Hewlett-packard Development Company, L.P.

Purdue Research Foundation

Rochester Institute of Technology

Richard Eric Maggard

Jan Philip Allebach

Renee Jeanette Jessome

Mark Edward Shaw

Mark Q Shaw

Zuguang Xiao

Amy Ruth Reibman

Darrel D Cherry

Eli S Saber

Shaoyuan Xu

Katelyn Christene Morse

Runzhe Zhang

Wan-Eih Huang

Daniel Siddall

Yeshwanth Raja

An example of an apparatus including a communication interface to receive an image file is provided. The image file represents a scanned image of a output generated by a printing device. The apparatus further includes an identification engine to process the image file with a convolutional neural network model to identify a feature. The feature may be indicative of a potential failure. The apparatus also includes an image analysis engine to indicate a life expectancy of a part associated with the potential failure based on the feature. The image analysis engine uses the convolutional neural network model to determine life expectancy.

Part replacement predictions using convolutional neural networks

In an example method, an image of a printed document is descreened. The descreened image is separated into blocks. A smooth area of the descreened image is selected based on an averaging of localized color distance values of pixels in each of the blocks. A streak in a block of the smooth area is detected in response to detecting that a magnitude of a color distance projection of the block exceeds a threshold value.

Detecting streaks in printed documents using blocks

Examples of methods are described herein. In some examples, a method includes calculating a first cost function measure based on band defects in an image. In some examples, the method also includes calculating a second cost function measure based on the band defects and a synthetic band. In some examples, the method further includes detecting a missing band based on a comparison of the first cost function measure and the second cost function measure.

Missing band detection

Pixel blocks of a user-generated print job raster page are clustered into raster color clusters, and pixel blocks of a corresponding scanned page are clustered into scanned color clusters. For each raster color cluster, if a color difference between the cluster and a corresponding scanned color cluster is greater than a threshold, color fading of the cluster is determined from simulated depletion of each colorant of a printing device, and a likely depleted colorant is determined based on the corresponding scanned color cluster and the determined color fading. A most likely depleted colorant is determined from the likely depleted colorant predicted for each raster color cluster for which the determined color difference is greater than the threshold.

Predicting depleted printing device colorant from color fading

In some examples, print quality diagnosis may include aligning corresponding characters between a scanned image of a printed physical medium aligned to a master image associated with generation of the printed physical medium to generate a common mask. Print quality diagnosis may further include determining, for each character of the scanned image, an average value associated with pixels within the common mask, and determining, for each corresponding character of the master image, the average value associated with pixels within the common mask. Further, print quality diagnosis may include determining, for each character of the common mask, a metric between the average values associated with the corresponding characters in the scanned and master images.

Print quality diagnosis

Growing community of inventors

Boise, ID, United States of America

Richard Eric Maggard