Mobile Check Deposit Active OCR for Real-Time Data Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile check deposit processes lack flexibility and real-time feedback, requiring customers to wait until the upload process is complete to make changes and do not allow for mid-stream adjustments, and images are not stored on the user's device, posing risks for fraud.
Innovation Solution
Implementing active OCR on a mobile device to process live imagery in real-time, extracting data fields from a stream of check images without capturing an image, allowing for mid-stream adjustments and providing real-time deposit status updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional image capture and upload process is used, then complete check images are stored on server, but customers cannot make mid-stream adjustments and lack real-time feedback
Solution Approach 1:
The system performs OCR data extraction on check images during the upload process before the customer receives final confirmation. This preliminary action allows the system to process and validate check data in advance, enabling customers to review and potentially cancel deposits before final submission, thus allowing mid-stream adjustments without delaying the overall process.
Solution Approach 2:
The system provides real-time feedback to customers during the upload process by displaying extracted check data (amount, payee, date) as images are being uploaded. This feedback mechanism allows customers to verify information and make decisions about whether to proceed with or cancel the deposit while the upload is still in progress, rather than waiting for completion.
2Reliability
If check images are not stored on user's device, then server security is improved, but customers face fraud risks from unauthorized deposits
Solution Approach 1:
The system extracts and validates all necessary check data (amount, payee, date, MICR line) during the upload process before final deposit confirmation. By performing this preliminary OCR extraction and validation, the system creates a verified digital record that can be used for fraud detection and prevention, allowing customers to confirm the deposit details match their intent before authorization.
Solution Approach 2:
The system replaces the traditional mechanical approach of storing image files with an electronic data extraction approach using OCR technology. Instead of relying on customers to physically retain images or the server to store complete image sets, the system converts images into structured data fields during upload, which can then be validated, verified, and used for fraud prevention without requiring long-term image storage.
3Productivity
If real-time OCR processing is implemented, then data extraction speed is improved, but device processing requirements increase
Solution Approach 1:
The system merges the OCR processing function with the existing mobile banking application, integrating the data extraction capability directly into the upload workflow. By combining the image upload and OCR processing into a single unified process rather than separate sequential steps, the system achieves real-time data extraction without requiring additional standalone processing hardware or complex external systems.
Solution Approach 2:
The mobile device's camera and processor are designed to serve multiple functions: capturing images for various purposes, processing images for OCR extraction, and uploading images to the server. By making the device multi-functional, the system can perform real-time OCR processing using existing hardware capabilities without requiring specialized equipment or significantly increasing device complexity.
Data Source
AI summary
A computer implemented method, system and non-transitory computer-readable device for a remote deposit environment activating, on a client device, a financial application, wherein the financial application is configured to instantiate a customer interface (UI) on the client device. Upon receiving a customer request, based on interactions with the UI, the method implements an electronic deposit of a financial instrument by activating a camera on the client device to generate a live stream of image data of a field of view of at least one camera, wherein the live stream includes imagery of at least a portion of the financial instrument. The method continues by blending common pixels from the imagery to form a blended image, and extracting by an optical character recognition program one or more data fields from the blended image of the financial instrument.