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

Abstract

The invention discloses a model generation method, an iris image quality evaluation method and electronic equipment. The iris quality assessment method comprises the following steps: acquiring a to-be-assessed iris image; judging whether the quality classification belongs to a preset lowest quality classification or is lower than the lowest quality classification through an iris image quality evaluation model; if so, determining that the quality of the iris image to be evaluated is unqualified; if not, calculating a first mass fraction; calculating the quality scores of all images in the current storage of the iris image to be evaluated; and judging whether the iris image to be evaluated is qualified or not according to the first quality score, the quality score and a preset quality threshold. At the beginning of obtaining a training sample set, the model classifies image textures and quality, and combines a quality score S as a quality reference. When the model is used for carrying out quality evaluation on the iris image, preliminary judgment is carried out according to texture classification and quality classification, judgment only needs to be carried out within a small threshold range, and the iris image quality evaluation efficiency is improved.

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 image to be evaluated vary greatly, which causes great interference to the no-reference quality evaluation, making it difficult to set a standard to filter out different images when evaluating the quality of iris images. individual iris quality

Images