Iris image segmentation algorithm based on nonlinear dimension space

Abstract

The invention particularly discloses an iris image segmentation algorithm based on a nonlinear dimension space. The iris image segmentation algorithm based on the nonlinear dimension space comprises the following steps: inner boundary of an iris is positioned: a dimension evolution characteristic of the nonlinear dimension space is utilized to conduct smooth processing on an original iris image, a hot spot of a pupil area is eliminated, gray level of the pupil area is ensured to be in a floor level of the whole image, pupil detection is achieved through threshold, and positioning of the inner boundary of the iris is achieved; outer boundary of the iris is positioned: the dimension evolution characteristic of the nonlinear dimension space is utilized to conduct smooth processing on the original iris image, sheltering of eyelashes small in geometry dimension on the iris area is eliminated, and accurate positioning of the outer boundary of the iris is achieved. In the process of positioning the outer boundary of the iris, similarly, the dimension evolution characteristic of the nonlinear dimension space is utilized to conduct smooth processing on the original iris image, sheltering of eyelashes small in geometry dimension on the iris area is eliminated, and accurate positioning of the outer boundary of the iris is achieved.

Description

technical field [0001] The invention relates to an iris image segmentation algorithm based on nonlinear scale space. Background technique [0002] Biometrics uses computers to identify individuals using their own physiological or behavioral characteristics. These physical characteristics include physiological characteristics of the human body such as fingerprints, irises, palmprints, hand shapes, faces, voices, retinas, and DNA, as well as behavioral characteristics such as signature movements, walking gait, and keyboard strength. These physiological or behavioral characteristics can be a reliable basis for identification because people are different, they are almost carried around, and they are quite stable. At present, with these unique advantages, biometric recognition algorithms have been widely used in information security, financial transactions, social security, personnel management, medical and health and other fields. [0003] Compared with other biological charac...

AI Technical Summary

Problems solved by technology

E.g, used k-means fuzzy clustering to realize the feature classification of iris image grayscale; Pundlik et al. used graph cut to realize iris segmentation, but the graph cut method relies on the statistical relationship between pixels, ignores the boundary information, and the iterative process is long; He proposed a hybrid segmentation method, that is, firstly use the linear interpolation algorithm to eliminate the reflection, and then use the chord length equalization method to search for the pupil center; Jarjes et al. use the snake model and the angle integral projection method to realize iris segmentation; Roy realizes the iris boundary by the level set method extraction of

However, since both Snake and level set methods rely on the curve evolution model controlled by partial differential equations, such iris segmentation methods converge slowly and are very sensitive to the initialization position of the curve

Images