Adaptive Fingerprint Calibration for Changing Unlock Environments

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Fingerprint recognition systems face challenges in maintaining calibration effectiveness due to environmental changes, leading to degraded unlocking experiences and reduced accuracy when users wear masks.

Innovation Solution

An adaptive fingerprint calibration method that updates the calibration image based on collected fingerprint images, using criteria such as overlapping area, real-finger scenarios, and foreign object detection to improve accuracy and speed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a fingerprint calibration image is preset in the terminal during production, then the fingerprint image can be calibrated to eliminate interference noise, but the calibration effect deteriorates as the external environment changes

Engineering Contradiction:
Improvefingerprint image calibration accuracyVSAvoidadaptation to external environment changes
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic calibration image update mechanism where the calibration image is no longer static but is continuously updated based on newly collected fingerprint images. The system determines whether to update the calibration image by comparing new fingerprint images with existing ones, allowing the calibration data to adapt to environmental changes while maintaining measurement precision.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system establishes a feedback loop where fingerprint recognition results are used to evaluate calibration effectiveness. When recognition accuracy deteriorates or environmental conditions change, the system triggers calibration image updates. This feedback mechanism ensures the calibration image remains effective under varying external conditions.

Inventive Principle:
Principle #23Feedback

2Adaptability or versatility

If the calibration image is updated frequently to adapt to environment changes, then the adaptation degree improves, but the system complexity and processing overhead increase

Engineering Contradiction:
Improvecalibration image adaptabilityVSAvoidcalibration update mechanism complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces specific parameters and thresholds to control calibration image updates, such as similarity thresholds for comparing fingerprint images and conditions for determining when updates are necessary. By changing these parameters dynamically based on recognition performance and environmental factors, the system achieves adaptability without excessive complexity.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system performs self-evaluation of calibration effectiveness by monitoring fingerprint recognition accuracy and automatically triggering calibration updates when needed. This self-service mechanism reduces the need for complex external control systems while maintaining high adaptability to environmental changes.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If multiple fingerprint images are collected and processed to generate calibration image, then the calibration accuracy improves, but the processing time and computational resources increase

Engineering Contradiction:
Improvecalibration image accuracyVSAvoidcalibration processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary filtering and selection of fingerprint images before generating the calibration image. By pre-processing candidate images to identify high-quality samples and removing duplicates or low-quality images, the system reduces the computational burden of calibration image generation while maintaining or improving accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system extracts only the essential and most representative features from multiple fingerprint images to create the calibration image, rather than processing all pixel data from every image. This extraction approach maintains calibration accuracy while significantly reducing processing time and computational resource requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4459573B1Fingerprint recognition method and apparatus
Publication Date: 2026.03.18 HONOR DEVICE CO LTD
  • EP4459573B1 patent drawingFigure 1(1)~1(2)
  • EP4459573B1 patent drawingFigure 2
  • EP4459573B1 patent drawingFigure 3

AI summary

A fingerprint recognition method and apparatus are applied to the field of fingerprint recognition technologies. The method includes: collecting a to-be-enrolled fingerprint image; performing, based on a first calibration image, calibration processing on the to-be-enrolled fingerprint image to obtain a first fingerprint image; and determining whether an adaptive calibration image exists; and updating the first calibration image based on the first fingerprint image and a first update coefficient when the adaptive calibration image exists, to obtain a second calibration image; or generating a third calibration image based on the first fingerprint image when no adaptive calibration image exists. The third calibration image is an image obtained by performing summation and averaging on a plurality of frames of fingerprint images, or the third calibration image is an image obtained by updating the first calibration image based on the first fingerprint image. A calibration image of an electronic device can be adaptively updated, so that a degree of adaptation between the calibration image and a current environment is improved, thereby better calibrating a collected fingerprint image, and improving unlocking experience of a user.