Fingerprint Preview Quality Assessment Using Ridge Flow Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Livescan type devices face limitations in providing output that can be correlated with sophisticated quality measures used by enrollment applications or Automatic Fingerprint Identification Systems (AFIS), due to processing power and bandwidth restrictions, which affects dynamic segmentation of fingertips from hand structures and background elements.

Innovation Solution

A resolution-independent ridge flow detection technique is employed, using a ridge flow map to determine fingerprint quality based on strength, continuity, and localized image contrast, enabling real-time processing and segmentation for images of fingertips, hands, or whole hands.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If full resolution scanning (500 ppi, 1000 ppi) is used for fingerprint quality metrics, then measurement precision is improved, but processing power requirements and bandwidth increase significantly

Engineering Contradiction:

Improvefingerprint quality assessment accuracyVSAvoidprocessing power requirements

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The patent extracts only the essential quality assessment information from full-resolution images by using low-resolution preview data. Instead of processing complete high-resolution images, the system extracts key features (ridge flow patterns, contrast metrics, segmentation information) from down-sampled preview images, achieving acceptable quality assessment with significantly reduced processing requirements.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs partial quality assessment using only the necessary portion of image data. By implementing quality metrics that work with low-resolution preview images rather than requiring complete high-resolution scanning, the system achieves sufficient quality determination without the excessive processing power needed for full-resolution analysis.

Inventive Principle:

Principle #16Partial or excessive action

2Measurement precision

If full resolution scanning is used for fingerprint quality metrics, then quality assessment accuracy is improved, but processing time increases

Engineering Contradiction:

Improvequality assessment accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary quality assessment using low-resolution preview images before committing to full-resolution scanning. By evaluating basic quality metrics (contrast, ridge flow, segmentation) from preview data, the system can quickly determine whether an image is sufficient, eliminating the need for time-consuming full-resolution processing in many cases.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a fast path for quality assessment that skips detailed full-resolution analysis when low-resolution preview data is sufficient. By rushing through the essential quality checks using down-sampled images, the system achieves rapid quality determination without waiting for complete high-resolution image processing.

Inventive Principle:

Principle #21Skipping (Rushing through)

3Measurement precision

If sophisticated quality metrics are used, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improvequality metric accuracyVSAvoidprocessing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements quality metrics that assess local image characteristics (ridge flow in specific regions, localized contrast, segment-specific features) rather than requiring complex global analysis. This allows sophisticated quality assessment to be performed through multiple simple local measurements rather than one complex global metric, reducing system complexity while maintaining precision.

Inventive Principle:

Principle #3Local quality

4Measurement precision

If dynamic segmentation is implemented, then segmentation accuracy is improved, but processing power requirements increase

Engineering Contradiction:

Improvesegmentation accuracyVSAvoidprocessing power

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The patent divides the fingerprint image into distinct segments (ridge regions, valley regions, background) and applies simplified processing to each segment independently. By segmenting the image first, the system can perform quality assessment and feature extraction on smaller, more manageable portions, reducing overall processing power requirements while maintaining segmentation accuracy.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11250239B2Fingerprint preview quality and segmentation

Publication Date: 2022.02.15 AWARE INC

AI summary

A ridge flow based fingerprint image quality determination can be achieved independent of image resolution, can be processed in real-time and includes segmentation, such as fingertip segmentation, therefore providing image quality assessment for individual fingertips within a four finger flat, dual thumb, or whole hand image. A fingerprint quality module receives from one or more scan devices ridge-flow—containing imagery which can then be assessed for one or more of quality, handedness, historical information analysis and the assignment of bounding boxes.