Optical Character Recognition, or OCR, is a process by which software reads a scanned newspaper page and translates its print into searchable text. While OCR technology enables searching of large quantities of data, like that contained in Virginia Chronicle, results are never 100% accurate. Because digitized images are taken from microfilm, OCR accuracy depends on both the print quality of the original newspaper and the image quality of the microfilmed copy. If the original newspaper print is poor or damaged or if microfilm images are faded, unevenly exposed, dark or blurry, it will negatively affect OCR accuracy.
As a registered user of Virginia Chronicle, you can assist in making its searchability better by correcting inaccurate OCR. In order to do so, become a registered user by clicking “Register” in the upper right corner of the home screen. Once you’re registered, you can begin correcting text.
Next, go to the page you would like to correct, right click on the page and choose “Correct page text.”
You will then be asked to “select an area of the issue to correct its text.” After you have selected an area, the correctable text appears on the left of the screen and newspaper page on the right with a corresponding red box over the text to correct. At this point, you are ready to go. Don’t forget to click the “save” button to save any changes you’ve made.
The Virginia Newspaper Project would like to extend big thanks to registered users of Virginia Chronicle who have already corrected over 27,000 lines of text! Thanks to such engaged users, a great research tool is made even better.