Blockwise Fingerprint Inter-Ridge Estimation Under Interfering Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating inter-ridge distances in fingerprints are inaccurate when the image contains interfering signals, particularly in latent fingerprints captured by generic devices.
Innovation Solution
A method involving a classification map generation, local inter-ridge distance estimation, and average distance calculation using neural networks, excluding normalization layers, to accurately determine inter-ridge distances in the presence of interfering patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional inter-ridge distance estimation methods are used on test images, then the process is simple and fast, but the measurement precision deteriorates when interfering signals are present
Solution Approach 1:
The test image is divided into multiple blocks, and a classification map is generated for each block to estimate local inter-ridge distances. This segmentation approach allows the system to process different regions independently, improving overall measurement precision while managing computational complexity through localized analysis rather than global processing
Solution Approach 2:
The patent applies different processing strategies to different blocks based on their local characteristics. By generating classification maps and estimating local inter-ridge distances for each block individually, then computing a weighted average, the system adapts to local variations and interfering signals, thereby improving measurement precision without requiring uniformly complex processing across the entire image
2Measurement precision
If generic imaging devices are used to capture latent fingerprints, then ease of operation is improved, but measurement precision deteriorates due to interfering patterns from the medium
Solution Approach 1:
The patent extracts the classification map information from each block separately, identifying local inter-ridge distances by analyzing only the relevant fingerprint features in each region. This extraction process isolates the useful fingerprint information from the interfering background patterns, allowing accurate measurement even when the entire image contains distracting elements from the medium
Solution Approach 2:
The classification map serves as an intermediary structure that mediates between the raw test image and the final inter-ridge distance estimation. By introducing this intermediate representation that captures local distance characteristics, the system can filter out interfering patterns from the medium while preserving the essential fingerprint ridge information needed for accurate measurement
Data Source
AI summary
A method comprising: generating a classification map comprising, for each block forming part of a plurality of blocks of a test image and for each class of a plurality of classes of distances in pixels, a score indicative of a probability of existence in the test image of a segment passing through the block and the length of which in pixels constitutes an inter-ridge distance of a fingerprint included in the class, generating a distance map comprising, for each block of the plurality of blocks, a local inter-ridge distance in pixels estimated for the block, and estimating an average inter-ridge distance in pixels of the test fingerprint on the basis of the inter-ridge distance map, the estimation comprising selecting, from the inter-ridge distance map, local inter-ridge distances of interest according to a criterion of proximity to the class of interest, and computing an average of the local inter-ridge distances of interest.