Proofpoint. has been granted a patent for a method and system that extracts personal data from sensitive documents. The technology utilizes modules for document prediction, cropping, denoising, and optical character recognition (OCR) to identify and categorize information effectively. GlobalData’s report on Proofpoint gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Proofpoint, Network traffic analysis was a key innovation area identified from patents. Proofpoint's grant share as of June 2024 was 57%. Grant share is based on the ratio of number of grants to total number of patents.
Extracting personal data from sensitive documents using ocr
The granted patent US12046067B2 outlines a comprehensive method and system for extracting personal data from sensitive documents. The process begins with predicting the document type through keypoint matching, followed by cropping the document to extract its shape and relevant fields, which may include text and images. The extracted fields undergo a denoising process to enhance their quality for optical character recognition (OCR). The OCR is then performed on these denoised fields to detect characters, with a specific focus on categorizing characters in at least one categorical value field by calculating similarity scores against predefined category data. The method also incorporates advanced techniques such as Generative Adversarial Networks (GAN) for denoising and Bidirectional Long Short-Term Memory (Bi-LSTM) models for correcting character errors.
Additionally, the patent describes a system that includes various modules to facilitate this extraction process. These modules encompass a document prediction module, a cropping module, a denoising module, and an OCR module, each designed to work in tandem to optimize the extraction of personal data. The document prediction module employs a KAZE-based approach for feature extraction and utilizes a pre-trained neural network to enhance prediction accuracy. The system also features a lite mode of operation to balance speed and accuracy, and it modifies the Tesseract OCR engine to improve character detection by using rescaled predicted field images. Overall, the patent presents a sophisticated approach to handling sensitive documents while ensuring data extraction efficiency and accuracy.
To know more about GlobalData’s detailed insights on Proofpoint, 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.
