Method for recognizing face images

Abstract

The embodiment of the invention discloses a method for recognizing face images, which comprises the steps of: accurately positioning two-dimensional face images in a preset database; conducting three-dimensional reconstruction to the two-dimensional face images according to a preset three-dimensional face image model and the accurate positioning results of the two-dimensional face images to obtain three-dimensional face images; conducting illumination model treatment to the three-dimensional face images to obtain virtual images with changing postures and illumination; classifying the virtual images to obtain classification results and taking the classification results as preset classification results; and recognizing the two-dimensional face images to be recognized by using the preset classification results. The method increases the sample space of the posture and illumination change of images by the three-dimensional reconstruction and illumination model treatment of the two-dimensional face images to generate virtual images and accelerates the three-dimensional reconstruction to a great extent simultaneously, thus leading the recognition of face images to have higher efficiency and recognition rate.

Description

technical field

[0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a method for face image recognition. Background technique

[0002] The face recognition system takes face recognition technology as the core. It is an emerging biometric technology and a high-tech technology in the international scientific and technological field. Face recognition system has a wide range of applications due to its non-reproducibility, convenient collection, and no need for the cooperation of the person being photographed.

[0003] Although research on facial image recognition has continued for decades, it remains a challenging problem in the field of pattern recognition even today. There are still a series of difficult problems in the face recognition method. For example, when the face posture, expression and ambient lighting (PIE, Pose Illumination Expression) change greatly, the recognition rate will drop sharply. How to solve the probl...

Examples

Embodiment 1

[0021] The embodiment of the present invention provides a method for face image recognition. The method performs multi-subspace shape modeling on a two-dimensional face image in a database to obtain a two-dimensional face shape model; Local texture modeling to obtain a 2D face local texture model; according to the 2D face shape model and local texture model, accurately position the 2D face image; according to the preset 3D face shape model and the 2D face Accurate positioning results of face images, 3D reconstruction of 2D face images to obtain 3D face images; lighting model processing of 3D face images to obtain virtual images of posture and illumination changes, thus increasing the posture and illumination of the image The changing sample space can overcome the influence of pose and illumination changes in the image recognition process. The obtained virtual image is extracted and classified, and the classification result is used to recognize the face image, which improves th...

Embodiment 2

[0181] The present embodiment provides a face recognition method, the method obtains a two-dimensional face image to be recognized; extracts features from the two-dimensional face image; compresses the extracted features to obtain compressed features; The compressed features are classified to obtain a classification result; the classification result is matched with the preset classification result, and the face image to be recognized is recognized according to the matching result. Such as Figure 4 As shown, this embodiment includes:

[0182] 401: Obtain a two-dimensional face image to be recognized, and perform preprocessing.

[0183] Specifically, the preprocessing of the two-dimensional face image includes: correction of the plane rotation and normalization of the scale and gray level of the face area, usually using the eye part in the image as a reference point for normalization. The normalization method is the same as the method in Example 1, and will not be repeated he...

technical field

[0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a method for face image recognition. Background technique

[0002] The face recognition system takes face recognition technology as the core. It is an emerging biometric technology and a high-tech technology in the international scientific and technological field. Face recognition system has a wide range of applications due to its non-reproducibility, convenient collection, and no need for the cooperation of the person being photographed.

[0003] Although research on facial image recognition has continued for decades, it remains a challenging problem in the field of pattern recognition even today. There are still a series of difficult problems in the face recognition method. For example, when the face posture, expression and ambient lighting (PIE, Pose Illumination Expression) change greatly, the recognition rate will drop sharply. How to solve the probl...

Examples

Embodiment 1

[0021] The embodiment of the present invention provides a method for face image recognition. The method performs multi-subspace shape modeling on a two-dimensional face image in a database to obtain a two-dimensional face shape model; Local texture modeling to obtain a 2D face local texture model; according to the 2D face shape model and local texture model, accurately position the 2D face image; according to the preset 3D face shape model and the 2D face Accurate positioning results of face images, 3D reconstruction of 2D face images to obtain 3D face images; lighting model processing of 3D face images to obtain virtual images of posture and illumination changes, thus increasing the posture and illumination of the image The changing sample space can overcome the influence of pose and illumination changes in the image recognition process. The obtained virtual image is extracted and classified, and the classification result is used to recognize the face image, which improves th...

Embodiment 2

[0181] The present embodiment provides a face recognition method, the method obtains a two-dimensional face image to be recognized; extracts features from the two-dimensional face image; compresses the extracted features to obtain compressed features; The compressed features are classified to obtain a classification result; the classification result is matched with the preset classification result, and the face image to be recognized is recognized according to the matching result. Such as Figure 4 As shown, this embodiment includes:

[0182] 401: Obtain a two-dimensional face image to be recognized, and perform preprocessing.

[0183] Specifically, the preprocessing of the two-dimensional face image includes: correction of the plane rotation and normalization of the scale and gray level of the face area, usually using the eye part in the image as a reference point for normalization. The normalization method is the same as the method in Example 1, and will not be repeated he...

Images