Ambient-Light Managed Check Imaging With Virtual Backgrounds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current remote deposit systems face challenges in processing images of checks due to poor contrasting backgrounds and inadequate ambient lighting, leading to inefficient use of resources and potential fraud issues.
Innovation Solution
Implementing ambient light sensors and LIDAR sensors on mobile devices to manage image processing, using machine learning algorithms to select virtual backgrounds that enhance contrast ratios, and performing OCR on live video streams to extract check data in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users take pictures of checks for remote deposit using mobile devices, then convenience of deposit is improved, but image processing quality deteriorates due to poor contrasting backgrounds and inadequate ambient lighting
Solution Approach 1:
The system performs preliminary actions by using ambient light sensors to assess lighting conditions and LIDAR to determine distance before the user captures the check image. Based on this preliminary assessment, the system proactively selects and applies appropriate virtual backgrounds and adjusts imaging parameters in advance, preventing image quality issues before they occur while maintaining user convenience
Solution Approach 2:
The patent introduces virtual backgrounds as an intermediary element between the check and the camera. These computationally generated backgrounds with high contrast patterns serve as a mediator that enhances the visibility of the check document, allowing for better image capture in various ambient lighting conditions without requiring users to change their physical environment
2Manufacturing precision
If virtual backgrounds are selected and overlaid to enhance contrast ratios, then image processing quality is improved, but device complexity increases
Solution Approach 1:
The system implements self-service by automatically selecting appropriate virtual backgrounds based on ambient light sensor readings and LIDAR distance measurements, then seamlessly overlaying them onto the check image without requiring user intervention. This automated process handles the complexity internally while presenting a simple interface to the user
Solution Approach 2:
The patent changes key parameters dynamically - selecting virtual backgrounds with different contrast characteristics based on measured ambient light levels and distance to the check. The system adjusts imaging parameters such as exposure, gain, and virtual background selection based on real-time sensor data, optimizing image quality for each specific capture scenario
3Productivity
If OCR is performed on live video streams in real-time, then productivity is improved, but use of energy increases
Solution Approach 1:
The system applies partial action by performing OCR processing selectively - not on every single video frame, but on key frames or frames that meet certain quality thresholds determined by ambient light and distance measurements. This reduces the total number of OCR operations while still achieving real-time processing of the check information
Solution Approach 2:
The system performs preliminary assessment using ambient light sensors and LIDAR to determine optimal imaging conditions before initiating OCR processing. By pre-evaluating lighting and distance, the system can decide whether real-time OCR is necessary or if a single captured frame suffices, reducing unnecessary energy-consuming processing while maintaining productivity
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
Improves image processing quality in poor lighting conditions, reduces resource consumption, enhances user experience, and minimizes duplicate deposits and fraud.
Implementation Method 1
an ambient light sensor, resident on a client device, manages image object processing sequences
Implementation Method 2
A LIDAR sensor, resident on the client device, manages image object processing sequences
Data Source
AI summary
A computer implemented method, system, and non-transitory computer-readable device that may be used in a remote deposit environment. Upon receiving a user 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 select a virtual background to increase a contrast ratio between pixels of the financial instrument and pixels of background imagery relative to the financial instrument. The method continues by extracting data fields based on the formation of image objects of each side of the financial instrument from the live video stream of image data. The extracted data fields are communicated to a remote deposit server to complete the remote deposit.