Iris Recognition Using Cumulative-Sum Change Point Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional iris recognition methods, such as those using the Garbor transform, require high-quality images and complex calculations, leading to high computation complexity and performance degradation due to iris image shifts.
Innovation Solution
The method employs cumulative-sum-based change point analysis (CPA) to transform iris images into polar coordinates, divide them into cells, group and analyze these cells for pattern extraction, generating a pattern vector that is less computationally intensive and robust to image shifts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the Garbor transform and wavelet method are used to extract characteristic patterns from iris, then the recognition accuracy is improved, but the computation complexity becomes very high
Solution Approach 1:
The iris image is divided into multiple cells, and each cell is independently processed to extract characteristic patterns. This segmentation reduces the overall computation complexity by breaking down the complex task into smaller, manageable units that can be processed in parallel or sequentially with reduced computational burden.
Solution Approach 2:
The invention extracts only the essential characteristic patterns from the iris image by identifying change points in the cumulative sum values. This extraction approach removes unnecessary computational steps associated with transforming the entire image through complex transforms like Garbor and wavelet, retaining only the critical features needed for recognition.
2Measurement precision
If the Garbor transform method is used to extract characteristic patterns, then the recognition performance is improved, but the requirement for high quality iris images increases
Solution Approach 1:
Instead of requiring the entire iris image to be of high quality, the invention applies cumulative sum analysis to extract characteristic patterns from specific regions (cells) of the image. This partial action approach allows the system to achieve good recognition performance even when parts of the iris image are of lower quality, as long as the characteristic patterns in the analyzed cells are sufficient.
3Ease of manufacture
If the iris image is transformed into polar coordinated image to extract characteristic patterns, then the pattern extraction is enabled, but differences are generated between the obtained iris image and polar coordinated image due to position shift
Solution Approach 1:
The invention uses cumulative sum analysis to identify change points in the iris image data, which are then used to generate pattern vectors. This parameter-based approach focuses on the changes in pixel values rather than relying on the geometric transformation to polar coordinates, thereby avoiding the position shift differences that occur during coordinate transformation while still enabling effective pattern extraction.
Data Source
AI summary
A method of iris recognition using a cumulative-sum-based change point analysis and an apparatus using the same are disclosed. The method includes: transforming an iris image to a polar coordinated image having n×m pixel size and dividing the polar coordinated image into at least one cell; grouping the divided iris images into at least one of first groups having a predetermined number of cells, and at least one of second groups each having more cells than the first group has; performing a cumulative-sum-based change point analysis using a predetermined characteristic pattern value of each cell as a representative value; and generating a pattern vector by assigning a predetermined value to a cell having the change point and assigning a different value to other cells.