Glasses Detection via Nose Bridge Image Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing glasses detection methods in facial recognition systems are inefficient due to high computational complexity and manpower costs, particularly when dealing with images of individuals wearing glasses, which reduces accuracy.
Innovation Solution
A method and apparatus that detect glasses in a face image by analyzing changes in the nose bridge region using a gradient algorithm, reducing the need for extensive sample collection and model training, and enabling quick and accurate detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a monitoring-based machine learning algorithm is used for glasses detection, then detection accuracy can be improved, but computational complexity and manpower costs increase significantly
Solution Approach 1:
The patent extracts and focuses on a specific local region (nose bridge region) from the entire face image for glasses detection. By isolating this critical area where glasses leave the most significant imprint, the method avoids the need for complex full-face analysis while maintaining high detection accuracy. This extraction approach directly reduces computational complexity by limiting processing to a small, targeted region rather than the entire image.
Solution Approach 2:
The patent segments the face image into multiple regions and specifically analyzes the nose bridge region for glasses detection. This segmentation strategy divides the complex task of full-face analysis into simpler sub-tasks, where only the nose bridge region needs detailed examination. The segmentation enables efficient detection by focusing computational resources on the most informative area, thereby reducing overall computational complexity while preserving detection accuracy.
2Measurement precision
If a monitoring-based machine learning algorithm is used for glasses detection, then detection accuracy can be improved, but manpower costs increase due to extensive sample collection and model training
Solution Approach 1:
The patent performs preliminary localization of the nose bridge region before conducting detailed glasses detection analysis. By pre-identifying and marking the nose bridge region in advance, the method avoids the need for extensive sample collection and model training required by traditional machine learning approaches. This preliminary action enables direct analysis of the target region using simpler algorithms, significantly reducing manpower costs and time investment while maintaining high detection accuracy.
3Reliability
If the entire face image is analyzed for glasses detection, then comprehensive detection can be achieved, but processing time and computational resources increase
Solution Approach 1:
The patent applies local quality analysis by focusing detection efforts specifically on the nose bridge region rather than uniformly analyzing the entire face image. The nose bridge region exhibits distinctive local characteristics when glasses are present, and by concentrating analysis on this specific area with appropriate local processing techniques, the method achieves reliable detection results. This local quality approach maintains detection comprehensiveness for glasses while dramatically improving processing efficiency by avoiding unnecessary analysis of other face regions.
Data Source
AI summary
This application discloses a method and a terminal for detecting glasses in a face image. The method includes: obtaining a face image; determining a nose bridge region in the face image; detecting an image change in the nose bridge region to obtain an image change result of the nose bridge region; and determining whether there are glasses in the face image according to the image change result of the nose bridge region. The terminal for detecting glasses in a face image matches the method.