OCR: What is optical character recognition?

Posted by media on November 14, 2018 at 9:00 AM

OCR what is Optical Character Recognition

At the end of the 18th century when the French Revolution began to define the bases of a new conception of the State, one of the concepts that started to be developed was recognition of the individualization of the person.

This recognition resulted in the creation of documents proving that a citizen was duly registered in the national archives. However, it took two centuries for that document to end up having the format of the current Spanish DNI (National Identification Card).

At present, thanks to OCR technology (Optical Character Recognition), which seeks to emulate the human eye's ability to recognize objects, we take this one step further in order to electronically identify people. We’ll tell you about it in the following post.

This post is also available in Spanish.

Table of contents

 

OCR, what is this latest technology?

Nobody is better looking than in their social media photo or as bad looking as in their DNI photo. This is 100% true, just as true as you are not aware of the importance of this document until you lose it. 

Whether to control the population or allowing to quickly identify citizens, identity documents or passports have become the standard method to identify ourselves in any public and private process.

In Spain the first DNI was green, it included data such as employment information and distinguished among four different categories depending on the holder's financial situation. From that first model in 1951 to the current one, the document has become more sophisticated with the aim of being more secure and preventing it from being easily falsifiable.

To this end and to improve the efficiency of digital flows, OCR technology is added to allow data to be recognized through the document scanner.


What is OCR?

The OCR concept refers to "Optical Character Recognition", a type of software that allows the optical recognition of the characters contained in an image (scanned document or photograph), so that these are comprehensible or recognizable for a computer.

Therefore, the OCR system is an analysis through which we analyse and scan a file to automate it.

"Optical character recognition is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo or from subtitle text superimposed on an image."   

 

How does OCR work?

In order to recognize the characters, the software examines the image pixel by pixel, looking for shapes that match the character traits. Depending on the level of complexity or degree of development of the software, it will look for matches with the characters and sources available in the program, or it will try to identify the characters by analysing their characteristics. 

OCR can analyse the elements of the document (blocks of text, images, tables...), examining blank spaces and breaking down the text into lines, words and characters.


What_is_the_advanced_electronic_signature 

What is OCR used for?

OCR is a transversal technology, applicable in different fields and industries for the digitalization of forms, administrative documents, reports, etc., as the advantages it offers are common to all of them.

In the culture industry, in the field of heritage preservation for example, OCR is applied mainly in the processes of digitalization of historical documents, on paper or microforms.

Thanks to this technology, at Signaturit we digitally verify identification documents, passports or driving licenses so our users can register their clients in a comfortable and secure way.

Signaturit's electronic identification

The online authentication method based on OCR technology consists in reading the documents’ MRZ code and comparing it with the rest of the data it contains in order to see if anything has been altered.

Signaturit offers two options for using it:

1. Have the user take a photograph of both sides of the DNI. Upon uploading the image to Signaturit, we get all the DNI information and validate that it hasn’t been manipulated.

2. Have the user attach a photograph of the DNI that they already have stored on their computer or mobile device. In this case, we also capture the data and validate that the information has not been manipulated.

Technically, our job is to verify the DNI’s MRZ code, which is the code that appears on the back and that is unique to each person. This code is generated through an algorithm, and is based on the information contained in each DNI.

Therefore, if someone modifies some data on their DNI, the MRZ code would no longer match the scanned information and our system would detect it as an invalid DNI. The same process applies if the identification document were a passport.

Capture

 

Benefits

- Digital identification: to prevent digital fraud with online person identification.

- User experience: optimum image capture from any mobile device.

- Easy Integration: with the option of integrating technology in any system via API.

 

H2020: Optical character recognition of European identity documents (IDs)

Last year, Signaturit received funding from Horizon 2020, the EU research and innovation funding programme, under Grant Agreement Number 778550, thanks to which we are developing several projects, including software for automatic recognition and extraction of more complex data in order to authenticate European identity documents.

This technology will allow us to extract and validate all the information contained in a European identity document from just a photograph of it providing more security to the transactions carried out on our platform.


EU_FLAG

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 778550. 


Conclusion

These types of tools collect the National Identity Document data which is a solution for the electronic identification of people that allows remote digital Onboarding for the opening of a bank account for example.

That fact that Signaturit allows this authentication procedure for a person's identity documents in a digital environment while signing a contract through our advanced electronic signature, makes us the perfect solution for 100% digital, legal and safe onboarding. 

If you need more specific information or you would like some advice regarding what types of authentication systems should be implemented in your company, don't hesitate to get in touch with us.

You can send us an email to info@signaturit.com, call us at +34 93 551 14 80 or fill out this form to reach us.

If you prefer, you can try directly our five authentication systems. You only need to register in Signaturit and you’ll have free access for 14 days to these and all other functionalities that we offer.

This post is also available in Spanish.

Download Whitepaper eSignatures 101 (English)

Topics: Electronic Signature

Blog Subscription

Recent Posts