Fingerprint Template Management for Changed and Forged Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fingerprint authentication systems face challenges due to changes in user fingerprints over time, obstacles during input, and inaccurate determination of forged fingerprints, leading to decreased authentication accuracy and user inconvenience.
Innovation Solution
An electronic device with a sensor, memory, and processor that manages fingerprint templates, including forged, abnormal, and normal state images, generates virtual fingerprint images, and trains an AI model to improve authentication accuracy by reflecting user fingerprint changes and obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the registered fingerprint image is not updated over time, then the authentication system maintains simplicity and speed, but the authentication accuracy decreases as user fingerprints change
Solution Approach 1:
The system performs preliminary classification of fingerprint images during the registration process, categorizing them as normal, abnormal, or forged states. This preliminary action enables the system to proactively manage fingerprint templates before authentication issues arise, improving accuracy without requiring frequent manual updates by users.
Solution Approach 2:
The electronic device automatically classifies and manages fingerprint images without requiring user intervention. The device self-services by identifying abnormal states (such as obstacles on fingerprints) and forged images, then automatically updating templates or rejecting fraudulent attempts, eliminating the need for users to manually update their fingerprints.
2Reliability
If obstacles are present on the user's fingerprint during input, then the authentication process remains simple and quick, but the success rate of authentication varies and decreases
Solution Approach 1:
The system performs preliminary classification of the input fingerprint image to detect abnormal states such as obstacles (moisture, dryness, injuries) before authentication. By identifying these conditions in advance, the system can handle them appropriately—either by requesting a retry or by adjusting the authentication process—thereby improving reliability without making the operation more complex for the user.
Solution Approach 2:
The classification module acts as an intermediary between the fingerprint sensor and the authentication algorithm. It detects abnormal states and translates them into appropriate handling decisions, shielding the user from complexity while improving authentication success rates by preventing false rejections due to temporary fingerprint conditions.
3Measurement precision
If the ASP module uses a generic model to determine forged fingerprints, then the system maintains simplicity and speed, but the accuracy of forged fingerprint detection decreases due to inability to reflect user-specific characteristics
Solution Approach 1:
The system applies local quality by using user-specific fingerprint characteristics and patterns stored in the template database to evaluate each fingerprint image. Instead of a generic model, the ASP module compares the input image against the specific user's registered patterns, enabling accurate detection of forged fingerprints while maintaining system simplicity through efficient template matching.
Solution Approach 2:
The system performs partial classification by focusing on key discriminative features of fingerprint images rather than analyzing every detail. The ASP module extracts and compares critical local patterns (such as ridge endings, bifurcations, and mineral points) to detect forgery, achieving high accuracy without requiring excessive computational complexity.
Data Source
AI summary
An electronic device is provided. The electronic device includes a sensor, memory configured to store plurality of fingerprint templates, each of the plurality of fingerprint templates is an embedding vector indicating each of plurality of registered fingerprint images, and at least one computer program, and at least one processor communicatively coupled to the sensor and the memory, wherein the plurality of registered fingerprint images comprises a forged fingerprint image made by forging a fingerprint of a user, an abnormal state fingerprint image comprising an obstacle obstructing fingerprint authentication, and a normal state fingerprint image which is either a successfully registered fingerprint image or a fingerprint image matching the successfully registered fingerprint image, and wherein the at least one computer program includes instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to acquire, using the sensor, an input fingerprint image indicating a fingerprint image input by the user, identify whether the input fingerprint image matches at least a part of the plurality of registered fingerprint images based on the plurality of fingerprint templates, in case that the input fingerprint image matches the at least a part of the plurality of registered fingerprint images, generate at least one virtual fingerprint image, based on the input fingerprint image matching the at least a part of the plurality of registered fingerprint images, store a template of the input fingerprint image and at least one template of the at least one virtual fingerprint image in the plurality of fingerprint templates, and train a fingerprint generation artificial intelligence model to generate a fingerprint image similar to the at least one virtual fingerprint image or the input fingerprint image.