Keeping up with trends in OCR: ICDAR 2017

December 4, 2017
Keeping up with trends in OCR: ICDAR 2017

Our lead research engineer and CTO have recently visited the conference and got great insight into the latest advances in areas of text, document, and graphics recognition & analysis. They were especially interested to find out more about areas where deep learning played an important role.

Our research team has come a long way in developing proprietary, custom-made machine learning system for mobile OCR. That is in large part due to our researcher’s expertise, who continuously keep up with trends in text recognition and explore new possibilities to optimize our neural network architectures. One such opportunity was this year’s International Conference on Document Analysis and Recognition in Kyoto, Japan. Our lead research engineer and CTO have recently visited the conference and got great insight into the latest advances in areas of text, document, and graphics recognition & analysis. They were especially interested to find out more about areas where deep learning played an important role. Here is a short review of their experience.

Great workshops

The conference was split into two parts – 4 days of workshops and 3 days of lectures and poster sessions. Workshops are considered optional when attending the conference, while the main program is shaped by lectures. However, after the last day of ICDAR, it was quite clear to us that the workshops were extremely valuable. There were a lot more face-to-face interactions with researchers, discussions after each lecture, and hands-on topics which are especially interesting for our industry specific solutions.

Problem complexity and data driven research

One particular area where deep learning seems to have made significant progress is scene text recognition. The most advanced neural network architectures could be seen on problems in this area. There are two main reasons for this, in our opinion. First, we believe that the creativity and innovativeness in problem solving are driven by the complexity of the problem – and scene text recognition is a very complex problem. From our personal experience, the complexity of problems such as performing OCR on handwritten math expressions on device in real time was something that really pushed us forward in our research. The second reason is closely related to the emergence of deep learning as a standard tool in computer vision. In order to utilize the power of these methods, large amounts of annotated data are needed. There were problems on ICDAR harder than scene text recognition, but there simply wasn’t enough data to make effective solutions and/or conclusions.

Lack of optimization

To our surprise, the one thing that the conference was missing was focus on optimization. Optimization makes research methods applicable to real-world products. To us it seemed like there was a general misconception that deep learning solutions aren’t fast enough for on-device processing. Our proposal to the organizers was to dedicate at least one workshop to this important area, and also that optimization is taken into account when comparing models in competitions.

We would like to point out that optimization is an important part in developing solutions and that deep learning neural nets can run on a device in real-time. Our first ML-based OCR model was in production in September 2016. The model was learned entirely on data to perform OCR for handwritten math expressions in the Photomath app. Afterwards, optimizing the runtime of our OCR models allowed us to have real-time ID scanning in BlinkID and receipt scanning in BlinkReceipt. We’re planning to continue with the development of mobile OCR for many other use-cases in the future.

All in all, it was a great event and we’re looking forward to ICDAR 2019. In the meantime, our research team is packing their bags again and heading for another conference – see you at NIPS 2017!

Integrate ID document scanning into your existing application today

Continue Reading

Find more thoughts on the industry insights, use cases, product features, trends in AI, and development processes.

Upgrade your UX with ID document scanning for web browsers
Technology

Upgrade your UX with ID document scanning for web browsers

February 23, 2023

How easy is it for your customer to start utilizing your product or service? In an age with no abundance…

Microblink’s top 5 blogs of 2022

Microblink’s top 5 blogs of 2022

December 28, 2022

What a year it has been.  For both our Identity and Commerce business units, 2022 was highlighted by growth, innovation,…

Identity Document Scanning product updates – November 2022
Product Updates

Identity Document Scanning product updates – November 2022

November 22, 2022

Find out what’s new in the v6 release of Identity Document Scanning, and how the updates empower your solution and…

Blue in the face: Twitter’s vexing verification raises identity issue on social media
Social Media

Blue in the face: Twitter’s vexing verification raises identity issue on social media

November 17, 2022

In the Twittersphere, the term “verified” has progressively taken on a meaning of its own. It was back in 2009…

Document Verification product updates – August 2022
Product Updates

Document Verification product updates – August 2022

August 10, 2022

Here’s a quick overview of all new features and supported documents in the latest version of Document Verification. Our unique…

Identity Document Scanning product updates – July 2022
Product Updates

Identity Document Scanning product updates – July 2022

July 31, 2022

We’re super excited to announce a new-better-than-ever version of Identity Document Scanning with 50 new identity documents and significantly improved…

3 ways automated document verification expedites onboarding
Industry Use Case

3 ways automated document verification expedites onboarding

March 1, 2023

Automated document verification software speeds up onboarding by reducing manual effort, improving accuracy, and enhancing compliance. By automating the verification of important documents like IDs, passports, and licenses, businesses can expedite the process, reduce manual effort, and improve accuracy. In this article, we’ll explore three key ways that automated document verification can help businesses onboard new customers or employees more quickly and efficiently.

Liveness detection: How not to get spoofed by identity fraudsters 
Fraud

Liveness detection: How not to get spoofed by identity fraudsters 

February 23, 2023

To combat the rise of identity fraud, organizations across industries have started implementing biometric (e.g., facial, retinal, fingerprint) scanning as…