Edge Detection for Self-Service Terminal Manipulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting manipulation attempts at self-service terminals, such as automated teller machines, are costly and complex, making it difficult to implement reliable and fully automated image evaluation for identifying skimming devices and other manipulations.
Innovation Solution
The method involves edge detection of camera image data to create edge images, which are then evaluated using reference edge images through XOR and AND operations, reducing data complexity and increasing speed and reliability, allowing for efficient detection of manipulated elements like keypad overlays and spy cameras.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If full automated image evaluation is implemented to detect manipulation attempts, then detection reliability is improved, but hardware and software complexity increases
Solution Approach 1:
The patent segments the image processing task by first creating edge images from the captured images, then comparing these edge images with reference edge images. This segmentation of the processing task reduces the complexity of full automated evaluation while maintaining detection reliability, as edge detection simplifies the image data to essential features for manipulation detection.
2Difficulty of detecting and measuring
If camera monitoring with image capture is used to detect manipulation attempts, then detection capability is improved, but data processing complexity and costs increase
Solution Approach 1:
The patent extracts only the essential information needed for manipulation detection by creating edge images from the captured images. Instead of processing and analyzing entire images, the system extracts edge information which contains the critical features for detecting foreign objects, thereby reducing data processing complexity and computational costs while maintaining detection capability.
3Productivity
If edge detection is used to process image data, then data processing speed is improved, but measurement precision may be affected
Solution Approach 1:
The patent applies local quality by comparing edge images with reference edge images to identify local deviations that indicate manipulation attempts. This approach maintains measurement precision by focusing on specific edge features and their comparison with known good references, rather than requiring perfect global edge detection accuracy, thus enabling fast processing with sufficient precision for security applications.
Data Source
AI summary
A method (100) is proposed for recognizing attempts at manipulating a self-service terminal, specifically a cash dispenser, in which a control panel with elements arranged therein, such as a keypad, cash-dispensing slot, etc. is provided, wherein a camera is directed onto at least one of the elements and wherein the image data generated by the camera are evaluated. Using edge detection, at least one edge image is created from the image data generated (step sequence 120). The edge image is evaluated using a reference edge image (step sequence 130). To generate the reference edge image, several individual images are used (step sequence 110). Fully automated evaluation and recognition of manipulation attempts is possible using edge detection.