National Libraries Case Study

Learn more about our solutions for the Publishing industry.

Client:
World renowned national library

Strategic Opportunity:
Preserve and open access to two million historical newspaper pages.

Key Challenge:
Create a hybrid imaging method that retains the historical "noise," but still allows OCR technology to generate accurate text for searching.

Apex CoVantage Solution:
Working with the client, Apex has perfected a compromise through technology that enables creation of composite images. These composite images allow for both the smallest possible file size, as well as the crispest, sharpest images. In addition, our processes "prep" the image of the text on the page and then process the enhanced text using an approach unique to Apex to achieve the highest possible accuracy in uncorrected text generated from OCR. Thus, text is rendered in true 1-bit black and white, which provides not only for a crisp, pleasing look, but also provides the basis for the best possible OCR results. On the same page, grayscale and color are rendered in 8 or 24-bit color respectively.

Result:
Not only does this render a page as a fully faithful reproduction of the original, it also creates files of the smallest possible size, facilitating loading speed.