Merged CNN Eye Segmentation for Robust Iris Image Quality Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional iris code-based biometric systems are sensitive to variations such as image cropping, blurring, lighting conditions, and occlusions, requiring accurate eye image segmentation to separate the iris from the pupil and sclera, which is challenging and affects identification accuracy.
Innovation Solution
A convolutional neural network (CNN) with a merged architecture for both eye image segmentation and quality estimation, comprising a segmentation tower and a quality estimation tower, sharing common layers to improve segmentation accuracy and filter out poor-quality images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional iris code-based biometric systems are used, then personal biometric identification can be achieved, but the system becomes sensitive to variations such as image cropping, blurring, lighting conditions, and occlusions
Solution Approach 1:
The patent applies preliminary action by performing quality estimation and segmentation before iris code extraction. The system pre-processes images to identify and filter out poor-quality images that would otherwise compromise identification accuracy, thereby preventing the harmful effects of image variations from affecting the biometric system
Solution Approach 2:
The patent converts the harmful sensitivity to image variations into a benefit by using these variations as training data for the quality estimation neural network. The system learns to recognize and compensate for common image degradation patterns, transforming previously harmful factors into useful information for improving identification reliability
2Measurement precision
If accurate eye image segmentation is performed to separate the iris from the pupil and sclera, then identification accuracy is improved, but the segmentation process becomes challenging and time-consuming
Solution Approach 1:
The patent merges the segmentation task with quality estimation into a single integrated neural network architecture. The shared layers extract common features for both tasks simultaneously, eliminating the need for separate segmentation processing and thereby reducing time loss while maintaining high segmentation accuracy
Solution Approach 2:
The neural network is designed with multi-functionality, where the same network performs both quality estimation and segmentation tasks. The shared convolutional layers serve dual purposes by extracting features useful for both determining image quality and segmenting eye structures, thereby improving efficiency without sacrificing precision
3Productivity
If a merged CNN architecture with shared layers is used for both segmentation and quality estimation, then processing efficiency is improved, but the device complexity increases
Solution Approach 1:
The patent segments the neural network into distinct functional towers (quality estimation tower and segmentation tower) connected through shared layers. This modular segmentation allows each tower to specialize in its specific task while sharing common feature extraction capabilities, thereby managing complexity through structured organization rather than monolithic design
Data Source
AI summary
Systems and methods for eye image segmentation and image quality estimation are disclosed. In one aspect, after receiving an eye image, a device such as an augmented reality device can process the eye image using a convolutional neural network with a merged architecture to generate both a segmented eye image and a quality estimation of the eye image. The segmented eye image can include a background region, a sclera region, an iris region, or a pupil region. In another aspect, a convolutional neural network with a merged architecture can be trained for eye image segmentation and image quality estimation. In yet another aspect, the device can use the segmented eye image to determine eye contours such as a pupil contour and an iris contour. The device can use the eye contours to create a polar image of the iris region for computing an iris code or biometric authentication.