Identity Recognition Using Bodyprints for Non-Facial Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing identity recognition systems face challenges in accurately recognizing individuals when facial recognition is not possible, such as when a person is facing away from the camera or in poor image quality.
Innovation Solution
The system uses physical characteristics associated with a person's body, such as their torso, clothing, and gait, to create a 'bodyprint' that can be used for identity recognition, even when facial recognition is not feasible.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If facial recognition is used for identity recognition, then recognition accuracy is improved when the face is visible, but recognition capability deteriorates when the person is facing away from the camera or in poor image quality
Solution Approach 1:
The patent segments the body into multiple regions of interest including the face, torso, and limbs. By analyzing different body segments independently, the system can recognize individuals even when one segment (the face) is not visible or recognizable, thus resolving the contradiction between facial recognition accuracy and adaptability to various scenarios.
Solution Approach 2:
The patent creates a multi-functional recognition system that can operate using facial characteristics, torso characteristics, or a combination of both. This universal approach allows the system to maintain high recognition accuracy across diverse scenarios including when the person is facing away from the camera, thereby improving both precision and adaptability.
2Ease of manufacture
If only facial characteristics are analyzed, then the system is simple to implement, but it fails to recognize individuals when the face is not visible
Solution Approach 1:
The patent merges facial characteristic analysis with torso characteristic analysis into a unified recognition system. By combining multiple data sources (face and torso), the system achieves reliable recognition in all scenarios while maintaining reasonable implementation complexity through integrated processing architecture.
Solution Approach 2:
The patent introduces body characteristics as an intermediary data source that complements facial characteristics. When facial recognition fails due to the person facing away or poor image quality, the torso characteristics serve as a mediator to enable reliable identification, thus improving system reliability without significantly complicating the overall implementation.
3Adaptability or versatility
If body characteristics are used for recognition, then recognition capability is improved when the face is not visible, but the complexity of the system increases
Solution Approach 1:
The patent segments the body into distinct regions (face, torso, limbs) and analyzes each segment using dedicated algorithms. This segmentation approach enables the system to handle various recognition scenarios effectively while managing complexity through modular processing of different body parts, making the overall system more adaptable without proportionally increasing complexity.
Solution Approach 2:
The patent applies partial action by focusing analysis on specific body regions (particularly the torso) rather than the entire body. This selective approach improves recognition capability in scenarios where the face is not visible while minimizing the increase in system complexity by concentrating computational resources on the most informative body parts.
Data Source
AI summary
Techniques are disclosed for providing a notification indicating an identity of a first person based on face-associated body characteristics. For example, a device performs facial recognition to identify the identity of the first person shown in a first video feed. The device also identifies and stores physical characteristic information of the first person from the first video feed, the stored information associated with the identity of the first person based on the recognized face. Subsequently, the device receives a second video feed showing a second person whose face is determined to not be recognized by the device. The device compares the stored physical characteristic information of the first person with additional physical characteristic information of the second person shown in the second video feed. Based on the comparison, the device provides a notification indicating whether the identity of the second person corresponds to the identity of the first person.