Xerox Corporation

Conduent Business Services, LLC

Alvaro Enrique Gil

Lalit Keshav Mestha

Yao Rong Wang

Martin Sidney Maltz

Zhigang Fan

Wencheng Wu

Edul N Dalal

Lina Fu

Matthew Frederick Hoffmann

Raja Bala

Peter A Crean

James Michael Sanchez

Himanshu Madhu

Connie F Purdum

Guangyu Zou

Prudhvi Krishna Gurram

Stuart Alan Schweid

Palghat Srinivas Ramesh

Daniel W Costanza

Timothy Wayne Jacobs

Rakesh Suresh Kulkarni

Frederick John Ramsey

J Michael Sanchez

According to embodiments illustrated herein, a method is provided for designing an image-analysis task. The method includes receiving one or more first target values of one or more output parameters of the image-analysis task from a requester through a GUI. Thereafter, one or more first values of one or more input parameters, associated with the image-analysis task, corresponding to the one or more first target values are determined based on the one of more first target values and a model. The model corresponds to a relationship between the one or more input parameters and the one or more output parameters. Further, the one or more first values of the one or more input parameters are presented to the requester through the GUI. The requester at least provides one or more second target values of the one or more output parameters through the GUI, based on the presentation.

Methods and systems for designing of tasks for crowdsourcing

A method and system for providing a feedback based dynamic pricing algorithm with an embedded controller for a HOT (High Occupancy Toll) lane. An input-output transfer function of a vehicle flow with respect to a HOT lane can be obtained utilizing a simulation module. A feedback controller combined with, for example, a Smith predictor can be designed to avoid an unstable behavior due to a time delay in the HOT lane, a price regulation, and a large transient caused by an integral part of the controller due to traffic jams. A driver behavior preference model can be derived based on a relationship between a toll rate and several characteristics of the HOT lane and a general purpose lane. The feedback controller and the behavior preference model can then be implemented to set the toll rate in real-time in order to satisfy a desired performance metric.

Method and system for providing dynamic pricing algorithm with embedded controller for high occupancy toll lanes

A system and method include a printing system with printing modules through which print media is transferred. The printing modules include sensors and a fault detection component. A printing system includes a fault identification system (FIS) and a scheduler. The FIS includes, a machine learning component, a Dependency-matrix component and an optimal search component. The optimal search component repeatedly implements a Rate of Return (ROR) that links the probabilities of occurrences of faults to a priori probabilities of faults and a detection function of the ROR to elements of the D-matrix, determines a ROR value, provides a benefit, and sends one more test to a scheduler of the printing system, which then physically implements the one more test. The prior steps are repeated until a stopping condition is reached and a fault is diagnosed.

Fault identification for a printing system

Methods and systems for creating statistical model. Values of at least one output parameter corresponding to each combination of values of a set of input parameters are collected. The at least one output parameter and the set of input parameters are associated with one or more crowdsourcing tasks. Each combination of the values of the set of input parameters is determined based on at least one of one or more design of experiments or a historical data. Further, a distribution of the values of the at least one output parameter is determined. The statistical model is created based on the values of the set of input parameters and one or more characteristics associated with the distribution of the values of the at least one output parameter.

Methods and systems for modeling crowdsourcing platform

A print job processing system determines a set of job size thresholds for a set of print jobs received over a period of time by a print shop. The print shop includes multiple cells. The system orders the job size thresholds from lowest to highest, assigns the lowest job size threshold to a first one of the cells, assigns the highest job size threshold to a second one of the cells, and assigns each of the remaining thresholds to the remaining cells so that each of the cells has an assigned threshold. Then, when the system receives a print job, it determines a size for the received print job, identifies which of the cells has an assigned job size threshold that corresponds to the size of the received print job, and routes the received print job to the identified cell. The identified cell may then process the received print job.

Method and system for print shop job routing

This disclosure provides spot color control methods, apparatus and systems. According to one exemplary embodiment, disclosed is a method of generating device dependent color recipes for a plurality of printing devices. The method includes generating a first device dependent recipe for a target color for rendering on a first printing device, and generating a second device dependent recipe for the target color for rendering on a second printing device, whereby the second device dependent recipe is a function of the first device dependent color recipe.

Spot color control method, apparatus and system

What is disclosed is a method for profile LUT construction which uses a cost function to provide improvements to one or more image quality attributes present in printed images while imposing constraints in terms of color accuracy and spectral response to achieve a color match under various illuminants. Image quality attributes are selected. A reference profile is selected. For each node, candidate recipes are found which reproduce L*a*b* colors within a threshold e. Recipes are pruned to a subset containing recipes where a spectral difference between a predicted spectra corresponding to N color levels and a reference reflectance spectra corresponding to a spectra of a recipe produced by the reference profile, is less than a threshold. A cost function is computed and a recipe identified which minimizes the cost for this node. The process repeats for all nodes to produce a new profile LUT.

Generating an image profile LUT for a N-color marking device via multi-objective cost minimization

What is disclosed is a method for determining a color solution which achieves color objectives for a color marking device involves performing the following. In one embodiment, N objectives of interest are identified for a color marking device and a N-dimensional Pareto Front is constructed which comprises a collection of color solutions which accommodates those objectives. The Pareto Front is constructed using an optimization process based upon printer models of the objectives. Color solutions can be at least one color recipe, or a combination of color recipes and process actuators. A target point is selected in an N-dimensional objective space based upon at least one user-selected preference. The target point is then mapped to a point on the Pareto Front. The mapping identifies one of the color solutions which, in turn, is used to generate a spot color for the device. The generated spot color achieves the user-selected preference.

Using a Pareto Frontier to find an optimal color solution for spot calibration

A method for processing black point compensation parameters for a color image to be printed so as to enhance image quality of the color image is provided. The method includes converting a received color image to a gray scale image; determining, using the received color image and the gray scale image, a performance attribute to estimate the effect of the black point compensation parameters on the image quality of the received color image, respectively; deriving a model to estimate relationships between the black point compensation parameters and the determined performance attribute; maximizing the performance attribute of the derived model so as to process the black point compensation parameters for the color image; and using the processed black point compensation parameters to construct output device profiles.

Method and system for optimizing black point compensation parameters

A method for processing black point compensation parameters for a color image to be printed so as to enhance image quality of the color image is provided. The method includes analyzing image content of a received color image to identify one or more performance attributes to be considered during a black point compensation parameters processing procedure, the performance attributes estimate an effect of the black point compensation parameters on the image quality of the received color image; selecting, based on the identified performance attributes, a black point compensation (BPC) algorithm to be used during the processing procedure; deriving a model using the identified performance attribute that is configured to estimate relationships between the black point compensation parameters and the identified performance attribute; maximizing the performance attribute of the derived model so as to process the BPC parameters for the color image; and using the processed black point compensation parameters to construct output device profiles.

What is disclosed is a novel system and method for mapping out-of-gamut colors to a device's gamut to improve image quality in a color document reproduction device involves performing the following. First, an out-of-gamut color x, which is intended to be mapped to a boundary surface of a color gamut of a color marking device, is selected. A gamut mapping function is also selected. The selected gamut mapping function is intended to be applied to the selected out-of-gamut color point. At least one performance attribute is then selected for the color marking device and a multi-objective cumulative cost Jis determined based upon a combination of costs Jand J. The multi-objective cumulative cost Jis then iteratively driven to a minimum. Once the minimum has been determined, a gamut mapping of the selected out-of-gamut color can then be performed using the minimized multi-objective cumulative cost. Various embodiments are disclosed.

Attribute driven gamut mapping via a minimized multi-objective cumulative cost function

What is disclosed is a system and method for image reconstruction using a compressed sensing framework to increase the number of wavelength bands in hyperspectral video systems. The present method utilizes a restricted representation matrix and sampling matrix to reconstruct bands to a very large number without losing information content. Reference multi-band image vectors are created and those vectors are processed in a block-wise form to obtain custom orthonormal representation matrices. A sampling matrix is also constructed offline in the factory. The compressed sensing protocol is applied using a l-norm optimization (or relaxation) algorithm to reconstruct large number of wavelength bands with each band being interspersed within the band of interest that are not imaged. The teaching hereof leads to very large number of bands without increasing the hardware cost.

Hyperspectral image reconstruction via a compressed sensing framework

A switching controller system and method for improving graininess in an image during a profile construction. A switching control strategy can be employed to construct an ICC destination profile by switching between a first controller (e.g., a 3-input 4-output controller) and a second controller (e.g., a 3-input 3-output controller) based on a color space region that requires a graininess minimization. The first controller dynamically modifies the CMYK values until reaching a subset of LAB values contained in the ICC profile. The second controller varies three colorants and holds a remaining colorant of the CMYK values until reaching the remaining LAB values in the ICC profile. Such an approach reduces the graininess and provides an improved smoothness with respect to the image during the ICC profile construction.

Switching controller system and method for improving image graininess during color management profile construction

Differences between an offline spectrophotometer and an inline spectrophotometer can result in differences between a hardcopy target color and a printed reproduction of that color. The inline spectrophotometer is inside of a printer and configured to measure printer output. As such, the inline spectrophotometer cannot conveniently measure the hardcopy target color. A printing error or an instrument offset can be determined and passed to a color correction module that updates the device dependent color specification associated with the given spot color. This color specification may be stored, for example, in the printer controller, and used when a document subsequently calls for that spot color, thereby providing accurate color reproduction from that particular printer incorporating that particular inline spectrophotometer.

Minimizing spectrophotometer impact on spot color accuracy

A methodology is disclosed to achieve adaptive illumination independent matching of out-of-gamut spot colors. In one embodiment, the methodology includes an iterative process to determine a variety device specific recipes for out-of-gamut spot colors across different illumination spectra and gamut mapping techniques, and then automatically choosing and/or recommending the optimal recipe and gamut mapping technique that provides the lowest color dispersion across a variety of illuminants under consideration.

Growing community of inventors

Rochester, NY, United States of America

Alvaro Enrique Gil