In-Screen Fingerprint Recognition via AI Image Restoration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The success rate of in-screen fingerprint recognition is reduced due to the application of screen protectors, which increase the distance between the fingerprint sensor and the user's finger, affecting the quality of the fingerprint image captured.
Innovation Solution
An electronic device method that uses AI restoration models to improve the quality of fingerprint images by determining if a screen protector is present and applying appropriate image restoration techniques to enhance image quality for successful recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Strength
If a screen protector is applied to protect the touch screen, then the touch screen protection is improved, but the distance between the fingerprint sensor and user finger increases, reducing fingerprint image quality
Solution Approach 1:
The patent converts the harmful effect of the screen protector (reducing fingerprint image quality) into a beneficial solution by training an AI model to recognize screen protector states and restore fingerprint images. The system learns from degraded images captured through screen protectors and generates restored images with quality comparable to or better than images captured without screen protectors, thus converting the previously harmful condition into an acceptable operating state.
Solution Approach 2:
The patent changes the parameters of the fingerprint image through AI restoration. The AI model adjusts image parameters such as clarity, contrast, and detail preservation to compensate for the degradation caused by the screen protector. This parameter transformation allows the system to maintain high-quality fingerprint recognition even when images are captured through protective films.
2Area of stationary object
If the distance between the fingerprint sensor and user finger increases due to screen protector, then the screen protector coverage is improved, but the fingerprint image sharpness and completeness deteriorate
Solution Approach 1:
The system converts the degraded fingerprint images (caused by increased distance through screen protector) into restorable data by training an AI model on pairs of degraded and reference images. The model learns the transformation patterns and can generate sharp, complete fingerprint images from degraded inputs, thus benefiting from the wider coverage while maintaining precision.
Solution Approach 2:
The AI model creates a copy or reconstruction of the ideal fingerprint image based on the degraded input. By learning from training data that includes both degraded and reference images, the model can generate a high-quality copy of the fingerprint pattern even when the original captured image is blurred or incomplete due to the screen protector distance.
3Device complexity
If traditional fingerprint recognition is used without AI restoration, then the system complexity is reduced, but the fingerprint recognition success rate decreases
Solution Approach 1:
The patent replaces traditional mechanical/image processing fingerprint recognition methods with an AI-based restoration system. Instead of using conventional image enhancement techniques, the system employs deep learning models that automatically learn and apply restoration transformations, achieving higher reliability while managing complexity through integrated AI processing.
Solution Approach 2:
The system performs preliminary action by pre-training the AI model with large datasets of fingerprint images (including degraded and reference pairs) before actual use. This preliminary training enables the model to automatically restore fingerprint images during recognition without requiring complex real-time processing, thus improving success rate while keeping the operational system relatively simple.
Data Source
AI summary
A fingerprint recognition method and an electronic device. The electronic device includes a touch screen and a fingerprint sensor. The electronic device displays a first interface and captures first fingerprint information that is input by a user at the first interface. The electronic device determines whether the touch screen is in a first state, and the first state is used to indicate that the touch screen is in a screen protector state. If the touch screen is in the first state, the electronic device restores the first fingerprint information by using a first preset artificial intelligence (AI) restoration model to obtain second fingerprint information. The electronic device determines that the second fingerprint information matches preset fingerprint information and displays a second interface. Quality of a fingerprint image in the second fingerprint information is higher than quality of a fingerprint image in the first fingerprint information.