Wide-Angle Camera Subject Distortion Analysis for Spoofing Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing face recognition technologies struggle to accurately differentiate between real faces and spoofed faces, particularly when using two-dimensional images like face photographs.

Innovation Solution

An information processing apparatus that specifies distortion in a subject's image based on position and direction information, and identifies the subject's shape from this distortion, using a wide-angle camera to capture images that highlight the differences in wide-angle distortion between real faces and plane-projected faces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If face recognition is performed using conventional two-dimensional image processing, then the recognition process is simple and fast, but the accuracy is insufficient and spoofing cannot be prevented

Engineering Contradiction:

Improvesubject recognition accuracyVSAvoidimage processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transitions from two-dimensional image processing to three-dimensional shape analysis by specifying distortion based on position information and direction information. This dimensional change enables accurate differentiation between real faces and spoofed faces by analyzing the three-dimensional characteristics of facial features.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent changes the processing parameters from conventional two-dimensional coordinates to three-dimensional distortion parameters. By specifying distortion using position information (x, y coordinates) and direction information (angular information), the system achieves more accurate subject recognition while maintaining computational feasibility.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If a wide-angle camera is used to capture images for distortion analysis, then the ability to detect spoofing is improved, but the image distortion increases

Engineering Contradiction:

Improvespoofing detection reliabilityVSAvoidimage geometric accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent converts the harmful effect of wide-angle distortion into a beneficial feature for spoofing detection. By analyzing the distortion patterns created by the wide-angle camera, the system can differentiate between real faces and spoofed faces, as the distortion characteristics differ between genuine three-dimensional faces and two-dimensional representations.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent changes the approach from correcting wide-angle distortion to utilizing it as a detection feature. By specifying distortion based on position and direction information, the system transforms the geometric inaccuracy into a reliable indicator for identifying spoofed subjects.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12307810B2Information processing apparatus, information processing method, and information processing system

Publication Date: 2025.05.20 SONY SEMICON SOLUTIONS CORP

AI summary

Provided is an information processing apparatus, an information processing method, and an information processing system that can more accurately recognize a subject. The information processing apparatus includes a processing unit that specifies a distortion of a subject on the basis of position information indicating a position of the subject included in a captured image and direction information indicating a direction of the subject, and identifies a shape of the subject on the basis of the specified distortion of the subject.