and track the face when shooting;

[0031] B1. Geometric constraints, decompose rigid bodies and non-rigid bodies for shooting pictures or video picture samples: perform regional selection of face regions for shooting pictures or video picture samples; then record rigid body rigid changes and regional changes in the face field through the shape_model program For non-rigid non-rigid changes, the recording process of the shape_model program is as follows:

[0032] b1 through the subspace matrix V representing the face shape and the variance vector e, the parameter vector stores the shape relative to the model;

[0033] The par...

technical field

[0001] The present invention relates to the field of face tracking and face detection, in particular to a non-rigid face detection and tracking positioning method, specifically to the realization of face detection and tracking in real-time environment, in the field of face tracking and face detection A newer method is proposed, which has more advantages in the fields of accuracy and training time, and optimizes the application of face detection and tracking in computer vision and human-computer interaction. Background technique

[0002] Activeshapemodels (ASM: Active Shape Model) and activeappearancemodels (AAM: Active Appearance Model) are two of the most widely used local feature description models. In current computer vision applications, the algorithm for face tracking is very complicated, and detection is time-consuming and expensive. low accuracy issues. Moreover, embedded platforms such as home appliance systems are limited by storage space resources,...

Examples

Embodiment

[0028] Such as figure 1 As shown, a non-rigid face detection and tracking positioning method, the method steps are as follows;

[0029] A. The camera takes a picture or a video picture, and shoots the face through the camera and obtains the picture or video picture;

[0030] B. Face detection and tracking, through the detail improvement module to detect and track the face when shooting;

[0031] B1. Geometric constraints, decompose rigid bodies and non-rigid bodies for shooting pictures or video picture samples: perform regional selection of face regions for shooting pictures or video picture samples; then record rigid body rigid changes and regional changes in the face field through the shape_model program For non-rigid non-rigid changes, the recording process of the shape_model program is as follows:

[0032] b1 through the subspace matrix V representing the face shape and the variance vector e, the parameter vector stores the shape relative to the model;

[0033] The par...

Images