Hewlett-packard Development Company, L.p.

Xerox Corporation

Rochester Institute of Technology

Eli S Saber

Mark Edward Shaw

Lalit Keshav Mestha

Ranjit Bhaskar

Robert P Loce

Perry Victor Lea

Marvin D Nelson

Dhirendra C Damji

Sohail A Dianat

Darrel D Cherry

Shawn Patrick Updegraff

Roger Scott Twede

Peter Bauer

Sreenath Rao Vantaram

Porfirio J Perez

David G Bohan

Richard Eric Maggard

Renee Jeanette Jessome

David C Day

Vladimir Misic

Guru Prashanth Balasubramanian

Eric Robert Peskin

Osborn De Lima

Michael A Stauffer

Rakshit Sunil Kothari

Steve Bolte

Daniel Siddall

Yeshwanth Raja

Shruty Janakiraman

Arnold G Leon

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

Example implementations relate to detecting document objects. For example, detecting document objects may include a system comprising a pre-processing engine to establish a threshold for a document, wherein a structure of the document is unknown, a detection engine to detect a candidate area in the document, using a Hough transform and connected component analysis to merge detected candidate areas in the Hough transform to a same document object in the document, and a classification module to classify the candidate area as a document object or not a document object.

Detecting document objects

An example involves identifying a first artifact in an image on a display, the first artifact caused by a first subpixel of a first pixel, determining a type of the first artifact based on a location of the first artifact relative to content of the image, and correcting the first artifact to remove the appearance of the first artifact from the display based on the type of the first artifact.

Correcting artifacts on a display

A multi-resolution color image segmentation algorithm which takes advantage of gradient information in an adaptive and progressive framework is described. A gradient-based segmentation method is initiated with a dyadic wavelet decomposition scheme of an arbitrary input image, accompanied by a vector gradient calculation of its color converted counterpart. The resultant gradient map is used to automatically and adaptively generate thresholds for segregating regions of varying gradient densities, at different resolution levels of the input image pyramid. In combination with a confidence map and non-linear spatial filtering techniques, regions of high confidence are passed from one resolution level to another until the final segmentation at highest (original) resolution is achieved.

Methods for adaptive and progressive gradient-based multi-resolution color image segmentation and systems thereof

A method for segmenting an image includes computing a color gradient map based on an inputted image and selecting at least one initial seed of at least one pixel based on the color gradient map. The method further includes growing a region of pixels adjacent to the initial seed and merging adjacent regions of pixels using a measure of similarity.

Unsupervised color image segmentation by dynamic color gradient thresholding

A method for sharpening the corners of digital image data within an anti-aliasing image path so as to overcome corner rounding when displayed or printed. The method comprises stepping a window across the image data and comparing that windowed data to templates or performing Boolean logic and arithmetic operations on the image data. Upon determining a match or a corner detection, pixel values are substituted in the identified pixel locations to achieve a clustering of the substituted pixel values about the corner structure producing a corner-enhanced digital image. Filtering and sampling are then performed according to an anti-alias operation to the corner-enhanced image to produce an anti-aliased corner enhanced image. The data substitution will achieve a localized clustering or 'ear' of toner/ink, or in the alternative for inside corners the localized clustered absence of toner/ink. The result of this clustering is a sharpening of the corners so that they display or print as intended by the bitmap.

Corner sharpening of text and line art in a super resolution anti-aliasing image path

Tone reproduction curves for calibrating a marking system are obtained using a test pattern with a plurality of patches, preferably a plurality of first test patches extending in a first direction and at least one second test patch extending in a second direction crossing the first direction. Reflectance values are obtained from the first and second test patches. A set of gray balanced tone reproduction curves are obtained based on the reflectance values of the first test patches, and a set of spatial gray balanced tone reproduction curves are obtained based on the reflectance values of the second test patches.

Systems and methods for obtaining a spatial color profile, and calibrating a marking system

A multiple-LED sensor is used to detect area coverage of marked patches on a marking substrate. The same sensor may also be used for color calibration. The marking substrate area coverage sensor obtains reflectance measurements from marked patches of a marking substrate. For example, the marked patches may be patches of a marking substance such as toner, ink or paint, or patches marked by etching or the like. A Neugebauer model may be used to obtain the reflectance measurements. A batch least squares algorithm may be used to estimate the appropriate parameters of the Neugebauer model. For improved accuracy, a recursive least squares algorithm may be used. The recursive least squares algorithm allows the marking substrate area coverage sensor to calibrate itself to changes in the sensing environment.

Systems and methods for sensing marking substrate area coverage using a spectrophotometer

An electrophotographic printing or copying machine includes a functional module which can be readily removed and replaced. The module includes a monitor in the form of an electronically-readable memory, which includes information about how the particular module is to be operated. In a remanufacturing process, certain combinations of codes in the memory are noted to determine whether individual parts in the module should be replaced.

Remanufacturing system for replaceable modules in a digital printing apparatus

Growing community of inventors

Webster, NY, United States of America

Eli S Saber