Iris Detection Binarization to Suppress Corneal Reflections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing iris detection technologies suffer from reduced accuracy due to corneal reflections and background interference, leading to inaccuracies in detecting iris center position and size.
Innovation Solution
A method involving binarization and pixel replacement, where pixels in a first luminance area satisfying a condition are replaced with a different luminance value, followed by calculating iris information using the modified image to suppress the influence of corneal reflections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional iris detection methods are used, then the detection process is simple, but the accuracy decreases when cornea reflects external light or background
Solution Approach 1:
The patent extracts and removes the harmful reflective regions from the image processing flow. By detecting high-luminance areas that correspond to corneal reflections and excluding them from iris detection, the method isolates the useful information (iris texture) from the harmful interference (reflections), thereby improving detection accuracy without being affected by corneal glare
Solution Approach 2:
The patent applies different processing strategies to different regions of the image. High-luminance regions identified as corneal reflections are handled differently from normal regions - they are excluded from gradient calculation and iris boundary detection. This localized quality adjustment ensures that reflective areas do not degrade the overall detection accuracy
2Measurement precision
If binarization is performed with fixed threshold, then processing is fast, but accuracy decreases due to reflected light creating false contours
Solution Approach 1:
The patent performs preliminary detection and removal of high-luminance corneal reflection regions before performing binarization and contour detection. By preprocessing the image to eliminate reflective artifacts, the subsequent binarization with fixed threshold produces accurate iris contours without false edges, maintaining both speed and accuracy
Solution Approach 2:
The patent introduces an intermediate processing step that detects and masks corneal reflection regions between the original image and the binarization process. This intermediary operation prevents reflected light from creating false contours during thresholding, acting as a mediator that protects the final detection accuracy
Data Source
AI summary
An iris detection method includes acquiring a first image; generating a second image including an eye section of the person from the first image; generating a third image where pixels having a gradation value smaller than a threshold value are represented by a first luminance value and pixels having a gradation value equal to or greater than the threshold value are represented by a second luminance value after binarizing the second image; generating a fourth image by replacing the pixel of the second luminance value come into existence in a first luminance area having the first luminance value and satisfying a predetermined condition with the pixel of the first luminance value in the third image; calculating iris information including information about at least one of a position and a size of the iris of the person by use of the fourth image; and outputting the iris information.