Multi-view-angle reconfigurable face data acquisition system

Abstract

The invention discloses a multi-view-angle reconfigurable face data acquisition system. The system comprises background cloth, a seat and a hemispherical bracket. The hemispherical bracket comprises six bracket layers formed and arranged according to weft and six support rod layers formed and arranged according to warp. A predetermined number of cameras are evenly mounted on each bracket layer. Each camera is connected to a computer through an interface. The system further comprises a plurality of light sources distributed at a plurality of positions centered on a ball of the bracket. The cameras and the light sources are all connected to the computer through a control sub system. The control sub system is used to control all of the cameras to synchronously snapshotting all-round face images and cyclic actions of the light sources. Illumination is diversified, the number of light sources can be adjusted and replaced independently, the background can be adjusted, and the all-round coverage of a face is achieved by position calibration.

Description

technical field [0001] The invention relates to the technical field of face data collection, in particular to a multi-view reconfigurable face data collection system. Background technique [0002] In recent years, biometric technology has played an important role in identity authentication, maintaining national security, personal information security, aviation security, relief supplies distribution and medical treatment, and its applications are becoming more and more extensive. Compared with fingerprint recognition, iris recognition, speech recognition and other biometric recognition technologies, face recognition has the advantages of naturalness and imperceptibility. It is widely used because of its high detection rate, high adaptability and convenient collection. [0003] Face recognition needs to use stable facial features, and the corresponding algorithms are based on methods such as LDA and PCA. With the continuous optimization and improvement of face recognition alg...

AI Technical Summary

Problems solved by technology

The complex multi-camera face acquisition system can be divided into non-movable and mobile. The non-movable system is difficult to disassemble and poor in portability, and cannot realize remote collection; although the mobile system is highly portable, it has a single function, versatility and scalability poor sex

In addition, none of them can fully cover the perspective of the face, and the face data is not rich enough.

Images