Face Recognition Apparatus Dynamic Resolution Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional face recognition systems face challenges in maintaining high authentication accuracy due to varying face sizes and resolutions in video data captured by monitoring cameras, leading to degraded recognition performance when face regions have low resolution or are not oriented frontally.
Innovation Solution
A face recognizing apparatus that selects appropriate face feature point detecting techniques based on the size of the face region, using a combination of techniques such as first, second, and third face feature point detecting methods to adapt to different resolutions and orientations, and performs detection result corrections to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-resolution recognition technique is used, then recognition accuracy is improved when face resolution is high, but recognition accuracy deteriorates when face resolution is low
Solution Approach 1:
The system dynamically switches between high-resolution recognition technique and low-resolution recognition technique based on the detected face region resolution. When the face region has high resolution, the high-resolution technique is applied; when the face region has low resolution, the low-resolution technique is applied. This dynamic adaptation resolves the contradiction by making the recognition system flexible rather than fixed.
Solution Approach 2:
The system changes the recognition parameter (resolution requirement) based on the input face region characteristics. By detecting the resolution level of the face region first, the system adjusts which recognition technique to use, thereby maintaining recognition accuracy across varying resolution conditions.
2Area of stationary object
If monitoring camera is installed in a high place to capture wide area, then coverage area is improved, but face resolution and frontality deteriorate
Solution Approach 1:
The system dynamically adapts the recognition technique based on the actual face region quality captured from the high-place monitoring camera. By detecting whether the face region meets the resolution and frontality requirements, the system switches between recognition techniques appropriately, resolving the contradiction between wide coverage and high resolution.
Solution Approach 2:
The system applies different recognition techniques to different local conditions (face region qualities). Instead of using a single technique for the entire coverage area, it evaluates each detected face region individually and applies the appropriate technique based on its specific resolution and orientation characteristics.
3Adaptability or versatility
If multiple face feature point detecting techniques are combined to handle various resolutions, then adaptability is improved, but system complexity increases
Solution Approach 1:
The system segments the recognition process into distinct stages: face region detection, resolution evaluation, technique selection, and recognition execution. By dividing the overall process into manageable segments with clear decision points, the system manages complexity while maintaining adaptability across different resolution conditions.
Data Source
AI summary
According to one embodiment, a face recognizing apparatus includes: a storage unit; an input unit; a face detector; an extractor; and a recognizing unit. The storage unit stores face feature information on a face feature of each person. The input unit receives image information including at least a face of a person. The face detector detects a face region of the face of the person from the image information received by the input unit. The extractor extracts face feature information on a face feature from the face region detected by the face detector. The recognizing unit recognizes the person in the image information received by the input unit based on the feature information extracted by the extracting unit and the face feature information stored in the storage unit.