Palm print acquisition equipment, palm print acquisition method and palm print image acquisition device

Abstract

The invention discloses palm print acquisition equipment, a palm print acquisition method and an image acquisition device. The equipment comprises an image acquisition device and an image processing device, wherein the image acquisition device comprises a lens group, a light splitting module, a common camera and a depth camera, after light captured by the lens group is split by the light splittingmodule, one part is acquired by the common camera to obtain a two-dimensional RGB image, and the other part is simultaneously acquired by the depth camera to obtain a depth map of a palm; the image processing device uses the two-dimensional RGB image and the depth map to calculate a 3D point cloud describing the spatial attitude of the palm, wherein the spatial attitude comprises two-dimensionalcoordinates of RGB image pixels and third-dimensional coordinates of the RGB image pixels determined by the depth map; the spatial attitude of the 3D point cloud is corrected to a preset positive direction through spatial transformation, and third-dimensional direction information of the corrected 3D point cloud is removed to obtain a corrected two-dimensional palm image; and palm print ROI extraction is extracted on the corrected two-dimensional palm image. According to the invention, the stability of palm print ROI extraction can be significantly improved.

Description

technical field [0001] The invention relates to the field of biological feature identification, in particular to a palmprint collection device, a palmprint collection device method and an image collection device thereof. Background technique [0002] Palmprint recognition is an important technology in biometric recognition. The general process of palmprint recognition is: image acquisition, image preprocessing, palmprint ROI extraction, feature extraction, and feature matching recognition. Wherein, palmprint region of interest (ROI, Region of Interest) extraction refers to defining an area on the palm, usually a rectangular area, for feature extraction in the next step. Therefore, the stability of ROI extraction directly affects the stability of features, thereby affecting the performance of the entire palmprint recognition algorithm. [0003] Existing palmprint recognition technology solutions can be divided into contact palmprint recognition and non-contact palmprint rec...

AI Technical Summary

Problems solved by technology

[0006] The disadvantage of contact palmprint recognition is that the palm must be fixed on the device, which limits the freedom of use, and the direct contact between the palm and the device will cause hygiene problems, especially when multiple people share a device

In addition, during actual use, changes in illumination or wrong placement of the palm can easily cause changes in the extracted ROI.

[0007] The disadvantage of non-contact palmprint recognition is that the posture changes of fingers and palms can easily lead to the instability of the extracted ROI.

Images