Advanced Software (return to the homepage)
Optical character recognition (OCR) technology: A brief history
Blog //06-09-2022

Optical character recognition (OCR) technology: A brief history

by Steve Britton, Client Director

Optical character recognition (OCR) technology converts text images into machine-encoded text. It is widely used as a form of data entry from printed paper data records, such as passport documents, invoices, bank statements, and computerised receipts. Digitising text means it can be easily presented, edited, stored, and searched, making key administrative tasks such as invoicing and sales processing more efficient.

Today, we’re taking a look at how this technology was developed, and whether it can remain relevant in the era of digitisation.

How OCR technology developed

OCR technology traces its roots back to telegraphy. In 1914, on the eve of the First World War, the physicist Emanuel Goldberg invented a machine that could read characters and convert them into telegraph code – an early form of optical character recognition.

Later, Goldberg went a step further and created what was perhaps the first electronic document retrieval system. In the 1920s, microfilm had become a popular way for businesses to store financial records – but quickly retrieving specific records from spools of film was almost impossible. To overcome this, Goldberg repurposed existing technologies, using a photoelectric cell to recognise patterns with the help of a movie projector. The US patent for his ‘Statistical Machine’ was later acquired by IBM.

Since then, OCR technology has become more sophisticated and more widespread. Early versions had to be trained with images of each character and were limited to recognising one font at a time – but in the 1970s, inventor Ray Kurzweil commercialised ‘omni-font OCR’, which could process text printed in almost any font.

By the early 2000s, desktop and mobile OCR applications became available online as a cloud-based service. Now more accessible than ever, businesses all over the world began relying on this technology to extract data from paper documents.

Today, many OCR service providers offer this technology, often via APIs. Most applications are now capable of recognising most characters and fonts to a high level of accuracy, and the technology continues to improve.

The future of data

For decades, OCR technology was the only way to turn printouts into data that could be processed by computers. Alongside electronic data interchange (EDI) and invoice portals, it remains a popular tool for converting paper invoices into extractable data that can be integrated into financial management systems (FMS) or enterprise resource planning (ERP) software.

Because OCR technology recognises characters, there is always scope for errors. Data accuracy can vary depending on the quality of the document received, and some manual intervention may be required.

New data processing technology, such as our OneAdvanced Data Automation solution, utilises machine learning to offer a faster, more accurate, option. OneAdvanced Data Automation extracts information from the data layer of PDFs or other data-rich documents – guaranteeing 100% data accuracy, every time. Many organisations are adopting this technology to cut operating costs, boost productivity, and free up their staff to focus on higher-value tasks.

Realising your business’ potential

Some businesses still scan in paper invoices, or receive image-based invoice files from their suppliers, meaning that OCR technology remains a valuable tool for filling in the gaps when it’s not possible to receive an application-generated electronic document.

OneAdvanced Data Automation’s total managed service allows organisations to capture and process both data-based and image-based invoices. Our OCR tool can process image files with 80% to 90% accuracy, meaning that a small amount of manual correction may be required. This add-on service can bring paper and electronic invoicing into the same processing platform, enabling our customers to target savings of up to 80%.

As image files are likely to represent a small proportion of your inbound document volume, we recommend encouraging your suppliers to submit digital documents. With OneAdvanced Data Automation, they won’t have to change their infrastructure, applications or processes – they can simply use their accounting software to generate a PDF, Word, Excel, or HTML file, and email it to you. Then, your OneAdvanced Data Automation system will provide validated, 100% accurate data in your FMS or ERP, typically within just a few minutes of receipt.

OneAdvanced Data Automation is accurate, reliable and flexible. With enhanced data visibility, you can gain vital insights to improve decision-making, support your strategic goals, and grow your revenue.

To discover how OneAdvanced Data Automation can help you achieve your goals, get in touch today at

Brand Blog
Steve Britton

Steve Britton


Client Director

For over 20 years, Steve has worked with global corporates to digitise and automate their Accounts Payable and Accounts Receivable business processes. With a professional background in software sales, Steve has worked with tech industry & BPO giants across Europe & the USA. Steve maintains a hands-on interest in technology, an endless energy for entrepreneurial innovation and a passion for delivery of the best customer service.

Read published articles