Asymptotic cost in document conversion

Abstract

In spite of a hundredfold decrease in the cost of relevant technologies, the role of document image processing systems is gradually declining due to the transition to an on-line world. Nevertheless, in some high-volume applications, document image processing software still saves millions of dollars by accelerating workflow, and similarly large savings could be realized by more effective automation of the multitude of low-volume personal document conversions. While potential cost savings, based on estimates of costs and values, are a driving force for new developments, quantifying such savings is difficult. The most important trend is that the cost of computing resources for DIA is becoming insignificant compared to the associated labor costs. An econometric treatment of document processing complements traditional performance evaluation, which focuses on assessing the correctness of the results produced by document conversion software. Researchers should look beyond the error rate for advancing both production and personal document conversion.

Optimisation of archival processes involving digitisation of typewritten documents

“…Therefore, this information is very important for planning of digitisation projects as it greatly affects the labour cost of a scanner operator. The approximate cost of operating a book scanner, 120 hours per week (three shifts), is approximately 1,440 USD and has remained more or less flat in the last few decades (Blostein and Nagy, 2012). Using the optimised scanning quality levels (300–500 dpi), we can save 470 hours per 100,000 pages – almost 4 weeks of work or 6,000 USD.…”

“…Goal of this research is to formulate a testing procedure that is applicable to a variety of similar typewritten documents that can be found in the archives all around the world. The use of optimised procedure unlocks the potential to accelerate the workflow and automate the digitisation process (Blostein and Nagy, 2012), thus saving time and reducing costs of document conversion. Choosing the optimised approach can potentially save days, or even weeks of work in a large-scale digitisation project and produce substantial economic benefits.…”

“…Therefore, mass digitisation [1], indexing and full text retrieval of archival materials is the field in which the improvement of process automation can be expected. In a modern day personal computer era, optical character recognition (OCR) process does not require special purpose hardware or expensive software to build a system that can be used in the digital repositories (Blostein and Nagy, 2012, p. 3). Special purpose workflows can be easily built depending on the type of archival materials (Blanke et al , 2012).…”