Eye Image Biometric Authentication for HMDs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication using eye images is challenging, especially when users wear Head-Mounted Displays (HMDs), as it is difficult to obtain suitable input images due to varying camera angles, eyelid movements, and gaze directions.
Innovation Solution
An apparatus and method for biometric authentication that selects a registered eye image most similar in shape to the eye image to be authenticated by comparing segmentation data and eye state information, improving authentication performance by correcting image tilt and centering the pupil.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple eye region images are captured and stored in the registration process to improve authentication performance, then authentication accuracy is improved, but the complexity of the authentication process increases due to the need to select and compare multiple images
Solution Approach 1:
The patent segments the eye region image into multiple key features including eye shape, pupil position, iris pattern, and eyelid characteristics. By breaking down the complex image comparison into these discrete segmented features, the system can efficiently compare and select the most similar registered image without processing the entire image data, thus reducing computational complexity while maintaining authentication accuracy.
Solution Approach 2:
The patent performs preliminary feature extraction and similarity calculation during the registration process, where multiple eye region images are pre-processed and stored with their extracted features. During authentication, this pre-prepared data allows for rapid comparison and selection of the most similar image, eliminating the need for real-time complex analysis and reducing the authentication process complexity.
2Adaptability or versatility
If the system captures eye images from various angles and conditions to handle user movement and gaze changes, then adaptability to different states is improved, but the difficulty of obtaining suitable input images for authentication increases
Solution Approach 1:
The patent applies local quality analysis by examining specific local regions of the eye image such as the pupil center, iris boundaries, and eyelid contours. By focusing on these critical local features rather than the entire image, the system can effectively match eye images even when captured from different angles or under varying conditions, improving adaptability while simplifying the detection process.
Solution Approach 2:
The patent utilizes parameter changes by transforming and normalizing image parameters such as eye shape coordinates, pupil position ratios, and iris pattern characteristics. These parameter transformations enable the system to compare eye images captured under different conditions (various angles, lighting, gaze directions) by mapping them to a common parameter space, thereby improving adaptability without increasing detection difficulty.
Data Source
AI summary
Disclosed herein is an apparatus and method for biometric authentication based on an eye image The apparatus receives the eye image to be authenticated that captures a region around an eye of a subject, generates segmentation data and eye state information from the eye image to be authenticated, selects a registered eye image based on similarity acquired by comparing the segmentation data and eye state information of the eye image to be authenticated with those of previously registered eye images, and authenticates the subject based on the similarity.