Hewlett-packard Development Company, L.p.

Purdue Research Foundation

Hewlett-packard Company

Other

Xerox Corporation

Samsung Electronics Co., Ltd.

Eastman-kodak Company

The United States of America As Represented by the United States

Oce-technologies B.v.

Hewlett-packard Indigo B.v.

Jan Philip Allebach

Mark Q Shaw

Charles Addison Bouman

Amy Ruth Reibman

Chuohao Tang

Qian Lin

Mark Edward Shaw

Terry M Nelson

Sean Michael Collison

Zhigang Fan

Raja Bala

Jay Stephen Gondek

Carl Staelin

Hengzhou Ding

Peter Bauer

Zhenhua Hu

Paul L Jeran

Mani Fischer

Richard Eric Maggard

Shaoyuan Xu

Robert Alan Ulichney

Doron Shaked

Kurt Robert Bengtson

Edward John Delp

Omri Shacham

Tamar Kashti

Todd J Harris

Zuguang Xiao

Yafei Mao

Reiner Eschbach

Ping Wah Wong

Morgan Thomas Schramm

Utpal Kumar Sarkar

Lluis Abello Rosello

Brian J Atkins

Renee Jeanette Jessome

Yousun Bang

Yandong Guo

Minwoong Kim

Xiaoyu Xiang

Yung-Yao Chen

Madhur Gupta

Puneet Goyal

Yi Yang

Runzhe Zhang

Wan-Eih Huang

Frank W Sliz

Albert Parra

Perry Victor Lea

Dennis A Abramsohn

Ho-young Lee

Heui-keun Choh

Mark John Wibbels

Hila Nachlieli

Anthony Peter Holden

C Brian Atkins

George Tsu-Chih Chiu

Joan Vidal Fortia

Peter I Majewicz

Reuven J Sherwin

George Henry Kerby

Tal Frank

Brent Michael Bradburn

Victor D Loewen

Peter A Jansson

YouSun Bang

Yung-hsiang Lu

Dejan Depalov

Geoffrey John Woolfe

Brian C Atkins

Ildus Ahmadullin

Yotam Ben-Shoshan

Smadar Shiffman

Lixia Li

Jin-young Kim

Randall G Guay

Ellen Ochoa

Anton Wiranata

Zhen He

Allen L Frazier

Lu Wang

Hernan Ildefonso Gutierrez-Vazquez

Maria V Ortiz Segovia

Kathryn Janet Ferguson

Thyagarajan Balasubramanian

Xiaojun Feng

Kurt Robert Bengston

David C Day

Donald W Sweeney

Katelyn Christene Morse

Minki Cho

Wenyi Chen

Thanh Ha

YanFu Kuo

Chao-Lung Yang

Yuehwern Yih

Nicolas Pmf Bonnier

Seong Jun Park

Weijuan Xi

Cheng Lu

A saliency map of an image is generated. Saliency regions of the saliency map are identified. The saliency regions are merged into a combined saliency region. Candidate image crops of the image are generated based on the combined saliency region. An image crop of the image is selected from the candidate image crops using a machine learning model.

Image crop

According to examples, an apparatus may include a processor and a memory on which are stored computer-readable instructions that, when executed by the processor, may cause the processor to access a master image to be printed and receive a scanned image corresponding to the master image. The processor may identify a defect in a scanned image region of interest (ROI) based on the master image. A type of the scanned image ROI may include a raster ROI, a symbol ROI, a background ROI, and/or a color vector ROI, and the identified defect may be associated with the type of the scanned image ROI. The processor may determine a severity of the identified defect of the scanned image and may output the determined severity.

Image region of interest defect detection

An example system includes a feature extraction engine to identify features in a compressed image at a plurality of scales. The features include features corresponding to compression artifacts and features corresponding to image content to be upsampled. The feature extraction engine is to identify the features in the compressed image at a first scale based on noncontiguous pixels. The system also includes a reconstruction engine to refine the features corresponding to the image content to be upsampled and mitigate the features corresponding to the compression artifacts. The system includes an upsampling engine to generate an upsampled version of the compressed image based on the refined and mitigated features.

Image upsampling

An example device is described for facilitating polygon localization. In various aspects, the device can comprise a processor. In various instances, the device can comprise a non-transitory machine-readable memory that can store machine-readable instructions. In various cases, the processor can execute the machine-readable instructions, which can cause the processor to localize a polygon depicted in an image, based on execution of a deep learning pipeline. In various aspects, the deep learning pipeline can comprise a circular-softmax block.

Polygon localization via a circular-softmax block

In some examples, a computing device can include a processor resource and a non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause the processor resource to: identify a plurality of regions within a captured document, determine a quantity of vertical transitions and horizontal transitions within the plurality of regions, and select an output resolution for the plurality of regions based on the quantity of vertical transitions and horizontal transitions within the plurality of regions.

Output resolution selections

Example implementations relate to audio samples to detect device anomalies. For example, computing device, comprising: a processing resource and a non-transitory computer readable medium storing instructions executable by the processing resource to: generate a matrix of audio information for a plurality of audio samples of a device, select audio information from one of the plurality of audio samples, generate a plurality of principal components for the selected audio information utilizing a principal component expansion, select a principal component from the plurality of principal components based on a quantity of variance, and detect an anomaly of the device based on a comparison between a real time audio sample of the device and the selected principal component.

Audio samples to detect device anomalies

An example system includes: a landmark detection engine to detect landmark positions of landmarks in images based on facial detection; an optical flow landmark engine to determine the landmark positions in the images based on optical flow of the landmarks between the images; a landmark difference engine to determine, for a landmark in a given image: a distance between a detected landmark position and an optical flow landmark position of the landmark; and a weighted landmark determination engine to determine, for a first and second image, a position for the landmark in the second image based on: a respective detected landmark position and a respective optical flow position of the landmark in the second image; and respective distances, determined with the landmark difference engine, between a first detected landmark position of the landmark in the first image and respective optical flow landmark positions for the first and second images.

Landmark temporal smoothing

In some examples, an imaging device can include a processing resource and a memory resource storing instructions to cause the processing resource to perform a feature extraction process to extract a gamut-based feature included in a plurality of pixels of a scanned image to determine whether the scanned image includes a particular marking, apply a classification model to the scanned image, and optimize the scanned image based on the classification of the scanned image.

Feature extractions to optimize scanned images

An example system includes a landmark engine to detect a facial landmark in an image of a face. The system includes a comparison engine to determine a difference between the facial landmark in the image and a facial landmark of a neutral face. The system also includes an action engine to determine whether a facial action unit occurred based on whether the difference satisfies a condition.

Facial action unit detection

Examples disclosed herein relate to identifying a plurality of content areas of a document to be scanned, classifying each of the plurality of content areas into a content type, determining a minimum scanning resolution to maintain readability for each of the plurality of content areas according to the classified content type, and performing a scan of the document to a digital file, wherein each of the plurality of content areas is scanned at least at the determined minimum scanning resolution to maintain readability of the respective content area.

Determining minimum scanning resolution

A method is disclosed. In the method, color differences are calculated between a current video frame and a motion predicted version of the current video frame based on a human visual system's ability to perceive the color differences. Also, information in a difference frame is discarded based on the color differences. The difference frame includes differences between the current video frame and the motion predicted version of the current video frame.

Techniques for video compression

In some examples, a device includes a printing device to generate an image on a substrate from a digital image, and a processor to: receive a scanned image of the image on the substrate, identify a plurality of image portions of the scanned image, identify horizontal color changes across a horizontal portion of the plurality of image portions, identify vertical color changes across a vertical portion of the plurality of image portions, compare the horizontal color changes and vertical color changes to corresponding horizontal color changes and corresponding vertical color changes of the digital image, and measure a presence of color plane misregistration, and the color, direction and magnitude of misregistration based on the comparison.

Color plane misregistration determinations

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

A system generates a prediction model for makeup color matching. The system includes a data storage device and a modeling engine. The data storage device stores a plurality of color sets comprising a skin color set, a makeup color set, and a target color set. The modeling engine is coupled to the data storage device and configured to generate a prediction model and an output color set. The prediction model models generation of the target color set based on inputs from the skin color set and the makeup color set. The output color set approximates the target color set with a predictable accuracy.

Color image analysis for makeup color prediction model

Growing community of inventors

West Layfayette, IN, United States of America

Jan Philip Allebach