Display Luminance Control for Facial Recognition Lighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current face image recognition technologies face challenges in improving the success rate due to inadequate lighting conditions, which affect the quality of captured face images, leading to unqualified data sources and reduced recognition accuracy.
Innovation Solution
A face image processing method that enhances the luminance of the display on an electronic device when the collected face image's brightness is below a preset threshold, re-collects the image, and performs facial recognition only when the adjusted image meets the required luminance range, while also prompting users to adjust lighting conditions if the image is too bright.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If face image recognition is performed under existing lighting conditions, then the recognition process can be executed, but the success rate is low due to inadequate lighting causing unqualified data sources
Solution Approach 1:
The system performs preliminary detection of lighting conditions before executing face image recognition. When insufficient lighting is detected, the system preemptively adjusts display luminance to illuminate the face area before the recognition process begins, ensuring qualified image data is captured from the start
Solution Approach 2:
The electronic device uses its own display screen as a lighting source to illuminate the face area. By adjusting the display luminance to a target value, the device serves itself by providing the necessary lighting conditions for its own face image recognition function without requiring external lighting equipment
2Manufacturing precision
If the display luminance is enhanced to improve face image brightness, then the image quality improves, but energy consumption increases
Solution Approach 1:
The system applies partial action by adjusting display luminance only in the specific face image capture area rather than uniformly increasing overall device brightness. The display luminance is enhanced to a target value sufficient for recognition quality, avoiding excessive energy consumption by limiting the adjustment to the minimum necessary level
Solution Approach 2:
The system dynamically changes the display luminance parameter from its normal operating value to a target luminance value when face image capture is required. This parameter adjustment is conditional and temporary, changing only when lighting conditions are insufficient and only for the duration needed to capture qualified images
3Measurement precision
If multiple face images are re-collected to achieve adequate brightness, then recognition accuracy improves, but the operation time increases
Solution Approach 1:
The system performs preliminary adjustment of display luminance before face image re-collection. By pre-illuminating the face area and ensuring adequate lighting conditions before the next image capture attempt, the system reduces the number of retry cycles needed, thereby minimizing time loss while achieving recognition accuracy
Data Source
AI summary
The present disclosure provides technical solutions for improving facial image capturing, recognition, and authentication, including: collecting a face image in response to a facial scan instruction (e.g., for facial recognition) using a camera of a mobile terminal; calculating a measure of image brightness (e.g., a luminance value) of the collected face image; enhancing, when a value of the measure of image brightness of the collected face image is less than a first preset threshold, luminance of light that is emitted from a display of the mobile terminal to a target luminance value, and re-collecting a face image using the camera of the mobile terminal and calculating a corresponding value of the measure of image brightness for the re-collected face image; and performing, when the value of the measure of image brightness of the re-collected face image falls within a preset value range, facial recognition based on the re-collected face image.