What is OCR?
Optical Character Recognition – Optical Character Recognition (OCR) software is the technique of converting optical characters into text by digitizing scanned documents, records or photographs with image processing techniques. With the OCR program, it is possible to search jpeg, tiff, image and pdf files and convert these files to word, excel, pdf formats.
eBA Digitization Management Application uses the Abbyy FineReader Engine infrastructure, which is one of the world’s most accepted OCR applications. Abbyy FineReader makes it easy to work with paper documents and pdf files with its powerful conversion and OCR technology. With the eBA Digitization Management System application, you can convert images, scanned documents and documents, pdf format files to Word, Excel and searchable pdf documents. In addition, thanks to the compression and storage algorithms in the infrastructure of the application, it is ensured that all scanned documents are created and archived in a certain standard.
Today, one of the biggest problems of institutions is the electronicization and access of silos of physical documents, as well as the management of the physical locations of these documents, which they are obliged to keep due to regulations. With the smart scanning features of eBA, these documents are not only transferred to electronic media by tagging while they are digitized, but also provide quick access to both digital and physical form of corporate documents by keeping their physical location information. In this way, it provides the opportunity to manage and access corporate information with an electronic archive culture by using archiving systems and filing techniques.
The rapid transfer of documents to electronic media, their classification, and transfer to other operational systems at necessary points can be achieved with the data processing module of Bimser’s eBA solution.
The data processing module supports full-text search with technologies such as OCR (optical character recognition), ICR (intelligent character recognition), and allows people to automatically find relevant documents by searching for meta information or tag information as well as content while accessing documents. In fact, by associating documents with each other, it allows the person who reaches a document to quickly access other documents related to that document. In this way, the efficiency of the institutions increases as the employees use their time effectively by minimizing the loss of time. Thanks to technologies such as ML (Machine Learning), AI (Artificial Intelligence) used by the module, the creation of document tags and the searched documents are quickly presented to the user, and the tag information of the document is automatically created while creating the document.
Data processing is applied on image formats such as tiff, pdf, bmp, jpeg with Abbyy Fine Reader Engine, which is accepted as an OCR engine. With OCR support, automatic XML metadata storage of index information, document recognition, data recognition, data capture and data processing methods and invoices, contracts, waybills, etc. it is possible to transfer other physical documents quickly and automatically to the digital archive.
Thanks to the image processing function of the eBA Document, Document and Workflow Management System, black/white, gray and color scanning operations and their conversion to each other during the scanning of physical documents (pdf to jpeg, jpeg to pdf, pdf to tiff, tiff to pdf, pdf to bmp, bpm to pdf, pdf to png, png to pdf, pdf to word, pdf to excel). The image processing function also has image enhancement features such as blank page removal, orientation and skew correction, noise removal, resolution and size correction.
With the eBA Capture module, you can separate the document from the keyword on the scanned document, via the barcode, depending on the number of pages. By taking the relevant action for the specified document type, it can be archived to the document management system, enterprise content management system (ECM – enterprise content management), directory system, or scenarios can be operated with the inclusion of the document in the process, approval and then archiving with a workflow. For additional information deemed necessary, it is possible to match the labels that are not on the document, integrated with other operational systems, during the scanning process.
In addition to digitizing the physical document archive, incorporating daily physical or digital documents into the operation with eBA Capture saves time, effort and cost. With the scanning process or the delivery of the electronic document to the application, the document type is determined, labeled, included in the relevant workflow and archived automatically. Moreover, when the necessary configurations of all these are made, with the Robotic Process Automation (RPA) architecture in its infrastructure, it can also be managed with robots that it has provided without human touch. Thanks to these smart robots, documents can be checked for accuracy by connecting to corporate applications, incorrect or unsuitable documents are collected in a pool and forwarded to the relevant units.
