Automatic filter selection using image quality assessment

<title>Correlating degradation models and image quality metrics</title>

“…Small Speckle Factor (SSF) [13]: This is similar to SSF defined in [9], but counts the number of connected components with fewer than O.S*FS pixels.…”

“…Most are defined to quantitatively capture the different types of degradations seen in large document collections. Eight different quality measures defined in [7,9,10,13] were implemented for these experiments. Some quality metrics aim to measure the same effect, but the method used to calculate the degradation effect has been defined differently by different authors.…”

“…Stroke Thickness Factor (STF) [13]: This is the most frequently measured thickness in the horizontal direction. At each row of the text lines, the number of consecutive black pixels is counted.…”

“…Touching Character Factor (TCF) [9,13]: The TCF measures the degree to which neighboring characters touch. This is looking for long and low connected components.…”

“…These methods utilized quality metrics calibrated from the image scanned for OCR. More recently an approach has surfaced where authors are designing systems to automatically choose a filter that when applied to the degraded document image improves the image quality and therefore the OCR performance [9,13,14]. Here the choice offilter is related to the level and type of degradation present in the document image.…”