Iris Recognition Image Selection via Preliminary Quality Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Iris recognition in mobile devices is hindered by environmental conditions such as varying lighting, occlusions, and hardware limitations, leading to degraded image quality, recognition errors, and increased resource consumption.
Innovation Solution
A method and apparatus that perform multi-staged checks on acquired images based on quality criteria, discarding images with poor pupil radius, contrast, and eyelid opening distance, and selecting images suitable for iris recognition, thereby improving image quality and reducing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If iris recognition is performed on all acquired images, then recognition coverage is improved, but resource consumption and processing time increase
Solution Approach 1:
The patent applies preliminary quality assessment actions before iris recognition processing. Multiple quality criteria (illumination, occlusion, focus, contrast, image size) are evaluated in advance to filter out unsuitable images, ensuring that only high-quality images proceed to resource-intensive recognition processing, thus reducing overall power consumption while maintaining recognition accuracy
Solution Approach 2:
The patent changes the parameter of image quality thresholds by defining specific criteria ranges (illumination intensity ranges, occlusion percentage limits, focus quality thresholds, contrast minimums, and image size boundaries). These parameter changes enable systematic filtering of images based on quality metrics, optimizing the balance between recognition accuracy and resource utilization
2Reliability
If iris recognition is performed on all acquired images, then recognition coverage is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary quality assessment actions before iris recognition processing. Multiple quality criteria (illumination, occlusion, focus, contrast, image size) are evaluated in advance to filter out unsuitable images, ensuring that only high-quality images proceed to resource-intensive recognition processing, thus reducing overall processing time while maintaining recognition accuracy
Solution Approach 2:
The patent segments the image processing workflow into distinct stages: quality assessment stage (evaluating illumination, occlusion, focus, contrast, size) and recognition stage (processing only qualified images). This segmentation allows the system to quickly eliminate poor-quality images without performing full recognition processing, significantly reducing total processing time
3Reliability
If multi-staged quality checks are performed on images, then recognition accuracy is improved, but device complexity increases
Solution Approach 1:
The patent segments the quality assessment into five distinct evaluation modules: illumination assessment, occlusion detection, focus quality evaluation, contrast analysis, and image size verification. Each module independently evaluates one quality criterion and returns a pass/fail result, making the complex multi-criteria assessment manageable and implementable on mobile devices with limited processing power
Data Source
Figure 1~2
Figure 3~5
Figure 6
AI summary
An apparatus for recognizing an iris is provided. The apparatus includes an image acquisition module configured to acquire a plurality of images, and a processor configured to select at least one image for iris recognition from among the plurality of images based on pupil information of each of the plurality of images, and recognize an iris in at least one image, wherein the pupil information includes at least one of information about a pupil radius and information about a pupil contrast.