An overview of the technologies ShareRing used to power our OneID., eVOA application processes and much more!

What Is Optical Character Recognition?

Optical Character Recognition is a widespread technology used to recognise text inside images, such as scanned documents and photos. OCR technology is used to convert practically any kind of images containing written text (typed, handwritten or printed) into machine-readable text data.

OCR is frequently utilised as an “out of sight” technology, powering many well-known systems and services in our daily life. Less known, but as important, use cases for OCR technology comprises of:

• Data entry automation
• Indexing documents for search engines
• Automatic number plate recognition
• Assisting blind and visually impaired persons

OCR Technology became popular in the early 1990s while endeavouring to digitise historic newspapers. Since then the technology has experienced a number of enhancements. In this day and age solutions deliver near to perfect OCR accuracy. High-level methods like Zonal OCR are used to automate complex document-based workflows.

What is Machine Learning? 

Machine learning is an application of artificial intelligence (AI) that supplies systems with the ability to automatically learn and develop from experience without being explicitly programmed. Machine learning concentrates on the advancement of computer programs that can access data and use it to learn for themselves.

Machine learning facilitates the analysis of massive quantities of data. While it usually delivers faster, more accurate results. In order to recognise profitable opportunities or threatening risks, it may also require additional time and resources to train it properly. Merging machine learning with AI and cognitive technologies can make it even more powerful in processing large quantities of data.

What is Face Match technology?

ShareRing’s OCR and Face Matching Technology

ShareRing will use a combination of OCR, FaceMatching and Machine Learning technologies to enable users to create their OneID, apply for eVOA and much more within minutes instead of hours.

For the OCR and field recognition, ShareRing uses a mix of Google Tesseract, AWS Textract and our own secret sauce.  For eVOA applications, we use machine learning and OCR to automatically validate passport details, hotel and flight bookings. We’re now teaching it to recognise different booking templates.

The @ShareRingGlobal eVOA system will soon be processing 2000 applications per day, expanding to 10,000+ per day in the next few months. We estimate that it will save our partners more than $100,000 per month in their manual processing costs, while also providing better security.

— Timothy Bos (@TheRealTimBos) January 5, 2020

Now that’s a REAL world use of blockchain technology!

ShareRing’s OCR and FaceMatching with Car Rentals

In ShareRings OneID process a user would take a photo of their ID as well as take a selfie; we check it automatically with authorities like AML, and we do OCR on it to make sure that the positioning of all the things is right. We also do face matching to make sure the photo matches what’s on the passport.

Then we can encrypt that file, take a fingerprint of that file (which is like a hash of that file) store that hash on the blockchain, but keep the file either on your phone or your Google Drive or iCloud, which is encrypted with your blockchain private key. What that actually means is when my ID is sent from me to this car rental company only the bits that are needed will be sent.