Fingerprint Sensor Image Processing for Finger-Mark Discrimination

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fingerprint sensors are sensitive to skin type, finger dampness, and lighting conditions, leading to variable and difficult-to-distinguish images that include both genuine fingerprints and marks, which can be confused with each other.

Innovation Solution

A method involving determining ridge and valley values for each pixel, calculating a normalized dynamic range, and comparing it to a threshold to differentiate between pixels showing a finger and marks, with optional additional conditions on ridge and valley values to enhance accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional fingerprint sensors are used to acquire images, then the sensor can detect skin patterns, but the images become variable and difficult to distinguish due to sensitivity to skin type, dampness, and lighting conditions

Engineering Contradiction:

Improveimage quality consistencyVSAvoidsensitivity to lighting and skin conditions

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent transforms the image data by calculating a normalized dynamic range parameter for each pixel. This parameter is computed as the ratio of the difference between ridge and valley values to a reference value, thereby changing the representation of the fingerprint image from raw sensor values to a normalized scale that is independent of lighting conditions and skin characteristics.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces direct reliance on raw sensor signal intensity with a computational approach using ridge-valley differential analysis. Instead of depending on absolute light reflection values that vary with lighting conditions, the system uses the relative difference between ridges and valleys to determine fingerprint presence, substituting a mechanical/optical dependency with a mathematical transformation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If the sensor detects marks left by fingers, then the sensor can capture skin pattern-like structures, but these marks cannot be distinguished from genuine fingerprints within sight

Engineering Contradiction:

Improvefingermark discrimination accuracyVSAvoiddiscrimination between fingers and marks

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the fingerprint image into individual pixels and processes each pixel independently by calculating its normalized dynamic range based on local ridge and valley values. This pixel-level segmentation allows for fine-grained analysis of each region's characteristics, enabling the system to distinguish between genuine fingerprints and marks based on their unique local patterns.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies local quality analysis by computing the normalized dynamic range specifically for each pixel based on its local ridge and valley values. This allows different regions of the image to be evaluated according to their local characteristics, enabling the system to identify pixels that correspond to genuine fingerprint ridges versus marks, as each region has distinct local quality properties.

Inventive Principle:

Principle #3Local quality

3Illumination intensity

If the sensor uses internal light sources and ambient light for imaging, then the sensor can capture sufficient light for fingerprint detection, but lighting conditions create variability in the acquired images

Engineering Contradiction:

Improvelight capture capabilityVSAvoidimage consistency under varying lighting

Core Design Contradiction:

Illumination intensityVSStability of the object's composition

Solution Approach 1:

The patent converts the harmful effect of lighting variability into a beneficial normalization process. By calculating the normalized dynamic range as the ratio of the ridge-valley difference to a reference value, the system uses the lighting conditions themselves as part of the normalization reference, thereby converting the variability introduced by different lighting into a mechanism that equalizes the image data across varying illumination conditions.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Data Source

PatentUS20250292613A1Method for processing an image acquired by a fingerprint sensor, in order to discriminate between fingers and marks

Publication Date: 2025.09.18 IDEMIA PUBLIC SECURITY FRANCE

AI summary

A method is provided for processing an image acquired by a fingerprint sensor, in order to discriminate between fingers and marks. The method comprises determining a ridge value associated with a pixel of the image and a valley value associated with the pixel; calculating a dynamic range associated with the pixel as a ratio between a difference between the ridge value and the valley value that are associated with the pixel, and a reference value that is a linear combination of the ridge value and the valley value that are associated with the pixel; comparing the dynamic range associated with the pixel and a threshold; and generating a result associated with the pixel, said result indicating that the pixel shows a finger within sight of the fingerprint sensor only if the dynamic range is above the threshold.