Dual-Sensor Imaging for Iris Authentication Under Sunglasses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image capturing apparatuses struggle to extract unique biological information, such as iris color, from images of individuals wearing sunglasses, as existing techniques are not designed to handle infrared light images effectively, leading to inaccurate feature extraction.
Innovation Solution
An image capturing apparatus and method that simultaneously captures visible light and infrared light images, using a detection unit to identify objects, an extraction unit to extract feature information from infrared light images, and an estimation unit to estimate unique information, even when specific portions are shielded from light, thereby improving authentication accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If an infrared light image is used to capture eyes of persons wearing sunglasses, then the eye portion can be captured, but unique biological information such as iris color cannot be extracted
Solution Approach 1:
The patent segments the imaging function into two separate sensors: a visible light image sensor for capturing color information and an infrared light image sensor for capturing eye portion images. This segmentation allows each sensor to specialize in its strength, with the visible light sensor providing color data and the infrared sensor providing eye structure data, thereby resolving the contradiction between capturing eyes and extracting iris color information.
Solution Approach 2:
The patent merges the outputs of two different image sensors (visible light and infrared) by combining their respective image data in post-processing. The visible light image provides color information while the infrared image provides eye portion visibility, and by merging these complementary data sources, the system achieves both eye capture capability and iris color extraction even when sunglasses are worn.
2Reliability
If conventional image processing techniques are used on infrared light images, then eye portion can be detected, but feature extraction accuracy deteriorates
Solution Approach 1:
The patent applies different processing techniques to different parts of the image data based on their specific characteristics. The visible light image data is processed for color information extraction, while the infrared image data is processed for eye portion detection. By applying locally appropriate processing techniques matched to the specific quality and characteristics of each sensor's output, the system achieves both reliable eye detection and accurate feature extraction.
Solution Approach 2:
The patent introduces an intermediary processing stage that separately processes visible light and infrared image data before combining the results. This intermediary processing allows each sensor type to be optimized for its specific strengths, with the visible light sensor optimized for color information and the infrared sensor optimized for eye structure, thereby improving overall feature extraction accuracy.
3Device complexity
If a single image sensor is used, then device complexity is reduced, but the ability to extract unique biological information from shielded portions is lost
Solution Approach 1:
The patent implements a multi-functional imaging system where two different image sensors work together to achieve multiple objectives: the visible light sensor captures color information and the infrared sensor captures eye portion visibility. By combining these sensors, the system achieves universal functionality that can extract unique biological information from shielded portions, overcoming the limitations of a single sensor while maintaining practical device complexity through integrated processing.
Data Source
AI summary
An image capturing apparatus that can capture a visible light image and an infrared light image of the same object, the image capturing apparatus comprises a detection unit configured to detect a predetermined object in the visible light image, an extraction unit configured to extract feature information of a specific portion in the object detected in the infrared light image by the detection unit, and an estimation unit configured to estimate unique information of the predetermined object using the feature information extracted by the extraction unit.