We have repeatedly talked about how smart and flexible the solution for optical character recognition (OCR) and data capture is WISETREND-ABBYY FlexiCapture. It is especially good when you need to extract data from unstructured documents, such as invoices, purchase orders, and etc.
WISETREND-ABBYY FlexiCapture typically uses flexible layouts (FlexiLayouts) to customize the process of extracting data from unstructured documents. This very smart and powerful tool allows you to extract data even from very poorly structured documents. But creating FlexiLayouts in WISETREND-ABBYY FlexiLayout Studio is a complex problem that requires a lot of knowledge and skills. Therefore, let us consider in this article another WISETREND-ABBYY FlexiCapture tool for setting up document templates – field extraction training.
How does it work?
The WISETREND-ABBYY FlexiCapture field extraction training is a mechanism that uses user-marked field regions for training. It uses various anchors, such as static text, to determine the position of a field region. Field extraction training does not require any special knowledge or skills, you only need to mark out the regions of the fields on the document. In WISETREND-ABBYY FlexiCapture there are two main training scenarios.
The verification operator during his/her work in the WISETREND-ABBYY FlexiCapture Verification Station corrects the position of incorrectly detected field regions. At the end of verification, the document is sent further along the workflow, which contains the training stage after the export stage. After WISETREND-ABBYY FlexiCapture has accumulated enough samples of documents with the field region marked by the verification operator, the training results will automatically be used for all new documents. In order to activate auto-learning, you need to enable the corresponding checkbox in the project settings on the workflow tab.
Field extraction training done by the administrator
The project administrator can create a special training package using WISETREND-ABBYY FlexiCpature Project Setup Station, add sample images there, mark out the regions of the fields and train to extract the fields. WISETREND-ABBYY FlexiCapture requires a minimum of three sample documents for proper training.
To summarize, WISETREND-ABBYY FlexiCapture Field Extraction Training is an excellent tool that allows you to improve easily the accuracy of data capture from unstructured documents, without having special knowledge and skills.
WiseTREND has a great experience in creating data capture solutions using WISETREND-ABBYY FlexiCapture. If you need advice on automating business processes and using WISETREND-ABBYY FlexiCapture for this, please contact us.
Ilya Evdokimov is a long-term practitioner and expert in leading Optical Character Recognition (OCR), Data Capture and Document Processing techniques, technologies and solutions. With over 15 years of experience spanning enterprise software implementations, mobile applications development, cloud-based systems integration and desktop-level automation, Ilya Evdokimov uses through industry knowledge and experience to achieve high efficiency and workflow optimization in most challenging paper-dependent and digital image capture environments.