In the current market, reduction of warranty costs is an important avenue for improving profitability by manufacturers of printer products. Our goal is to develop an autonomous capability for diagnosis of printer and scanner caused defects with mid-range laser multifunction printers (MFPs), so as to reduce warranty costs. If the scanner unit of the MFP is not performing according to specification, this issue needs to be diagnosed. If there is a print quality issue, this can be diagnosed by printing a special test page that is resident in the firmware of the MFP unit, and then scanning it. However, the reliability of this process will be compromised if the scanner unit is defective. Thus, for both scanner and printer image quality issues, it is important to be able to properly evaluate the scanner performance. In this paper, we consider evaluation of the scanner performance by measuring its modulation transfer function (MTF). The MTF is a fundamental tool for assessing the performance of imaging systems. Several ways have been proposed to measure the MTF, all of which require a special target, for example a slanted-edge target. It is unacceptably expensive to ship every MFP with such a standard target, and to expect that the customer can keep track of it. To reduce this cost, in this paper, we develop new approach to this task. It is based on a self-printed slanted-edge target. Then, we propose algorithms to improve the results using a self-printed slanted-edge target. Finally, we present experimental results for MTF measurement using self-printed targets and compare them to the results obtained with standard targets.
Assessment of macro-uniformity is a capability that is important for the development and manufacture of printer
products. Our goal is to develop a metric that will predict macro-uniformity, as judged by human subjects, by
scanning and analyzing printed pages. We consider two different machine learning frameworks for the metric:
linear regression and the support vector machine. We have implemented the image quality ruler, based on the
recommendations of the INCITS W1.1 macro-uniformity team. Using 12 subjects at Purdue University and
20 subjects at Lexmark, evenly balanced with respect to gender, we conducted subjective evaluations with a
set of 35 uniform b/w prints from seven different printers with five levels of tint coverage. Our results suggest
that the image quality ruler method provides a reliable means to assess macro-uniformity. We then defined
and implemented separate features to measure graininess, mottle, large area variation, jitter, and large-scale
non-uniformity. The algorithms that we used are largely based on ISO image quality standards. Finally, we used
these features computed for a set of test pages and the subjects' image quality ruler assessments of these pages
to train the two different predictors - one based on linear regression and the other based on the support vector
machine (SVM). Using five-fold cross-validation, we confirmed the efficacy of our predictor.