Adaptive Iris Feature Pattern Updating Under Ambient Brightness Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing iris recognition technologies face challenges in maintaining accuracy due to variations in iris images caused by pupil size changes with ambient brightness and the need for real-time detection, particularly in portable devices.
Innovation Solution
A method and apparatus for updating biometric feature patterns by acquiring successive biometric images, comparing them with pre-registered patterns, and adding feature points to improve matching ratios, including temporary storage and updating based on time and sensor data correlations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If iris recognition is performed using traditional methods, then real-time detection is achieved, but recognition accuracy deteriorates due to pupil size changes with ambient brightness
Solution Approach 1:
The patent applies dynamics by making the feature pattern adaptive and updateable rather than static. The system dynamically adjusts the registered feature pattern based on newly acquired biometric images, allowing the recognition system to adapt to varying ambient brightness conditions and pupil size changes while maintaining high recognition accuracy
Solution Approach 2:
The patent changes the parameter of the registered feature pattern by incorporating new feature points from subsequently acquired biometric images. This parameter update mechanism allows the system to adjust to environmental variations such as ambient brightness changes, thereby improving recognition accuracy without requiring complete re-registration
2Measurement precision
If multiple successive biometric images are acquired and processed, then recognition accuracy is improved, but processing time and system complexity increase
Solution Approach 1:
The patent applies preliminary action by pre-registering a feature pattern before actual recognition is needed. This pre-processing step stores essential biometric characteristics in advance, so that during real-time operation, the system only needs to compare incoming images against the pre-established pattern, significantly reducing processing time while maintaining high accuracy
Solution Approach 2:
The patent uses partial action by selectively updating only the necessary portions of the feature pattern rather than processing all images completely. The system compares successive images and updates the registered pattern incrementally, adding new feature points only when needed, which reduces overall processing time while still improving recognition accuracy
3Reliability
If the registered feature pattern is updated frequently, then recognition accuracy is maintained, but device complexity and computational load increase
Solution Approach 1:
The patent implements feedback by using the results of image comparisons to determine whether and how to update the registered feature pattern. The system continuously monitors recognition outcomes and adjusts the feature pattern accordingly, maintaining high authentication reliability while avoiding unnecessary updates that would increase system complexity
Solution Approach 2:
The system performs self-service by automatically updating its own registered feature pattern based on newly acquired biometric images without requiring external intervention or complex manual configuration. This self-updating mechanism maintains authentication reliability while keeping the system relatively simple in operation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Method comprising: acquiring a plurality of successive biometric images associated with a same type of a biometric object associated with a same user, each of the successive biometric images comprising at least one feature pattern, the biometric object being one of an iris or a fingerprint; comparing a first biometric image of the images with a pre-registered feature pattern; in response to determining the first biometric image not matching the pre-registered feature pattern by the predetermined ratio or more, temporarily storing the first biometric image; comparing a second biometric image arranged after the first biometric image with the pre-registered feature pattern; in response to determining the second biometric image matching the pre-registered feature pattern by the predetermined ratio or more, adding at least one feature point of the first biometric image and at least one feature point of the second biometric image to the pre-registered feature pattern.