Ah, the centralized versus distributed question...it is one that is continually asked in the scanning, capture and document capture space. Most associate OCR Software with familiar desktop applications like eCopy Desktop, OmniPage, PaperPort, etc. These provide, in a way, distribution of the overall OCR process to end users.There are applications on the market that can provide centralized and controlled OCR capabilities, through either a server or a workstation deployment. One example is PSI:Capture from PSIGEN, and advanced document capture application, that allows centralized OCR processing. Why would you want to do this? Well, in most cases, this type of OCR deplyment model is utilized in conjunction with a document capture system, for centralized capture, indexing, QA, OCR and migration to a centralized DM / ECM system. Typically, these systems give a broad and expansive feature set, providing all different types of OCR functionality.
ScanGuru has made another important post (see above).
Here are some significant points to think about when considering distributed and centralized OCR.
Note that while Nuance OmniPage has a "decentralized" desktop application, it also has a SDK that allows the OmniPage engine to be incorporated into centralized document capture applications.
Leading production capture software systems use the OmniPage engine for OCR. You would recognized the names of these applications if I mentioned them.
The end user should always ask what OCR is embedded within the product they want to use. eCopy Desktop, now eCopy PaperWorks, and Nuance PaperPort have OmniPage embedded.
The other very important aspect is that OCR in the cloud (as an Internet service or SaaS application) will become increasingly more common. Nuance will make an important announcement on this next week.
When OCR is in the cloud, is it distributed or centralized? The user can use it at the desktop or it could be part of a centralized document capture application. This is a good question to consider.