Face Image Grouping via Representative Image Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques face difficulties in efficiently grouping face images of the same person captured with different cameras or from frames where the person has been framed in and out, using object tracking techniques.
Innovation Solution
A processing apparatus and method that determine similarity scores between representative face images from different face image groups to associate the same person identifier with face images, ensuring the groups meet specific similarity conditions within each group.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If object tracking technique is used to group face images, then face images captured with the same camera can be grouped efficiently, but face images captured with differing cameras or with framing changes cannot be grouped
Solution Approach 1:
The patent introduces a representative face image as an intermediary element to bridge different face image groups. By selecting a representative face image from each group and comparing similarity scores between representatives, the system enables grouping across different cameras and framing conditions without relying solely on direct tracking between individual face images.
Solution Approach 2:
The patent segments the face image grouping process into two independent determination steps: inter-face-image-group determination (comparing representative images between groups) and intra-face-image-group determination (verifying relationships within groups). This segmentation allows each step to focus on specific aspects, improving overall robustness and adaptability.
2Productivity
If face image grouping is performed without verification conditions, then processing is faster, but grouping accuracy deteriorates
Solution Approach 1:
The patent performs preliminary determination of representative face images and their similarity scores before final grouping. By pre-computing inter-group similarity metrics and establishing representative images in advance, the system can quickly verify grouping accuracy without re-processing all face images, thus maintaining both speed and precision.
Solution Approach 2:
The patent implements feedback mechanisms through two determination steps that verify grouping conditions. The inter-face-image-group determination checks similarity between representatives, while the intra-face-image-group determination validates relationships within groups. This feedback loop ensures accuracy by verifying assumptions about face image relationships.
Data Source
AI summary
The present invention provides a processing apparatus (10) including an inter-face-image-group determination unit (11) that determines whether a similarity score between a first representative face image in a first face image group and a second representative face image in a second face image group satisfies a first condition, an intra-face-image-group determination unit (12) that determines, for each of the first face image group and the second face image group, whether a second condition defining a relationship between the representative face image and another image in the face image group is satisfied, based on a similarity score between the first representative face image and each of other face images in the first face image group and a similarity score between the second representative face image and each of other face images in the second face image group, and a processing unit (13) that associates a same person identifier (ID) with a plurality of face images included in the first face image group and the second face image group when it is determined that the first condition is satisfied and that the first face image group and the second face image group each satisfy the second condition.