Spoofing Detection via Aperture-Induced Focus Differences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing surveillance and physical access control systems face challenges in efficiently detecting spoofing attempts, particularly as they often require complex methods and varifocal cameras, limiting their effectiveness and simplicity.
Innovation Solution
A method and system that capture images with different aperture sizes to calculate focus differences between protrusion and recess areas of a face, determining if the object is fake by comparing these differences against a threshold, which can be implemented in both varifocal and fixed focus cameras, reducing complexity and avoiding the need for focus motor operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If complex liveness detection methods are used to detect spoofing attempts, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent changes the parameter being measured from focus distance to aperture size. By capturing images at different aperture sizes (e.g., f/2.8 and f/8.0) while maintaining fixed focus, the system creates different depth of field conditions that reveal whether the subject is 2D or 3D. This parameter substitution simplifies the device while maintaining detection accuracy.
Solution Approach 2:
The patent replaces the mechanical focus motor system with an aperture control mechanism. Instead of mechanically moving the focus lens to create focus sweeps, the system uses aperture blades to change the depth of field. This substitution eliminates the need for focus motor operation during detection, reducing mechanical complexity while achieving the same liveness detection goal.
2Reliability
If focus sweep methods are used to detect liveness, then spoofing detection capability is improved, but loss of focus occurs requiring refocusing
Solution Approach 1:
The patent performs the aperture change action immediately after image capture without requiring refocusing. By capturing the first image at a first aperture size and then changing to a second aperture size for the second image, the system completes the detection sequence without intermediate refocusing steps. The focus remains predetermined throughout, eliminating time loss.
3Measurement precision
If varifocal cameras are used for liveness detection, then detection precision is improved, but adaptability to fixed focus cameras is reduced
Solution Approach 1:
The patent makes the liveness detection system universal by using aperture size as the controlling parameter instead of focus distance. Since aperture mechanisms exist in both varifocal and fixed focus cameras, the detection method becomes compatible with both camera types. The system achieves multi-functionality by detecting spoofing attempts across different camera configurations using the same aperture-based approach.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for effective detection of spoofing attempts in a straightforward manner, applicable to both varifocal and fixed focus cameras, enhancing security without significant complexity or loss of focus, and reducing the risk of false alarms.
Implementation Method 1
capturing a first image by the camera, using a first focus setting and a first aperture size... capturing a second image by the camera, using the first focus setting and a second aperture size which is different from the first aperture size
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method is disclosed for detecting if an object detected in a surveillance or access control system is fake. A first image is captured (S1) by the camera, using a first focus setting and a first aperture size. The object is detected (S2) in the first image. A first protrusion focus measure in a protrusion area of the object in the first image and a first recess focus measure in a recess area of the object in the first image are determined (S3a, S3b). A second image is captured (S4) by the camera, using the first focus setting and a second aperture size. The object is detected (S5) in the second image. A second protrusion focus measure and a second recess focus measure are determined in the second image (S6a, S6b). A protrusion focus difference between the first and second protrusion focus measures, and a recess focus difference between the first and second recess focus measures are calculated (S7a, S7b). The protrusion focus difference and the recess focus difference are compared (S8) and if they differ by less than a predetermined threshold amount, it is determined (S9) that the object is fake.