Optical Character Recognition (OCR) is a process by which a specialized engine is used to convert scanned images or images (documents) captured in real time to electronic text so that digitized data can be searched, indexed and retrieved. Azyo’s REAL OCR engines are developed and optimized for multiple real world applications such as extracting data from business documents, cheques, driver-licenses, passports, invoices, bank statements, insurance/mutual funds documents, university transcripts and likewise. Such solutions require processing data sets that consist of hundreds of thousands of scanned documents or images in order to train and optimize the machine learning algorithms. Processing the training data set is typically done by data scientists in order to provide accurate data that can be used by the engine to learn and apply, making it "smarter, efficient and accurate". Our unique in-house REAL OCR engine, and human intelligence, powered by artificial intelligence provides you with a scalable and affordable solution to process these large data sets efficiently.