Fingerprint Image Normalization Using Adaptive Ridge Spacing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fingerprint verification systems struggle with verification failures due to differences in ridge pattern sizes, especially when comparing images of the same individual taken at different life stages or resolutions, leading to suboptimal performance in personal authentication and criminal identification.
Innovation Solution
An information processing apparatus and method that normalizes fingerprint images by estimating ridge spacing and adjusting image size based on this estimation, allowing for consistent verification across varying ridge patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fingerprint images are directly verified without normalization, then verification process is simple and fast, but verification accuracy deteriorates due to size differences in ridge patterns
Solution Approach 1:
The patent applies preliminary action by performing ridge spacing estimation and image normalization before the verification process. The system estimates ridge spacing from the input fingerprint image and normalizes the image size based on this estimation, ensuring that size differences do not affect verification accuracy. This preprocessing step is performed before comparison with registered templates.
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting the normalization scale based on the estimated ridge spacing. Instead of using a fixed normalization size, the system calculates an appropriate normalization scale according to the actual ridge spacing in the input image, thereby adapting the verification process to different fingerprint characteristics while maintaining accuracy.
2Reliability
If fixed-size normalization is applied to all fingerprint images, then verification consistency is improved, but accuracy deteriorates for images with different actual ridge spacings
Solution Approach 1:
The patent applies dynamics by making the normalization process adaptive rather than static. The system estimates the ridge spacing from each input fingerprint image and dynamically determines the normalization scale based on this estimation. This allows the normalization process to adapt to different ridge spacings while maintaining consistent verification conditions.
Solution Approach 2:
The patent applies parameter changes by using the estimated ridge spacing as a parameter to determine the normalization scale. Instead of applying a fixed normalization size to all images, the system adjusts the normalization parameter (scale) according to the actual ridge spacing characteristics of each input image, thereby preserving matching accuracy.
3Reliability
If ridge spacing estimation and adaptive normalization are performed, then verification accuracy for different individuals is improved, but processing time and computational load increase
Solution Approach 1:
The patent applies mechanics substitution by replacing complex manual or rule-based normalization approaches with an automated ridge spacing estimation mechanism. The system uses algorithmic estimation of ridge spacing followed by automatic calculation of normalization parameters, substituting what would otherwise require complex manual intervention or multiple trial normalizations.
Data Source
AI summary
An information processing apparatus includes: an acquisition unit that acquires a pattern image obtained by imaging ridges of a living body; an estimation unit that sets a sampling point in the pattern image and estimates ridge spacing of the sampling point; and a normalization unit that normalizes a size of the pattern image on the basis of an estimation result by the estimation unit.