Photo Sharing User Subset Selection for Faster Face Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack an efficient method for identifying and sharing digital media with users present in photographs based on facial recognition, particularly in crowded environments, leading to inefficiencies in processing and accuracy.
Innovation Solution
A computing system that utilizes facial recognition and data attributes such as Bluetooth IDs, GPS trails, and Wi-Fi network IDs to determine a subset of users from a complete set, reducing processing time by creating a subset based on proximity and shared network connections, and facilitating seamless sharing of photographs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If facial recognition is performed on the complete set of user equipment, then identification accuracy is improved, but processing time increases significantly
Solution Approach 1:
The patent divides the complete set of user equipment into two segments: a first subset determined by comparing data attributes (GPS trails, Bluetooth IDs, Wi-Fi network IDs) and a second subset determined by performing facial recognition algorithms. This segmentation allows the system to first filter users based on proximity and shared network connections, then apply computationally intensive facial recognition only to the filtered subset, thereby reducing overall processing time while maintaining identification accuracy
Solution Approach 2:
The patent performs preliminary filtering of user equipment by comparing data attributes such as GPS trails, Bluetooth IDs, and Wi-Fi network IDs before conducting facial recognition. This preliminary action identifies a first subset of user equipment that shares common attributes with the capturing device, narrowing down the candidates before the more time-consuming facial recognition process is applied to the second subset
2Reliability
If facial recognition is performed on all users, then identification completeness is improved, but computational complexity increases
Solution Approach 1:
The patent segments the identification process into two distinct phases: first, filtering user equipment based on data attribute comparison (GPS trails, Bluetooth IDs, Wi-Fi network IDs) to create a first subset; second, applying facial recognition algorithms only to the second subset derived from the first subset. This segmentation reduces computational complexity by avoiding unnecessary facial recognition comparisons while maintaining identification completeness through the multi-stage filtering approach
3Measurement precision
If data attributes are collected continuously, then user identification accuracy is improved, but data transmission volume increases
Solution Approach 1:
The patent extracts and utilizes specific key data attributes (GPS trails, Bluetooth IDs, Wi-Fi network IDs) from the continuous data stream collected by user equipment. By selecting only these relevant attributes for comparison and transmission to the server, the system achieves accurate user identification without transmitting the entire continuous data stream, thereby reducing data transmission volume while maintaining identification accuracy
Data Source
AI summary
Methods, systems, and devices for determining a subset of users from among a set of users based on a set of received information associated with a photograph, where the disposition of the information is used to first determine the subset and then perform facial recognition on the subset of photographs for each user in order to accurately identify each user or users present in the photograph.