Iris Recognition Using Non-Uniform Feature Mark Boxes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Iris recognition accuracy is compromised by environmental changes such as varying sunlight angles and intensities, leading to texture changes and over-exposure issues in iris images, which affect the reliability of consumer electronic devices.
Innovation Solution
An electronic device and method that generates non-uniform feature mark boxes from iris images, allowing for bidirectional cross comparison to determine the similarity between iris images, thereby enhancing recognition accuracy and fault tolerance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional iris recognition methods are used, then the recognition process is simple, but recognition accuracy decreases under environmental changes such as varying sunlight angles and intensities
Solution Approach 1:
The patent divides the iris image into multiple regions and extracts features from each region separately using multiple feature extraction methods. This segmentation approach allows the system to focus on specific iris characteristics that remain stable under different environmental conditions, thereby improving recognition accuracy without requiring overly complex global processing
Solution Approach 2:
The patent employs multiple feature extraction methods that analyze different parameters and characteristics of the iris image simultaneously. By changing the parameters being analyzed (such as texture, color, geometric features) and using multiple extraction approaches, the system can identify features that remain consistent despite environmental variations in lighting and angle
2Measurement precision
If feature extraction focuses on specific texture regions, then recognition accuracy improves, but the method complexity increases
Solution Approach 1:
The patent segments the iris image into multiple regions and applies different feature extraction methods to each region. This allows focused analysis of specific texture areas that are most reliable for identification, improving accuracy while managing complexity through localized processing rather than uniform complex analysis across the entire image
Solution Approach 2:
The patent implements multiple feature extraction methods that can be applied across different image regions, creating a multi-functional system. These methods serve universal purposes of extracting various types of features (texture, color, geometric) that can be used individually or in combination, reducing the need for specialized complex processing for each specific feature type
Data Source
AI summary
An electronic device, an iris recognition method and a non-volatile computer-readable medium are provided. A processor in the electronic device obtains a first and second iris images, and calculates a plurality of first and second feature mark boxes that are non-uniformly arranged according to the first and second iris images. The processor uses the first feature mark boxes to obtain a first and second image features from the first and second iris images respectively, and compares the first and second image features to obtain a first recognition result. The processor uses the second feature mark boxes to obtain a third and fourth image features from the second and first iris images respectively, and compares the third and fourth image features to obtain a second recognition result. The processor determines a similarity degree of the first and second iris images according to the first and second recognition results.