Iris image processing method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses an iris image processing method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: uniformly extracting a target number of pixel lines from a target direction of a target iris expansion image; for each pixel line in the target number of pixel lines, performing first-order differential processing on every two pixels in the pixel line to generate a first-order gradient value corresponding to the two pixels, and obtaining a first-order gradient value group; for each pixel line in the target number of pixel lines, performing second-order differential processing on every two pixels in the pixel line to generate second-order gradient values corresponding to the two pixels, and obtaining a second-order gradient value group; and on the basis of the obtained first-order gradient value group and the obtained second-order gradient value group, generating an iris score value corresponding to the target iris expansion image. According to the embodiment, the texture change of the iris region can be synthesized, and the definition of the iris region can be accurately detected. Therefore, the subsequent iris image recognition rate is improved.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and specifically relate to an iris image processing method, device, electronic equipment, and computer-readable medium. Background technique [0002] Biometrics uses various physiological and morphological characteristics inherent in the human body as the identification medium, so as to achieve unique identification of personal identity and personal identity authentication. Human iris texture has the characteristics of lifelong invariance and individual differences. Compared with other biological features, such as fingerprints, faces, palm prints, voice, etc., it can have a higher accurate recognition rate. At present, the manner of detecting the sharpness of the collected iris image usually includes: using a NIMA model (Neural Image Assessment, neural image assessment) to detect the sharpness of the iris image, so as to facilitate subsequent iris recognition. [00...

AI Technical Summary

Problems solved by technology

[0004] First, it is difficult to accurately detect the definition of the iris area without taking into account the texture changes of the iris area (eg, spots, filaments, crowns, striations, crypts, etc.);

[0005] Second, when the iris image is collected, the focus may be on the eyebrows, eyelashes and other parts. The depth of field of the eyebrows, eyelashes and other parts is different from that of the iris area, resulting in errors in the clarity of the detected iris image, which will cause distortion of the iris image. misunderstanding or refusal

Images