The History of OCR
Author: Dave Van Everen
Optical Character Recognition (OCR) technology has come a long way since its inception in the late 19th century. One of the earliest OCR-related inventions was U.S. patent 2,026,329 on Dec. 31, 1935 for a “reading machine”, by Gustav Tauschek from Vienna, Austria. In its early days, OCR was used to digitize printed texts and make them machine-readable. Over the years, advancements in OCR technology have led to its widespread use across various industries. In this article, we’ll review the history of OCR and its evolution into a crucial technology for the digital age.
While OCR history can be traced back to the late 1800s and early 1900s with a variety of related inventions, early OCR systems really began to emerge in the 1960s and 1970s. These systems were designed for specific use cases, such as sorting mail based on zip codes, or reading handwritten numbers. Fun fact: the first optically machine-readable font OCR-A was developed in 1968 by Swiss typeface designer Adrian Frutiger, and serves as the inspiration for the Veryfi logo.
In the early 1970s, OCR technology was limited to recognizing a small number of fonts and was unable to handle complex images. Ray Kurzweil, inventor, futurist, and founder of Kurzweil Computer Products, developed an omni-font OCR system along with the CCD flatbed scanner, and gave OCR its commercial beginnings. This invention sparked an technology evolution spanning several decades over the history of OCR.
In 1980 Kurzweil’s company was sold to Xerox, which renamed it as Scansoft (later merged with Nuance Communications). Throughout the 1980s, OCR technology made significant strides with the development of new algorithms and more powerful computers. OCR systems were able to recognize a wider range of fonts and were able to handle more complex images, making them more accurate and useful for a wider range of applications.
In the 1990s, the widespread adoption of personal computers and the internet led to a significant increase in the use of OCR technology. OCR systems were used to digitize books, magazines, and other printed materials, making it easier to search and access information. The technology was also used to automate data entry processes in industries such as finance, healthcare, and government.
In the early 2000s, the history of OCR technology progressed with the introduction of new algorithms and improved hardware. OCR systems became more accurate and were able to recognize a wider range of characters and languages. This paved the way for the widespread adoption of OCR technology in a variety of industries and applications, such as document management and invoice processing. In this timeframe, Google also famously (and controversially) launched Google Books, code-named Project Ocean, using OCR to digitize tens of millions of books and make their text searchable.
Today, OCR technology is more advanced and sophisticated than ever before. OCR systems are able to recognize a wide range of characters and languages, handwriting, and other complex images. A variety of industries, including finance, consumer packaged goods, healthcare, government, and retail use OCR, and it is essential for automating many business processes. Imagine saving bookkeepers and Accounts Payable clerks 220,470 years of manual data entry in the U.S….every year! Those efficiency gains are possible thanks to OCR, assuming 965,658 AP clerks in the U.S. and 12,000 invoices per year per clerk.
OCR technology is continuing to evolve, with advancements in artificial intelligence (AI) and machine learning (ML) leading to even more accurate and sophisticated systems. For example, some OCR providers like Veryfi are adding Convolutional Neural Networks to improve versatility and accuracy. Over time, OCR technology will play a crucial role in the digital transformation of industries and organizations. Information will be easier and more efficient for organizations to access and manage. As its use increases, OCR software will also help eliminate tedious and error-prone manual data entry, freeing company resources to work on higher-value tasks.
OCR history began with revolutionary inventions designed to improve quality of life for humankind. Decades later, the technology is still undergoing continuous evolution and improvement, and is a crucial enabler of the digital age. OCR has come a long way and is truly improving quality of life for much of humanity. Today, a wide range of industries and applications use OCR. In the coming decades it will play a key role in global digital transformation.
If you’d like to see our innovative AI-Driven OCR in action, try it yourself in this free web demo.