Model generation method, iris image quality evaluation method and electronic device

Abstract

The invention discloses a model generation method, an iris image quality evaluation method and electronic equipment. The iris quality evaluation method comprises: obtaining an iris image to be evaluated; by the iris image quality evaluation model, judging whether the quality classification belongs to a preset minimum quality classification, or whether it is lower than the minimum quality classification; if so, the quality of the iris image to be evaluated If not, calculate the first quality score; calculate the quality scores of all images in the current storage of the iris image to be evaluated; judge whether the iris image to be evaluated is qualified according to the first quality score, the quality score and a preset quality threshold . At the beginning of obtaining the training sample set, the model classifies the image texture and quality, and combines the quality score S as a quality reference. When using this model to evaluate the quality of iris images, according to the texture classification, combined with the preliminary judgment of quality classification, it only needs to judge within a small threshold range, which improves the efficiency of iris image quality evaluation.

Description

technical field [0001] The invention relates to the technical field of biological feature identification, in particular to a method for generating an iris image quality evaluation model, an iris image quality evaluation method, a computer-readable storage medium, and an electronic device. Background technique [0002] With the advancement and development of science and technology, the original identity authentication methods such as swiping cards and account passwords can no longer meet the needs of the current society. Biometric recognition, such as face recognition and iris recognition, has become the mainstream method of identity authentication due to its high precision and difficult to copy advantages. Face recognition has lower restrictions on user posture and use distance, but the face will change over time, and the recognition accuracy is low. [0003] Iris recognition technology has developed rapidly. Iris recognition has the advantages of high precision, iris textu...

AI Technical Summary

Problems solved by technology

On the one hand, the quality of the collected iris images is uneven due to the differences in the irises of biological individuals, the instinctive blinking behavior of individuals, and the focusing problem in the process of using iris recognition equipment.

On the other hand, due to individual differences, there is a difference in texture density, which makes the content of the iris image to be evaluated vary greatly, which causes great interference to the quality evaluation without reference, making it difficult to set a standard for iris image quality evaluation. Iris quality in different individuals

Images