Facial Image Screening via Multi-Parameter Quality Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current face recognition systems face reduced recognition rates due to facial images being obstructed by shelters or experiencing expression changes, as existing methods rely heavily on face pose information for image selection.
Innovation Solution
A facial image screening method that tracks feature points, analyzes image quality, face pose, and blocking degree information to generate a comprehensive quality score, determining suitability for comparison based on these scores and a threshold value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If face pose information is used as the sole condition for screening facial images, then the screening process is simple and fast, but the recognition rate decreases when faces are blocked or have expression changes
Solution Approach 1:
The patent segments the facial image quality assessment into multiple independent components: face pose information, blocking degree information, and expression change information. Each component is evaluated separately through dedicated modules, allowing comprehensive quality assessment without requiring a single complex screening mechanism. This segmentation enables the system to independently evaluate different aspects of face quality and combine them for final recognition decisions.
Solution Approach 2:
The screening module is designed to perform multiple functions simultaneously: it evaluates face pose, detects blocking objects, analyzes expression changes, and integrates these assessments into a comprehensive quality score. This multi-functional approach allows the same module to handle various quality aspects that would otherwise require separate systems, improving recognition reliability while controlling complexity.
2Reliability
If multiple quality parameters are analyzed for facial image screening, then the recognition rate improves, but the computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary quality assessment of facial images before they enter the main recognition pipeline. The screening module evaluates multiple quality parameters (pose, blocking, expressions) in advance and filters out low-quality images before feature extraction and comparison. This preliminary action prevents wasteful processing of unsuitable images, reducing overall processing time while maintaining high recognition rates for qualified images.
Solution Approach 2:
Different regions of the facial image are analyzed with different quality criteria. The system evaluates specific facial regions for blocking, assesses local expression changes in relevant areas, and weights different quality parameters differently based on their importance for recognition. This local quality assessment allows efficient processing by focusing computational resources on critical regions rather than uniformly processing the entire image.
Data Source
AI summary
A facial image screening method is provided in the present disclosure. The facial image screening method includes the following steps: tracking a plurality of feature points of at least one facial image; analyzing each feature point to acquire a region information corresponding to each feature point, wherein the region information comprises an image quality information, a face pose information, and a blocking degree information; scoring the image quality information to obtain a first arbitration score; scoring the face pose information to obtain a second arbitration score; scoring the blocking degree information to obtain a third arbitration score; generating a comprehensive quality score according to the first arbitration score, the second arbitration score, and the third arbitration; and taking the plurality of feature points of the facial image as targets to be compared with captured features of a plurality of specific persons when the comprehensive quality score exceeds a threshold value. The present disclosure has an advantage that a facial image suitable for face comparison may be selected so as to improve the recognition rate of one-to-one or one-to-many comparison.