Mobile Document Image Capture with Real-Time Distortion Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The categorization of customer documents captured as digital images using mobile devices is hindered by distortions such as noise, dimensions, skew, and rotation, leading to miscategorization or non-categorization, which requires human intervention and increases document processing time.
Innovation Solution
A system and method that involves configuring an image capture device based on a categorization model, generating image representations, assigning confidence levels to categories, and automatically triggering the capture of a document image when a threshold confidence is reached, ensuring accurate categorization and reducing human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If distortion correction is performed after document image capture, then categorization accuracy is improved, but document processing time is increased
Solution Approach 1:
The patent applies preliminary action by performing distortion correction during the document capture process itself, rather than after capture. The system includes a distortion correction module that operates in real-time during image acquisition, adjusting for skew, rotation, and other distortions as the document is being captured, thereby eliminating the need for separate post-capture correction steps and reducing overall processing time while maintaining accuracy.
2Measurement precision
If manual categorization is performed for distorted documents, then categorization accuracy is maintained, but productivity is reduced
Solution Approach 1:
The patent implements self-service by enabling the document capture system to automatically correct its own distortions and maintain categorization accuracy without human intervention. The real-time distortion correction module automatically adjusts for various distortion types during capture, allowing the automated categorization system to process documents efficiently without requiring manual review or correction by operators, thus maintaining both accuracy and high throughput.
3Reliability
If real-time distortion correction is implemented during capture, then categorization success rate is improved, but device complexity is increased
Solution Approach 1:
The patent applies merging by integrating the distortion correction functionality directly into the existing mobile device camera system. The distortion correction module is combined with the image capture and categorization components, allowing the device to perform correction operations using its existing processing capabilities without requiring separate complex hardware systems. This integration approach improves categorization success rate while minimizing the increase in overall system complexity.
Data Source
AI summary
A computer-implemented system and method for controlling document image capture are provided. The method includes identifying a categorization model for categorizing image frames and configuring an image capture device, based on the identified categorization model. A flow of frames of a same document captured with the configured image capture device is received and an image representation generated for each of a plurality of frames within the flow of frames. With the identified categorization model, for each of the plurality of frames, a confidence for at least one category is assigned to the frame based on the image representation. A category is assigned to the document when a threshold confidence for one of the at least one categories is assigned. An automatic capture of an image of the document is triggered based on the assigned category.