Biometric Eye Recognition Using Augmented Image Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric systems using images of the human eye face performance issues when iris or eye veins are partially occluded, leading to unreliable recognition and user inconvenience, as existing methods are imprecise and require explicit recovery of model parameters under specific acquisition conditions.
Innovation Solution
The method involves generating augmented images by modeling and simulating various degrees of occlusion, particularly through eyelid and eyelash parameters, to train a classifier for improved biometric recognition, allowing for recognition without explicit prior recovery of model parameters and accommodating partial occlusions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional biometric systems require explicit recovery of model parameters under specific acquisition conditions, then measurement precision may be maintained, but device complexity and ease of operation deteriorate
Solution Approach 1:
The system performs preliminary actions by generating augmented images with simulated occlusions during the training phase. The classifier is pre-trained on these augmented images before actual biometric recognition, enabling it to handle partially occluded eyes without requiring explicit parameter recovery or specific acquisition conditions during operation.
2Measurement precision
If traditional biometric systems require explicit recovery of model parameters, then measurement precision may be maintained, but device complexity increases
Solution Approach 1:
The system creates copies of the original eye images through augmentation processes, generating synthetic images with various occlusion patterns. These copied images are used for training the classifier, eliminating the need for complex parameter recovery mechanisms while maintaining recognition accuracy.
3Reliability
If biometric systems are trained only on clear images without occlusion, then training data quality may be high, but adaptability to real-world conditions deteriorates
Solution Approach 1:
The system changes parameters by introducing occlusion parameters during image augmentation. By varying occlusion patterns, positions, and types in the training data, the classifier learns to recognize eyes under diverse conditions, improving both reliability and adaptability to real-world scenarios with partial occlusions.
Data Source
AI summary
This disclosure describes methods and systems for improving performance of biometric systems that use features in the eye, such as iris or eye-veins, particularly when both biometric performance and user convenience are objectives. The disclosure relates to optimizing biometric performance when the iris or eye veins are neither fully visible, nor fully occluded, but in a partially-occluded state which occurs often when a user's eye is in a relaxed or natural state. In some embodiments, the method comprises a biometric enrollment or training step whereby an original image of a human eye is acquired, and a plurality of synthetic or augmented images are generated that are a combination of the original image and synthesized images that simulate specific ways that the eye can be occluded. A classifier can be trained using the plurality of augmented reference images, and subsequent recognition is performed using the classifier on newly acquired real images.