Signature Smoothing Algorithm for Mobile Payment Fraud Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Touch screen devices used for signature capture often capture a low number of input points per unit of time, resulting in blocky or jagged signatures that are unrecognizable and unsuitable for fraud detection or business purposes.
Innovation Solution
An HTML5 application is used to capture and smooth signatures by processing input points, generating a Bezier curve between midway points to create a more representative signature, which can be stored and used for payment processing, fraud detection, and authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If touch screen devices capture signatures at low input points per second, then device simplicity is maintained, but signature quality becomes blocky or jagged and unrecognizable
Solution Approach 1:
The patent applies curve smoothing algorithms (such as Bezier curves or cubic splines) to transform the blocky, jagged signature points into smooth continuous curves. This principle converts the discrete, angular input points into a rounded, flowing representation that matches natural signature characteristics, resolving the contradiction between simple capture and high quality output.
Solution Approach 2:
The patent modifies parameters of the captured signature data by applying mathematical transformations including smoothing algorithms, scaling adjustments, and normalization. These parameter changes enhance the visual quality and recognizability of signatures captured at low sampling rates without requiring more complex hardware.
2Manufacturing precision
If touch screen devices capture more input points per second, then signature smoothness improves, but device complexity and processing requirements increase
Solution Approach 1:
The patent implements selective smoothing where only portions of the signature trajectory requiring correction are processed with intensive algorithms, while other segments use simpler interpolation. This partial application of complex processing reduces overall computational burden while maintaining sufficient smoothness for recognizability.
Solution Approach 2:
The signature smoothing is performed automatically by the device's processing system without requiring additional hardware components or manual intervention. The existing processor and software framework handle the smoothing operations, making the system self-sufficient and avoiding increased device complexity.
3Productivity
If blocky or jagged signatures are displayed to customers, then capture speed is maintained, but customer confusion and fraud detection reliability decrease
Solution Approach 1:
The patent applies smoothing algorithms immediately after signature capture, before the signature is displayed to the customer or stored for fraud detection. This preliminary processing ensures that the signature is already in its optimized, recognizable form, preventing customer confusion and ensuring reliability without delaying the capture process.
Solution Approach 2:
The patent introduces a software-based smoothing layer as an intermediary between the raw capture data and the final signature representation. This intermediary processing layer transforms the blocky input points into smooth curves, mediating between the fast capture mechanism and the quality requirements for fraud detection.
Data Source
AI summary
A mobile device renders a page that receives input points on a signature provided in conjunction with a mobile payment transaction. The page applies a smoothing algorithm to smooth the input points and create a signature file that more truly represents the actual input signature. The signature file and/or the input points are provided to a payment facilitator for use in completing the mobile payment transaction, performing fraud detection, and potentially for other purposes. Mechanisms are also disclosed for authenticating a buyer device in conjunction with a mobile payment transaction.