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

Abstract

OCR often performs poorly on degraded documents. One approach to improving performance is to determine a good filter to improve the appearance of the document image before sending it to the OCR engine. Quality metrics have been measured in document images to determine what type of filtering would most likely improve the OCR response for that document image. In this paper those same quality metrics are measured for several word images degraded by known parameters in a document degradation model. The correlation between the degradation model parameters and the quality metrics is measured. High correlations do appear in many places that were expected. They are also absent in some expected places and offer a comparison of quality metric definitions proposed by different authors.

[Paper] An Encoding Method for Images Containing Textual Information for Very Low-Bandwidth Transmission

“…A deterioration model parameter intended for improving the performance of OCR has been designed 15) , and the correlation between the parameter and the subjective evaluation of humans was also investigated 16) . As a consequence, it became clear that the image quality assessment used to evaluate the performance of OCR cannot adequately predict the image quality evaluation obtained by the subjective perception of humans 17) .…”

Document Image Quality Assessment: A Brief Survey

“…This model has also been used for large-scale simulation studies in image pattern recognition, which provides a means of estimating the intrinsic difficulty of concrete image recognition problems. The relationship between model parameters and human perception, image quality metrics or observable degradation features was studied in [14], [36], [38].…”

"Quality" vs. "Readability" in Document Images: Statistical Analysis of Human Perception

“…In relation to the human readability, document images are presented to individuals and asked them to look at the documents, read and assess their readabilities, whereas as in relation to the machine readability, document images are generally subjected to an optical character recognition (OCR) process and the accuracy obtained from OCR is considered as degree of machine readability of the documents [22]. In both human and machine readability, poor quality document images might result in low document image readability (documents are unreadable) [17][18][19][20][21][22][23].…”

“…In the OCR-based category, character-based features have commonly been used to estimate the quality of document images. The metrics obtained as the quality of the document images were then associated with the results obtained from OCR to compute correlation values in order to evaluate the performances of the proposed methods in the literature [5][6][7][8][9]23]. High correlation values indicate that the performances of the proposed methods / metrics are commendable.…”

“…In addition to the methods in the literature that provide only a metric as the quality of a document image, there are also many studies which propose employing different preprocessing and filtering techniques in order to enhance the quality of document images (especially historical and degraded ones), results in improving the readability of those documents [17][18][19][20][21][22][23][24]. Different pre-processing and filtering operations [17,18,19], binarization methods [20], and quality assessment followed by filtering operations [21,22,23] have been used to improve document image quality and readability. Eye tracking technology has also been used to aggregate reading behaviour of many readers in order to provide objective quality feedback [24].…”