Fingerprint Recognition With Key-Point Selection and Image Rotation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing fingerprint matching methods are slow due to the use of all feature points for fingerprint unlocking, especially when a user wears a face mask, impacting the speed of fingerprint recognition.
Innovation Solution
A method that selects key points from a fingerprint image, determines key point pairs with a distance parameter, sorts and rotates the image using a rotation matrix, and performs similarity matching to improve recognition speed and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all feature points are used for fingerprint matching, then matching accuracy is improved, but recognition speed deteriorates
Solution Approach 1:
The patent segments the fingerprint feature points into two categories: key points (L points) and other feature points. Only the key points are used for template matching and recognition, while other feature points are discarded. This segmentation reduces the number of points processed during matching, thereby improving recognition speed while maintaining accuracy through selective use of the most informative key points.
Solution Approach 2:
The patent extracts only the essential key points from the complete set of fingerprint feature points. By taking out and retaining only the L key points that carry the most discriminative information, the system reduces computational complexity and accelerates recognition speed without sacrificing the core matching accuracy.
2Reliability
If all feature points are stored in the fingerprint template library, then matching completeness is improved, but storage space increases
Solution Approach 1:
The patent extracts and stores only the key point features (L points) in the fingerprint template library, excluding other non-key feature points. This extraction reduces the amount of data stored while maintaining the essential information needed for accurate matching, thereby reducing storage space requirements without compromising matching completeness.
Solution Approach 2:
The patent segments the fingerprint features into key points and other points, storing only the key points in the template library. This segmentation approach maintains matching completeness by preserving the most critical features while significantly reducing the quantity of data stored.
3Productivity
If key point selection and image rotation are performed, then recognition speed is improved, but processing complexity increases
Solution Approach 1:
The patent performs key point selection and image rotation as preliminary actions before the main matching process. By pre-processing the fingerprint image to identify and align the L key points and compute the rotation matrix in advance, the system simplifies the subsequent matching operation and accelerates recognition speed, though it introduces additional processing steps.
Solution Approach 2:
The patent changes the parameter space by transforming the fingerprint image through rotation and translation operations defined by the rotation matrix. This parameter transformation aligns the key points between the input image and template, enabling faster and more accurate matching while increasing the computational complexity of the processing pipeline.
Data Source
AI summary
The method includes: obtaining features of L key points of a first fingerprint image; determining G pairs of key points based on the L key points of the first fingerprint image and L key points of a first fingerprint template; sorting the G pairs of key points based on the first distance parameter corresponding to each pair of key points, and determining N pairs of key points from the G pairs of key points that are sorted; determining a first rotation matrix using the N pairs of key points, and rotating the first fingerprint image based on the first rotation matrix to obtain a second fingerprint image, where the second fingerprint image is in a same direction as the first fingerprint template; and performing similarity matching using the second fingerprint image and the first fingerprint template.