Iris Boundary Fitting for Fast Occlusion Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing iris recognition systems face challenges in accurately determining iris occlusion due to varying eye sizes and interference from eyelid shadows and eyelashes, leading to low semantic segmentation accuracy and speed.
Innovation Solution
Perform key point prediction on eye images to identify iris and eyelid boundary key points, apply contour fitting based on iris shape conditions, and analyze the relative positional relationship between the predicted iris area and eyelid boundary to determine iris occlusion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If semantic segmentation is performed on eyelids and iris to determine iris occlusion, then iris occlusion can be determined, but semantic segmentation accuracy is low and processing speed is low due to interference from eyelid shadows and eyelashes
Solution Approach 1:
The patent extracts key boundary points from the eye image and uses them to define geometric regions (iris area and eyelid area) rather than relying on complete semantic segmentation. By extracting only the essential boundary information and constructing simplified geometric models, the system achieves accurate occlusion determination without the computational burden of full semantic segmentation, thus improving processing speed while maintaining accuracy.
Solution Approach 2:
The patent creates a simplified geometric copy of the iris and eyelid structures using key boundary points and shape constraints, rather than working with the complex original semantic segmentation. This geometric model serves as a representation that can be processed more efficiently, allowing for accurate occlusion analysis at higher speed by operating on the simplified model rather than the complex semantic segmentation results.
2Measurement precision
If semantic segmentation is performed on eyelids and iris to determine iris occlusion, then iris occlusion can be determined, but semantic segmentation accuracy is low due to interference from eyelid shadows and eyelashes
Solution Approach 1:
The patent extracts only the essential boundary information (key boundary points) from the complex eye image and uses these extracted points to construct geometric models. This extraction approach simplifies the algorithm by focusing only on the critical boundary definitions needed for occlusion determination, eliminating the need for complex semantic segmentation while maintaining accuracy through the use of shape constraints and geometric relationships.
Solution Approach 2:
The patent segments the eye image into distinct geometric regions (iris area and eyelid area) based on key boundary points and predefined shape constraints. This segmentation approach divides the complex occlusion determination problem into simpler geometric calculations, reducing algorithm complexity while maintaining precision through the use of constrained geometric models that reflect actual anatomical structures.
Data Source
AI summary
In a method for iris occlusion analysis, key point prediction is performed on an eye image of a target object to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points. Contour fitting is performed on the plurality of iris boundary key points based on an iris contour shape condition to obtain a predicted iris area. An eyelid boundary formed by the plurality of eyelid boundary key points is determined. The iris occlusion analysis is performed on the target object based on a relative positional relationship between the predicted iris area and an area formed by the eyelid boundary to obtain an iris occlusion analysis result.