- Starting from v10.1.4.1, Windows OCR is no longer supported. You can have Windows-based OCR only if you upgrade from earlier product versions with Windows OCR installed. You can use the instructions to increase the number of OCR licenses (the number of documents for OCR processing) in your environment.
In Work.AI, the no-code OCR step lets you accomplish the following:
View OCR dashboards
To plan capacity means to ensure the availability of a cost-effective capacity that meets or exceeds the business needs as established in Service Level Agreements (SLAs) at any given time. Within the context, capacity is defined as the maximum load the Work.AI platform can handle.
Goal
The document describes the differences between OCR for Work.AI Developer (Developer) and the Work.AI platform.
Work.AI offers the following OCR providers:
Templates are intended to simplify document ingestion by enabling automated information extraction from structured forms (for instance, ACORD). When a template is created, blank forms are annotated with labels. Based on these labels, data is then extracted from input documents.
The guide describes two automation use cases leveraging no-code Work.AI features and contract-based data schemas:
From the article, you can learn the following information about the Data Analyst (DA) role:
A Data Analyst (DA) acts based on several factors originating from the customer's data analysis. The article shares a typical workflow for new DAs.
The open-source library is used for language detection. It contains 71 built-in language profiles.
In the WorkFusion platform, the OCR component is installed by default. If you do not plan to use OCR, you can disable it. This will increase the throughput for Control Tower, RPA, and AutoML workers.
Problem statement
The machine-readable zone (MRZ) is typically found in official travel or identity documents of many countries. It can have two or three lines of machine-readable data. A new profile allows processing MRZ written in accordance with ICAO Document 9303.
Consistency
Goal:
Goal: Get labeled dataset of high quality
In order to ensure a dataset is of high quality, result of labeling must be:
Roles
Optical Character Recognition
A dataset is a container for documents and all related meta information as required for model training or testing, such as:
Overview
The article dwells on the obsolete approach of OCR usage in the scope of the ODF 2 framework.
Goal: achieve acceptable OCR configuration and get an understanding of the final OCR quality.
The ocr plugin works in the synchronous mode, and therefore, becomes a performance bottleneck if used within a BP where the OCR page volume is high, or documents contain more than 20 pages.
Using command line
Training set
Dataset requirements
To recognize tables and detect text in images, add the DetectTextOnImage and AggressiveTableDetection request parameters to the /processDocument and /processImage API endpoints. These parameters are set to false by default. To enable them, set the value to true. For details on the OCR API, see the guide.
Goal of the step: Split documents into batches by layout types before starting any manual handling—labeling, reviewing, and so on.
Before labeling, the most essential information the Subject-Matter Expert (SME) should share with the Data Analyst (DA) includes the following:
The article is an example of the OCR Bridge step usage in the scope of the ODF 2 framework. The Bot Tasks used in the example are a part of Processing Business Process from the example project.