Iris Authentication Device Using Facial Feature Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current iris authentication methods face challenges in accurately distinguishing between the right and left eyes, particularly due to issues like dark shadows, strong lighting, facial expressions, and obstructions such as hair or glasses, which require high-cost, high-magnification cameras and advanced image analysis for accurate identification.
Innovation Solution
An iris authentication device and method that includes first and second image input units, a determination unit to identify whether the second image is of the left or right eye based on the first image, a memory for storing iris characteristic information, a score calculation unit for comparing iris patterns, and an authentication unit for verifying the user based on calculated scores, allowing for reliable identification and authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the inner corner of the eye is used to identify between right and left eyes, then identification can be performed, but accurate capture becomes difficult under various conditions (dark shadows, strong light, facial expressions, hair or glasses obstructions)
Solution Approach 1:
The patent extracts and uses multiple facial features (inner corner of eye, outer corner of eye, eyebrow positions, nose position, mouth position) separately to determine eye laterality, rather than relying on a single feature. This extraction approach allows the system to select from multiple available features to achieve accurate identification even when some features are obscured or difficult to capture.
Solution Approach 2:
The determination unit is designed to handle multiple types of facial features and multiple capture conditions universally. It can process various features (inner corner, outer corner, eyebrows, nose, mouth) and adapt to different lighting conditions, facial expressions, and obstructions, making the eye identification function robust across diverse scenarios.
2Measurement precision
If a telephoto camera with high magnification and high-accuracy image analyzing device is used to capture the inner corner of the eye, then identification accuracy improves, but device cost increases
Solution Approach 1:
The image capturing device is designed to capture multiple facial features (inner corner, outer corner, eyebrows, nose, mouth) simultaneously in a single wide-field view, rather than requiring a specialized telephoto camera for just the inner corner. This multi-functional approach allows standard cameras to achieve the same identification accuracy.
Solution Approach 2:
The patent segments the facial recognition task into multiple feature detection components (inner corner, outer corner, eyebrows, nose, mouth), each contributing to the overall eye laterality determination. This segmentation allows the use of standard imaging equipment to capture all features at once, eliminating the need for high-magnification specialized cameras.
3Reliability
If multiple facial features are used to determine eye laterality, then identification reliability improves under various conditions, but processing complexity increases
Solution Approach 1:
The determination unit employs a feedback mechanism where it evaluates the availability and quality of each facial feature, and adaptively selects the most suitable features for determination. This feedback-based selection process improves reliability by using only clear, unobstructed features while simplifying processing by excluding features that are difficult to capture or analyze.
Solution Approach 2:
The system is designed to use multiple facial features (excessive action) for determination, but practically uses only the subset of features that are successfully captured and meet quality thresholds (partial action). This approach ensures high reliability when possible, while automatically simplifying to fewer features when capture conditions are poor, thus managing processing complexity dynamically.
Data Source
AI summary
The disclosure is inputting a first image obtained by capturing an object of authentication moving in a specific direction; inputting a second image at least for one eye obtained by capturing a right eye or a left eye of the object; determining whether the second image is of the left eye or the right eye of the object, based on information including the first image, and outputting a determination result associated with the second image as left/right information; comparing characteristic information relevant to the left/right information, the characteristic information being acquired from a memory that stores the characteristic information of a right eye and a left eye pertaining to object to be authenticated, with characteristic information associated with the left/right information, and calculating a verification score; and authenticating the object captured in the first image and the second image, based on the verification score, and outputting an authentication result.