Machine-Learning Image Processing for Remote Check Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing remote deposit capture systems face challenges in verifying the authenticity of checks and users, particularly in diverse environmental and hardware conditions, and struggle with validating document security features and user identity, often leading to inefficiencies and security concerns.
Innovation Solution
A computing system that utilizes a machine-learning architecture to process image data from client devices, detecting documents like checks, extracting information, and validating authenticity through object recognition engines, bounding boxes, and dynamic alignment indicators, while generating risk scores and prompts for additional verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If remote deposit capture is implemented to eliminate manual processes and travel, then productivity and convenience are improved, but verification of user identity and check authenticity becomes more difficult
Solution Approach 1:
The system performs preliminary actions by capturing a video feed of the check and user before processing the deposit. The video feed includes multiple frames that are analyzed in advance to verify authenticity, extract information, and assess risk factors before the deposit is finalized, enabling remote verification without manual inspection
Solution Approach 2:
The patent introduces an intermediary processing system that acts as a mediator between the user and the financial institution. This system uses video feed analysis, machine learning models, and risk assessment algorithms to verify authenticity and extract information, replacing the need for direct human inspection while maintaining security
2Measurement precision
If detailed instructions are provided to users for remote deposit capture, then verification accuracy may improve, but user convenience decreases
Solution Approach 1:
The system enables self-service by allowing users to capture and submit check images independently through their devices. The automated processing system handles verification, information extraction, and risk assessment without requiring users to follow complex manual procedures or interact with staff
Solution Approach 2:
The system changes parameters by analyzing multiple frames from a video feed rather than relying on a single static image. This approach automatically adjusts for variations in lighting, angle, and focus across multiple frames to improve verification accuracy without requiring users to manually optimize image quality
3Adaptability or versatility
If image data is used for document validation, then remote processing capability is improved, but detection of security features and digital manipulation becomes more challenging
Solution Approach 1:
The system performs preliminary analysis of the video feed to detect security features and potential digital manipulation before finalizing the deposit. Multiple frames are examined in advance to identify holograms, microprint, and other security elements, as well as to detect signs of digital alteration
Solution Approach 2:
The system uses feedback mechanisms by analyzing multiple frames from the video feed to verify consistency of security features across different moments in time. Discrepancies between frames may indicate digital manipulation, and the system adjusts its risk assessment based on this comparative analysis
4Measurement precision
If multiple frames from video feed are processed to improve document detection accuracy, then measurement precision is improved, but processing time and computational resources increase
Solution Approach 1:
The system extracts only the necessary information from the video feed frames rather than processing all data equally. Key elements such as check images, security features, and relevant document fields are identified and extracted for focused analysis, reducing overall processing requirements while maintaining accuracy
Data Source
AI summary
Presented herein are systems and methods for the employment of machine learning models for image processing. A method may include a capture of a video feed including image data of a document at a client device. The client device can provide the video feed to another computing device. The method can include, by the client device or the other computing device object recognition for recognizing a type of document and capturing an image exceeding a quality threshold of the document amongst the frames within the video feed. The method may further include the execution of other image processing operations on the image data to improve the quality of the image or features extracted therefrom. The method may further include anti-fraud detection or scoring operations to determine an amount of risk associated with the image data.