UiPath OCR Activities

The UiPath OCR Activities pack ensures a robust and efficient OCR solution, enhancing text extraction capabilities across a spectrum of use cases.

Overview of UiPath OCR Activities Pack

The UiPath OCR Activities pack encompasses two distinct activities: the UiPath Screen OCR activity and the UiPath Document OCR activity.

UiPath Screen OCR represents UiPath's proprietary machine-learning-based OCR solution tailored for screen-based content. Serving as a viable alternative to other OCR engines, it seamlessly integrates with the various Screen Scraping and Computer Vision activities available in the UI Automation package.

UiPath Document OCR Activity

UiPath Document OCR is a specialized, in-house, machine-learning-driven OCR tool designed specifically for documents. It is optimized for usage on scanned documents and images of documents. The activity can be employed in any document scenario in which an OCR engine is needed, for instance, the Digitize Document activity or the Read PDF With OCR activity.

Specialized OCR Activity for East Asian Languages

The package features an OCR activity designed for Chinese, Japanese and Korean. This activity facilitates the extraction of strings and associated information from a designated UI element or image through the OCR engine. It can be used with other OCR activities (Click OCR Text, Hover OCR Text, Get OCR Text, Find OCR Text Position) or with Computer Vision activities (CV Screen Scope, CV Get Text).

IMPORTANT: Installing this package version requires upgrading all the other Document Understanding packages to their latest version. (in case any are installed).

This includes the following packages: IntelligentOCR (>= 6.4.0), DocumentUnderstanding.ML (>= 1.16.0), PDF (>= 3.9.0), AmazonTextract (>= 1.0.0), OCR.Activities (>= 3.9.0) and OmniPage (>= 1.11.0). On lower versions, some functionality may be missing or unexpected errors might occur.

Applications and Features of the UiPath OCR Activities Pack

The UiPath OCR Activities pack can enhance automation and data extraction capabilities in a variety of scenarios:

Data Entry and Form Processing

The UiPath OCR activities can be employed to extract data from paper forms, invoices, and other structured documents.

Screen-based Automation

UiPath Screen OCR is ideal for automating processes that involve extracting information from screen elements.

Document Management

UiPath Document OCR is well-suited for managing and processing documents in various formats, such as contracts, agreements, and reports.

Financial Data Extraction

In the finance sector, the OCR activities can be applied to extract relevant data from financial statements, invoices, and receipts.

Human Resources Automation

HR departments can utilize the OCR package for automating the extraction of information from resumes, applications, and other HR-related documents.