Person Identification Using Physique Features When Faces Are Obscured
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing systems fail to identify individuals in original images when their faces are not visible or of poor quality, as they rely solely on face recognition, limiting the ability to recognize persons from images where facial features cannot be captured.
Innovation Solution
An information processing apparatus and method that collates feature information from a person in an original image with retrieval target information, extracts secondary feature information when a match is found, and stores it for identification, using a combination of a collation unit, extraction unit, and registration unit to identify individuals based on physique and other recognizable features even when faces are not visible.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If face recognition is used for person identification, then identification accuracy is improved when faces are visible, but identification capability deteriorates when faces are not visible or of poor quality
Solution Approach 1:
The system changes the parameters used for identification from face-only features to multiple alternative features including physique, height, weight, and other body characteristics. When face recognition parameters are unavailable or insufficient, the system switches to using these alternative parameters for person identification, thereby maintaining identification capability across different scenarios.
Solution Approach 2:
The identification system is segmented into multiple independent feature extraction modules: face feature extraction, physique feature extraction, and other body feature extraction. This segmentation allows the system to independently evaluate and combine different feature types, enabling identification through alternative features when face recognition fails.
2Speed
If only face feature information is extracted for identification, then processing speed is improved, but identification reliability deteriorates when face images are unavailable
Solution Approach 1:
The system performs preliminary extraction of multiple types of feature information (face features, physique features, body measurements) during the initial image processing stage. By preparing these alternative features in advance, the system ensures that identification can proceed reliably using pre-extracted data when face images are unavailable, without requiring additional processing time later.
3Reliability
If multiple types of feature information are extracted and stored, then identification reliability is improved, but data storage requirements and processing complexity increase
Solution Approach 1:
The system designs a universal feature storage structure that can accommodate multiple types of features (face features, physique features, body measurements) in a unified format. This multi-functional storage system allows the same data structure to serve different identification purposes, reducing overall system complexity despite handling diverse feature types.
Data Source
AI summary
An information processing apparatus (100) includes a collation unit (102) that collates first feature information extracted from a person included in a first image (10) with first feature information indicating a feature of a retrieval target person, an extraction unit (104) that extracts second feature information from the person included in the first image in a case where a collation result in the collation unit (102) indicates a match, and a registration unit (106) that stores, in a second feature information storage unit (110), the second feature information extracted from the person included in the first image.