Mobile Check Image Validation Using Native ML Frame Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile operations software programs face performance issues and errors in capturing and validating check images due to reliance on third-party libraries, leading to slower processing times and crashes, and struggle with accurately capturing images that meet specific criteria such as brightness, contrast, and rectangular format, limiting the ability to validate checks properly.
Innovation Solution
Implementing a mobile application that leverages native image processing software (e.g., Apple VisionKit®) for client-side image processing and validation, using machine-learning models to identify documents and attributes, such as checks, by capturing multiple frames and selecting frames at preconfigured intervals to validate dimensions, brightness, and contrast, and recognizing text.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If third-party libraries are used for image processing in mobile applications, then the application can capture and process images, but processing speed decreases and system stability deteriorates due to lag and crashes
Solution Approach 1:
The patent extracts the image processing functionality from third-party libraries and implements it using native image processing software (Apple VisionKit®) directly integrated into the mobile application. This eliminates the intermediary layer of third-party libraries that caused lag and crashes, thereby improving both system stability and processing speed simultaneously.
2Measurement precision
If third-party libraries are used for image processing, then image capture functionality is available, but processing accuracy decreases due to errors in validating document criteria
Solution Approach 1:
The patent replaces the mechanical system of third-party library processing with a more sophisticated native image processing system that uses machine-learning models. This substitution enables more accurate validation of document criteria (brightness, contrast, rectangular format) while maintaining high processing efficiency through optimized native code execution.
3Measurement precision
If multiple validation criteria are implemented for check images, then validation accuracy improves, but device complexity increases
Solution Approach 1:
The patent implements a universal image processing system using native software and machine-learning models that can handle multiple validation criteria (brightness, contrast, rectangular format, document type recognition) within a single integrated framework. This multi-functional approach achieves high validation accuracy without proportionally increasing software complexity, as the same core infrastructure supports all validation functions.
Data Source
AI summary
Presented herein are systems and methods for the employment of machine learning models for image processing. A mobile application for client-side image processing and validation, which interacts with and leverages native image processing software of the client device, where the image processing software and the mobile application include any number of machine-learning models for identifying a document and attributes of the document for recognition and validation. This mobile application uses the image processing software from a client operating system to control the camera. The image processing software generates various types of information about a video frame and the document, and the mobile application invokes APIs or software libraries of the image processing software to access the information and validate the frame and document.