Strabismic Pupil Boundary Positioning via Segmented Arc Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current pupil boundary positioning methods in iris recognition are inaccurate for strabismic pupils, as they assume a circular boundary shape, leading to deformation issues and noise interference from eyelashes and light spots.
Innovation Solution
A method that initially positions the pupil boundary as a circle, divides the iris image into multiple sub-images based on central angles, and traverses search ranges to find maximum gray scale changes for circle center and radius, splicing circular arc segments to accurately define the pupil boundary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the pupil boundary is positioned as a circle shape using gradient processing and curve fitting, then the positioning process is simple and fast, but the positioning accuracy is poor for strabismic pupils because the boundary is not circular
Solution Approach 1:
The patent divides the pupil boundary positioning into multiple angle intervals (e.g., 0-90 degrees, 90-180 degrees, etc.), processing each segment separately. For each interval, it performs gradient processing and curve fitting to obtain local circle parameters, then combines these segments to form the complete pupil boundary. This segmentation allows accurate fitting of non-circular strabismic pupils while maintaining computational efficiency.
2Adaptability or versatility
If point-to-point alignment is performed directly based on the pupil boundary without circular assumption, then the circular shape limitation is removed, but noise from eyelashes and light spots causes boundary point omission and reduces accuracy
Solution Approach 1:
The patent applies different processing strategies to different regions of the pupil boundary. Within each angle interval, it performs gradient processing to enhance edge information and uses curve fitting to obtain smooth circular arc representations. This local processing approach reduces the impact of noise from eyelashes and light spots in specific regions while maintaining overall boundary accuracy.
3Adaptability or versatility
If the pupil boundary is processed as a group of point arrays without circular fitting, then circular limitation is removed, but subsequent unfolding and normalization processes are affected by boundary point omission
Solution Approach 1:
The patent performs preliminary circular arc fitting within each angle interval before proceeding to subsequent processing steps. By obtaining smooth circular arc representations of the pupil boundary segments first, it ensures that the boundary is well-defined and free from noise-induced omissions before unfolding and normalization operations. This preliminary action prevents error propagation to subsequent processing stages.
Data Source
AI summary
The present disclosure discloses a strabismic pupil positioning method, apparatus, a readable storage medium and a device, and belongs to the field of iris recognition. The strabismic pupil positioning method includes: performing initial positioning on a pupil boundary to be positioned as a circle on an iris image; with an initial positioning result as a reference, dividing the iris image into multiple sub-images based on a certain central angle; for each sub-image, traversing a circle center search range and a radius search range, and using a circle center value and a radius value, which correspond to a maximum gray scale change as the circle center and the radius of the sub-image; and obtaining a circular arc segment of each sub-image based on the circle center, the radius and the central angle of each sub-image, and splicing the circular arc segments of all sub-images together to obtain the pupil boundary.