Single-Image Face And Hand Detection to Reduce Subject Burden

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing biometric identification systems require subjects to attend to multiple photographing apparatuses, causing discomfort and burden.

Innovation Solution

A detection system that integrates face and hand detection units to capture biometric information from a single image, reducing the need for subjects to focus on multiple devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple photographing apparatuses are used to capture face and fingerprint images, then biometric information can be acquired, but the subject feels troubled due to needing to pay attention to multiple devices

Engineering Contradiction:

Improvebiometric information acquisitionVSAvoidsubject burden

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent combines multiple photographing apparatuses (face camera and fingerprint camera) into a single integrated imaging system. The image generation unit processes a single captured image to extract both face region data and fingerprint data, eliminating the need for separate photographing devices and reducing subject burden while maintaining biometric acquisition reliability.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The single photographing apparatus is designed to perform multiple functions: capturing both face images and fingerprint images simultaneously. The image generation unit universally processes the captured image to generate various biometric data types, making one device serve multiple purposes that previously required separate specialized devices.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Ease of operation

If a single image is used for both face and hand detection, then the subject burden is reduced, but the detection precision may be compromised

Engineering Contradiction:

Improvesubject burdenVSAvoidbiometric detection accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments the single captured image into distinct functional regions: a face region extracted by face recognition and a hand region extracted by hand recognition. This segmentation allows independent processing and analysis of each biometric feature, maintaining detection precision for both face and hand while using only a single photographing apparatus.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies different processing qualities and methods to different regions of the single image. The face region undergoes face-specific recognition processing while the hand region undergoes hand-specific recognition processing. Each region is optimized for its specific detection purpose, ensuring high precision for both biometric modalities from a single image capture.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20250310636A1Detection system, detection method, and non-transitory computer readable medium

Publication Date: 2025.10.02 NEC CORP

AI summary

A detection system according to an aspect of the present disclosure includes a face detection means, an area setting unit, a hand detection unit, and an output unit. The face detection means is configured to detect a face of a subject from an image obtained by photographing the subject. The area setting unit is configured to set, in a case where the face detection means has detected the face of the subject, a hand detection area around an area including the face of the subject. The hand detection unit is configured to detect a hand present in the hand detection area from the image obtained by photographing the subject. The output unit is configured to output information about the face of the subject detected by the face detection means and information about the hand of the subject detected by the hand detection unit.