Identity verification method and device based on sclera recognition, equipment and medium

Abstract

The invention discloses an identity authentication method and device based on sclera recognition, equipment and a medium. The method comprises the following steps: acquiring a sclera region image in an original eye image of a to-be-identified object; enhancing and extracting the vascular structure in the sclera region image; and obtaining image information of the blood vessel structure in the sclera area image, performing feature extraction on the image information of the blood vessel structure based on the neural network model to obtain feature information of the blood vessel structure, performing classification identification on the feature information of the sclera blood vessel, and performing identity verification according to a classification identification result; or comparing the image information of the blood vessel structure with preset sclera blood vessel sample information, and performing identity verification according to the matching degree of the image information and thesclera blood vessel sample information. According to the method, overall contour features and detail texture differences are reserved in feature extraction, so that good identifiability is still keptwhen blood vessel features change, and meanwhile, the sclera blood vessel features can be better extracted through a neural network during classification and recognition.

Description

technical field [0001] The invention relates to the field of identity verification, in particular to an identity verification method, device, equipment and medium based on sclera recognition. Background technique [0002] The identification method based on eye features has the advantages of high accuracy, high reliability, difficult to forge, non-contact and so on. Among them, the sclera is affected by genes due to its rich and complex vascular structure on the surface, which has significant differences among different individuals and does not change over time. At the same time, its acquisition only requires ordinary lighting and reduces application requirements. It is an ideal biometric technology. At present, the research on the sclera as a biometric method is far from enough. Factors such as image acquisition illumination and angle, eyelashes and eyelids and other non-target area feature interference seriously affect the recognition accuracy. [0003] A typical sclera r...

AI Technical Summary

Problems solved by technology

With the development of deep learning, there are also neural network-based blood vessel extraction methods, but this method is extremely dependent on high-quality labeled datasets, and it is difficult to obtain high-standard datasets and the network generalization is not high. Applicable to practical scenarios

Images