Latent Fingerprint Pattern Estimation via Ridge Flow Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern automatic fingerprint identification systems (AFIS) face challenges in accurately analyzing low-quality latent fingerprint images due to distortions and noise, which limits feature extraction and matching accuracy, especially for partial images lacking distinctive features.
Innovation Solution
The system generates a latent ridge flow map and compares it to reference ridge flow maps to estimate fingerprint patterns using feature vectors and trained classifiers, reducing the number of reference images to compare by filtering out mismatched patterns, thereby enhancing identification accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If automatic pattern classification techniques are used for partial latent fingerprint images, then the identification process is automated, but the accuracy deteriorates due to lack of distinctive features
Solution Approach 1:
The patent introduces ridge flow maps as an intermediary representation between the latent fingerprint image and pattern classification. Instead of directly classifying partial latent images which lack distinctive features, the system first generates ridge flow maps that capture the directional information of ridges. These ridge flow maps serve as a mediator that preserves essential pattern information even when the original image is partial or low quality, enabling accurate automated classification.
2Device complexity
If latent fingerprint images with noise and distortions are directly analyzed, then the analysis process is simple, but the identification accuracy deteriorates
Solution Approach 1:
The patent applies preliminary processing by generating ridge flow maps before performing pattern classification or matching. This preliminary action of creating ridge flow maps enhances the quality of the fingerprint data by emphasizing ridge directional information while suppressing noise and distortions. By performing this enhancement step before the main analysis, the system improves identification accuracy without significantly increasing overall complexity.
3Reliability
If all reference ten-print images are compared against latent fingerprint images, then comprehensive identification is achieved, but the computational burden increases
Solution Approach 1:
The patent performs preliminary pattern classification on the latent fingerprint image using ridge flow maps to determine the fingerprint pattern type (e.g., loop, whorl, arch). Based on this preliminary classification, the system can filter the reference database to only compare against ten-print images with matching or compatible patterns. This preliminary filtering action significantly reduces the number of comparisons needed while maintaining identification completeness, thereby improving processing speed without sacrificing reliability.
Data Source
AI summary
Systems and methods may be used by an automatic fingerprint identification system to estimate patterns of a latent fingerprint. A latent fingerprint image, and a plurality of reference ridge flow maps may initially be obtained. Each reference ridge flow map may be associated with a particular fingerprint pattern. A latent ridge flow map for the obtained latent fingerprint image may be computed. One or more characteristics associated with the latent ridge flow map may be compared to one or more characteristics associated with each of the plurality of reference ridge flow maps. A similarity score between the latent ridge flow map and a particular reference ridge flow map may be computed for each of the plurality of reference ridge flow maps. One or more fingerprint patterns present within the latent fingerprint may then be determined and provided for output.