Iris Recognition Quality Filtering for Mobile Biometrics

Solution Overview

Problem

Existing iris recognition systems in mobile devices face significant time lags and high false match rates due to computationally intensive image processing, particularly when processing every frame in a video sequence, leading to inefficiencies and inaccuracies in biometric identification.

Innovation Solution

Implementing a method that selectively processes and compares iris images based on predetermined quality criteria, such as image sharpness, grayscale spread, and similarity, to reduce unnecessary processing and improve accuracy, while allowing for multiple passes of feature extraction and comparison to optimize response time and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If every frame in a video sequence is processed for iris recognition, then recognition accuracy is improved, but processing time increases significantly and false match rate increases

Engineering Contradiction:

Improverecognition accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by performing quality assessment on image frames before full iris recognition processing. The system pre-evaluates frames using focus measurement and other quality metrics to identify suitable frames for processing, thereby avoiding computationally intensive processing of low-quality frames and reducing overall processing time while maintaining recognition accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements partial action by processing only a subset of video frames rather than every frame. The system selectively processes frames that meet predetermined quality criteria, performing full iris recognition only on high-quality frames while skipping low-quality frames, thus reducing processing time and false match rates without significantly compromising recognition accuracy

Inventive Principle:

Principle #16Partial or excessive action

2Reliability

If every frame in a video sequence is processed for iris recognition, then recognition coverage is improved, but false match rate increases

Engineering Contradiction:

Improverecognition coverageVSAvoidfalse match rate

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by performing quality assessment on image frames before full iris recognition processing. The system pre-evaluates frames using focus measurement and other quality metrics to identify suitable frames for processing, thereby avoiding computationally intensive processing of low-quality frames and reducing overall processing time while maintaining recognition accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback by using quality assessment results to guide subsequent processing decisions. The system measures focus quality and other frame characteristics, then uses this feedback information to determine whether to proceed with full iris recognition processing, creating a closed-loop system that adapts processing based on frame quality

Inventive Principle:

Principle #23Feedback

3Measurement precision

If computationally intensive image processing is performed, then recognition accuracy is improved, but processing speed decreases

Engineering Contradiction:

Improverecognition accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSSpeed

Solution Approach 1:

The patent applies preliminary action by performing quality assessment on image frames before full iris recognition processing. The system pre-evaluates frames using focus measurement and other quality metrics to identify suitable frames for processing, thereby avoiding computationally intensive processing of low-quality frames and reducing overall processing time while maintaining recognition accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements partial action by processing only a subset of video frames rather than every frame. The system selectively processes frames that meet predetermined quality criteria, performing full iris recognition only on high-quality frames while skipping low-quality frames, thus reducing processing time and false match rates without significantly compromising recognition accuracy

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS9582716B2Apparatuses and methods for iris based biometric recognition

Publication Date: 2017.02.28 DELTA ID INC

AI summary

The invention provides a method for iris based biometric recognition. The method includes receiving an image from an image sensor and determining whether the received image includes an iris. The steps of receiving and determining are repeated until the received image includes an iris. Responsive to determining that a received image includes an iris, iris information corresponding to such received image is compared with stored iris information corresponding to at least one iris and a match decision or a non-match decision is rendered based on an output of the comparison. The invention additionally provides a system and computer program product configured for iris based biometric recognition.