Jumio has filed a patent for a system and method that uses image data and corner coordinates to generate a polygon and perform validity checks on a document. The system also includes an auto-capture feature. GlobalData’s report on Jumio gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Jumio, Biometric transaction authentication was a key innovation area identified from patents. Jumio's grant share as of September 2023 was 57%. Grant share is based on the ratio of number of grants to total number of patents.
A patent for a method of auto-capturing document images
A recently filed patent (Publication Number: US20230316795A1) describes a method and system for automatically capturing images of documents. The method involves receiving image data of a document and obtaining corner coordinates representing the corners of the document in the image. A polygon is generated based on these corner coordinates, and corner-based validity checks are performed to ensure the accuracy of the document's position and orientation.
The method also includes training a neural network on a set of training image data, which includes images of both documents and non-documents. A second set of training data, consisting of labeled images of documents, is obtained to retrain the neural network. This retrained neural network serves as the coordinate determination model for accurately determining the corner coordinates of the document in the image.
Various corner-based validity checks are performed, such as checking if the document is upright, rotated, tilted, or if it meets certain aspect ratio and edge length criteria. Additionally, usability checks are conducted, including glare detection, blur detection, obstruction detection, damage detection, and color detection.
The system determines the validity of the document image based on the generated polygon and the results of the corner-based validity checks. It also compares the corner coordinates of a second image of the document to the first image, calculating an inter-image corner distance value. If this value satisfies a threshold, a counter representing the number of valid results is incremented. The system then determines if the counter satisfies a second threshold, and if so, an auto-capture is performed.
The system can handle non-consecutive images of the document, and the counter is reset if the inter-image corner distance value does not meet the threshold or if a third image of the document is determined to be invalid based on corner-based validity checks.
Overall, this patent presents a method and system for automatically capturing images of documents, ensuring their accuracy and usability through corner-based validity checks and usability checks. The use of a trained neural network as a coordinate determination model enhances the accuracy of determining the corner coordinates of the document in the image.
To know more about GlobalData’s detailed insights on Jumio, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
