The problem solving power of OCR

Originally developed in 1974 to assist the blind, optical character recognition (OCR) has matured and is now a widely adopted technology for digitizing printed text so documents can be electronically cleaned, searched, edited and stored more efficiently.

OCR software automatically detects complex page layouts and images, removes blank pages and carries out document cleaning such as orientation or smudge removal. Capturing both structured and unstructured data, OCR can support a wide range of languages, formulas and digits.
 

OCR the Y Soft way

YSoft SAFEQ Advanced Scan Workflows are a powerful scan solution that includes robust document processing, ideal when sophisticated document treatments and formatting are required. Under its hood, and working without user awareness, is an OCR engine. It is this engine that makes many of the productivity and digital document enhancements possible.

Here are a few of the many capabilities of the OCR engine in YSoft SAFEQ Advanced Scan Workflows.

Clean, searchable & editable scanned documents

Document cleaning

Removing blank pages, detecting page orientation, splitting dual pages and  despeckling the document ensures documents are not just readable but meet your quality and consistency requirements.

Searchable documents

Having a scanned document is useful but finding tomorrow or six months from now can be a time-consuming task. The OCR engine removes this highly manual task by recognizing text (in multiple languages) from the scanned image and creating a text overlay as part of the document. Although this text overlay is invisible to the user, it is this text overlay that enables keyword search. Scanned documents can also be converted into other formats so that keyword search is made possible as the picture below shows.

The text overlay also includes meta data about the document which is also keyword searchable. In addition, when creating a workflow with a searchable PDF format, you are also able to modify it for compliance, security or file size purposes, as shown below.

Editable documents

Typical scans solutions only create a digital image of a document. When a digital document needs to be edited, it is difficult to do so as images are not editable with common office applications. The OCR engine allows workflows to be created with the output set to an editable type of document format such as Microsoft Word and Excel. Editing a scanned document instead of recreating it can save enormous amounts of time.

The power of the highlighter

YSoft SAFEQ Advanced Workflows highlighter functionality uses the help of the OCR engine for document consistency and data privacy.

Highlighted text extraction – ensuring consistency

Using a highlighter pen to highlight text is one way to ensure consistent document naming. An Advanced Workflow can be created to ‘read’ text that is highlighted, for example, in green, and to use the text as part of the document’s filename. The workflow can be set up to use combine the highlighted text with another variable, such as today’s date. By setting parameters within the workflow, manual naming of documents is eliminated, and consistency is upheld.

Highlighted text redaction – ensuring privacy

Text highlighting not only supports the naming of your scanned documents but can also help to protect sensitive information when sharing digital documents. Again, facilitated by the OCR engine, YSoft SAFEQ looks for the selected highlighter color, in this example red, and redacts any words so that they cannot be seen. Your employee simply highlights a word or a phrase. And, unlike other redacting methods, redacted text with YSoft SAFEQ workflows is truly redacted. A keyword search will not reveal even the presence of redacted text.

The power of OCR in your hands

The problem solving power of OCR can be harnessed by all sizes of organizations, regardless of industry. Innovation is at the core of the Y Soft business, and we are currently exploring additional OCR engine and document mining technologies to further enhance quality, productivity, efficiency and privacy.
 
You can find out more about YSoft SAFEQ Advanced Workflows and how your organization could benefit from the power of OCR here.
 
How can OCR help your organization? We would love to hear from you, please share your comments in the section below.