When considering the ROI on a data capture integration, setup time is one of the most important and often miscalculated factors. Not just the setup time for initial integration, but the setup time used for any fine-tuning and optimization may sometimes postpone production.
The difference in setup time between a fixed data capture environment where coordinate based fields are used and rules based semi-structured environments is substantial. It’s not usually the fixed data capture environments that pose the biggest challenge in calculating ROI or predicting it. It takes an administrator on average between 15 to 45 seconds to create and fine-tune a fixed form field. In semi-structured processing, the field setup time can take between 60 seconds and hours, depending on the complexity of the document and the logic being deployed. It’s this large gap that throws a wrench in some ROI calculations.
For experienced integrators, the ability to put a document and it’s associated fields into complexity classes is usually pretty easy. After doing so gauging, the average amount of time to setup each field, and thus all fields should be accurate. There is always a field or two that requires extra fine-tuning. The key is a complete understanding of the document. Sometimes document variations are obvious, other times they sneak up on you and you have no idea the variation exists until you start working with it. Knowing all variations is the easiest way to understand the additional time any field will take to setup. Variants are the biggest contributor of time in semi-structured data capture setup. Second is odd field types, such as fields that take up one to many lines, or are continuous across two separate lines, and finally tables. The third and final largest contributor to setup time is poor document quality. This means the administrator has to be more general when creating fields and likely has to deploy multiple logic per each field to locate information in several possible ways.
When calculating the ROI on your data capture project, make sure to be aware of these sometimes sneaky factors that can eat at integration time. Bottom-line, know your documents, and know the technology before any work is done. If you are unsure, seek professional assistance.
Chris Riley – Solutions Architect
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.