Iris Recognition Image Selector Using Mask-Based Pixel Thresholding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current iris recognition systems face challenges in selecting high-quality images due to variations in lighting and user experience, particularly in multi-ethnic populations, leading to issues with threshold value applicability and motion blurring, which affects recognition accuracy and reliability.
Innovation Solution
An iris recognition system that employs an image selector, internal and external edge extractors, iris area normalizer, feature value extractor, and consistency decider, using a mask to scan iris images and calculate pixel values within specific threshold ranges to identify optimal images and extract reliable iris features, regardless of user motion and ethnic variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional threshold-based image quality assessment is used, then processing speed is maintained, but recognition accuracy deteriorates due to motion blurring and lighting variations
Solution Approach 1:
The patent segments the iris image into multiple regions (pupil region, iris region, sclera region) and applies different assessment criteria to each region. The mask divides the image into a center region for pupil detection and peripheral regions for iris pattern analysis, allowing region-specific quality evaluation that accounts for local variations in lighting and motion effects
Solution Approach 2:
The patent implements local quality assessment by evaluating different regions of the iris image with region-specific thresholds and criteria. The mask-based approach allows the system to apply different weightings to different areas, focusing on the iris region while being less sensitive to variations in the sclera or pupil boundaries, thereby improving overall recognition accuracy
2Ease of operation
If automatic focus input image device is used, then ease of operation is improved, but image quality deteriorates due to insufficient contrast
Solution Approach 1:
The patent changes the assessment parameters from simple focus metrics to multi-parameter evaluation including contrast values, luminance variations, and edge detection results. By adjusting the mask regions and threshold values based on image characteristics, the system adapts to different lighting conditions and maintains high image quality without requiring manual focus adjustment
3Reliability
If mask-based pixel calculation is applied, then recognition accuracy is improved across ethnic groups, but device complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-defining mask patterns and threshold values for different ethnic groups and lighting conditions. The mask configurations are prepared in advance based on statistical analysis of iris images from diverse populations, allowing the system to quickly select appropriate parameters without real-time complex calculations
Solution Approach 2:
The system dynamically adjusts mask parameters such as region boundaries, threshold values, and weightings based on the specific image characteristics and detected ethnic group characteristics. This parameter adaptation allows the same basic mask structure to serve multiple purposes across different populations without requiring completely different processing algorithms
Data Source
AI summary
The present invention generally relates to an iris recognition system, a method thereof, and more specifically, to an iris recognition system comprising the image selector scanning each iris image in pixel unit by using a mask defined into a second area which is in square shape and a first area configured as the peripheral girth of the second area, calculating the number of pixels C1 that luminance values of pixels located in the first area are smaller than a first threshold value and the number of pixels C2 that luminance values of pixels located in the second area are bigger than a second threshold value, and selecting an image of which the calculated pixel C2 values are minimum.