Palo Alto Research Center Inc.

Xerox Corporation

Cisco Technology, Inc.

Juan Liu

Daniel H Greene

James E Reich

Qingfeng Huang

Robert Roy Price

Marc E Mosko

Johan De Kleer

Eric Scott Hamby

Ajay Raghavan

Haitham Hindi

Lukas Daniel Kuhn

Ying Di Zhang

Wei Zhang

James M A Begole

Maurice Kyojin Chu

Lalit Keshav Mestha

Takashi Matsumoto

Rong Zhou

Eric Saund

Craig Eldershaw

Daniel Davies

Minh Binh Do

Rajinderjeet Singh Minhas

Kenneth J Mihalyov

Feng Zhao

Tim C Schmidt

Hoda Eldardiry

Evgeniy Bart

Gabriel M Hoffmann

Hoda M A Eldardiry

Xenofon Koutsoukos

David Garcia

Jie Liu

Johan Dekleer

Hermann Calabria

Aaron Creighton Wilson

Kelly L Coupe

Chuanjiang Luo

Arpita Ghosh

Ying Zhang

Lukas Kuhn

A computer-implemented system and method for discovering heterogeneous communities with shared anomalous components is provided. A graph is obtained that includes vertices representing entities that are connected by edges representing associated with the entities represented by the connected vertices. The vertices are associated with collections of words of different categories, each of the words describing an item associated with at least one of the events. Each of the vertices is further associated with topics describing a type of activity of the entity represented by that vertex. Communities within the graph are identified, each including at least two of the connected vertices. Identified as anomalous are categories of words whose removal from the collections associated with the vertices in a community increases a likelihood of that community being associated and the collections of the words associated with the community vertices.

Computer-implemented system and method for discovering heterogeneous communities with shared anomalous components

A method () is provided for characterizing a functionality of a flash () from at least one image () captured with a camera () using the flash (). The method () includes: analyzing the image () by segmenting () the image () into at least one sub-region (), and applying a metric () to the sub-region () to measure an image property within the sub-region (); and determining () the functionality of the flash () in response to a result of the applied metric.

Flash characterization for camera

One embodiment of the present invention provides a system for multi-domain clustering. During operation, the system collects domain data for at least two domains associated with users, wherein a domain is a source of data describing observable activities of a user. Next, the system estimates a probability distribution for a domain associated with the user. The system also estimates a probability distribution for a second domain associated with the user. Then, the system analyzes the domain data with a multi-domain probability model that includes variables for two or more domains to determine a probability distribution of each domain associated with the probability model and to assign users to clusters associated with user roles.

Detecting anomalies in work practice data by combining multiple domains of information

A method for detecting a persistent change in a dynamically varying scene includes: obtaining a set of reference images of the scene; transforming the reference images into an abstract feature space; classifying pixels of the reference images in the abstract feature space; generating a stable reduced-reference image based on the classifications of corresponding pixels; obtaining a set of test images of the scene; transforming the test images into the abstract feature space; classifying pixels of the test images in the abstract feature space; generating a stable test image based on the classifications of corresponding pixels; and comparing the stable reduced-reference and test images to one another to detect a difference therein, the difference corresponding to a persistent change in the dynamically varying scene occurring between when the reference images and the test images were obtained.

Automatic detection of persistent changes in naturally varying scenes

A system for compiling a machine operable diagnostic system includes a header unit, a component unit, an effects unit, a test unit, and an instantiation unit. The header unit identifies general properties of a system from a generic description in an electronic format which includes at least one category of a plurality of variations. The component unit identifies a plurality of components of a modeled system from the generic description, and adds and separates the plurality of variations to the plurality of components, and each identified component includes at least one type of failure and a probability of the at least one type of failure. The effects unit identifies from the generic description a plurality of observable effects. The test unit identifies a plurality of tests and test outcomes designed to elicit the observable effects. The instantiation unit constructs a procedural instantiation of the machine operable diagnostic system.

Generic programming for diagnostic models

One embodiment of the present invention provides a method and apparatus for enabling extensibility in sensing systems. The distributed sensing system comprises a number of sensor nodes, a device database, a sensing module registry, a sensing needs monitor, and an automatic composer. The device database is in communication with at least one sensor node and configured to maintain physical information on at least one sensor node. The sensing module registry is configured to maintain a registry of a number of software modules that are available for extracting information from sensor data. The sensing needs monitor is configured to maintain a list of context pairs that represent a number of sensing needs of a sensing application. The automatic composer is configured to generate a composition of software modules, at runtime, to realize the sensing needs of users and applications.

System and method for enabling extensibility in sensing systems

A method () is provided for detecting an obstruction within a field of view of a camera () from an image () captured by the camera (). The method () includes: analyzing the image () by applying edge detection () to the image (), identifying () regions of the image () lacking edge content and comparing () a size of the identified regions to a threshold; and determining if there is an obstruction based upon a result of said comparison.

Detection of near-field camera obstruction

The presently disclosed embodiment provides an interactive tool for printed image artifact characterization that successfully combines the advantages from both a human visual system and automated image quality characterization. In the interactive tool provided, the user may specify coarse level information, such as the region of interest in a print image, to be examined by the automated image-quality characterization algorithm, which can then employ sophisticated algorithms, e.g. signal processing, feature extraction, estimation and classification, to find precise fine-level descriptors.

Interactive tool for incorporating user input and feedback in image quality related diagnosis

A method for specifying utility in an information delivery system having data sources and receiving nodes includes specifying utility for a set of possible information delivery patterns of data samples, where the specification of the utility depends on characteristics of delivery patterns observed by a receiving node, if any, located at a specified location.

Specifying predicted utility of information in a network

The present disclosure is generally related to the field of printing, and other processes based on the continuous deposition of material, including industrial molding or extrusion processes, and more particularly to techniques for grouping object quality anomalies in a specified region of an object based on context-specific characterization and shared descriptive profile features.

Robust recognition of clusters of streaks at multiple scales

A system which generates a floor plan of a building includes: a camera which obtains a series of images as it is moved, each image represented by a first data set representing color and a second 3D data set representing depth. A processor generates the floor plan from the image data, defined by polylines that represent structures of the building and polygons that represent an area which has been observed by the camera. Suitably, the processor: performs a local matching sub-process which is operative to align two adjacent images with one another; performs a global matching sub-process in which key images and registered to one another; finds a 2D subset of points from the image data associated with each image, corresponding to a plane defined therethrough; determines the polylines based on said subset of points; and defines the polygons based on the polylines and a determined pose of the camera.

Apparatus and method for creating floor plans

A computer based method and system for tiered inference multiple fault diagnosis is provided. The method includes using a computer processor to dissect a hypothesis space representing a production system having a plurality of production modules into tiers. Production modules in the current tier are partitioned into a group or a set of sub-groups. A fault diagnosis algorithm is applied to the group of each sub-group to identify an acceptable fault diagnosis. When no acceptable fault diagnosis is found, the process moves to the next tier to perform further investigations. The process continues to move to higher tiers until an acceptable fault diagnosis is obtained or the system instructs the process to end.

Computationally efficient tiered inference for multiple fault diagnosis

Methods and systems are presented for characterizing a color rendering system or a color marking material design process, in which forward color transform parameters are generated for mapping color from a first color space associated with an internal color representation of the color rendering system or marking material design process into a second color space using a least squares minimization of an error metric weighted according to a Taylor series expansion of the error metric.

Color characterization model computation using weighted least squares minimization

Methods and systems are presented for characterizing printer streaking using a basis selection algorithm to determine parameters set for a streak template that best approximate a density profile derived from a scanned printed test image, with wavelet decomposition used to expedite the searching for position and width parameters.

Method and apparatus for characterizing printer streaking

Methods and systems are presented for characterizing a printer, display or other color reproduction device in which a forward color transform having a parametric surface forward color transform and a nonparametric residual forward color transform is updated by adapting the parametric surface forward color transform using an input adaptation data set and a measured adaptation data set, generating a prediction data set in the second color space using the adapted parametric surface forward color transform and the nonparametric residual forward color transform, generating a prediction error data set in the second color space using the input adaptation data set and the prediction data set, generating a membrane forward color transform using the prediction error data set, and updating the forward color transform using the adapted parametric and nonparametric forward color transforms.

Growing community of inventors

Milpitas, CA, United States of America

Juan Liu