Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Micro Focus Lcc

Staelin, Carl

Kisilev, Pavel

Schein, Sagi

Banner, Ron

Ron Banner

Carl Staelin

Omer Barkol

Pavel Kisilev

Michal Aharon

Sagi Schein

Amir Gaash

Daniel Freedman

Shahar Golan

Inbal Tadeski

Liza Mevzos

Described herein are techniques for generating a model based on input. In an example, a first model can be generated based on decomposing a rating matrix into a product of two matrices U and V, where U represents correlations between users and a plurality of factors and V represents correlations between items and the plurality of factors. At least some of the users and items can be grouped into groups according to the correlations. Input on one or more of the groups can be received. A second model can be generated based on the input on the one or more of the groups.

Generating a model based on input

Disclosed herein are a system, non-transitory computer readable medium, and method for responding to a query having a plurality of input objects. A subgraph based on a main graph of objects is used to generate a list of objects associating the input objects.

Reading object queries

Systems and methods for prioritizing print jobs of different families within a print job batch are provided. Such a system may include, for example, an input/output port and a processor. The input/output port may output a print job batch including at least one print job of a first family and at least one print job of a second family. The processor configured may determine the order of priority of the print job batch based at least in part on a first trend of expected differences in setup times between print machines when the first family is prioritized before the second family and a second trend when the second family is prioritized before the first family.

System and method for prioritizing print jobs in a batch

An image registration method to register a target image with a reference image is provided, including to determine a target set of features present in the target image, to determine a reference set of features present in the reference image, to generate respective signatures for each feature in the target and reference sets, to match features from the target set to corresponding features in the reference set using the signatures, to generate respective transformations to map pairs of features in the target set to corresponding pairs of features in the reference set, and determine a similarity transformation for the target image using a measure of the accuracy of the transformations.

Image registration

Systems and methods are provided for scheduling print jobs in a print service provider (PSP). In particular, embodiments include accessing a first set of data relating to processing times for a plurality of machines of a print service provider (PSP). The processing times relate to specific print jobs or types of print jobs sharing print job characteristics. In addition, embodiments include accessing a second set of data relating to setup times for the plurality of machines of the PSP. The setup times relate to specific sets of two print jobs or sets of two types of print jobs sharing print job characteristics. Further, embodiments include determining an order of processing for a plurality of print jobs based on the first and second sets of data.

Scheduling for digital commercial print workflows

A method and apparatus () is provided for estimating blur degradation of an image () that includes a specular highlight. A specular highlight in the image is first identified (), for example with user assistance. A blur kernel is then derived by extracting (A) the identified specular highlight as foreground from the image () and using the extracted foreground as the blur kernel (C). The image () can then be deblurred by deconvolution () with the derived blur kernel.

Estimating blur degradation of an image using specular highlights

A method for determining with a physical image processing device a visual balance of an image includes assigning a visual weight point to each of a plurality of visual elements within the image with the image processing device, each visual weight point having a weight value based on visual properties associated with the visual element, and determining the visual balance of the image with the image processing device by measuring a vector value at a center of the composition, the vector value being based on a distance of each visual weight point from the center and the weight value associated with each visual weight point.

Determining a visual balance of an image

A method of reducing blurring in an image of size greater than M columns by N rows of pixels, comprises deriving a blur kernel k representing the blur in the image, and deriving an inverse blur kernel k. The inverse blur kernel is given by (I) where h(m) is the sum of the first m terms of the series (II) &#x3b4; is the Dirac delta, m is greater than 1, and h(m) is a two dimensional matrix of size M&#xd7;N. The two dimensional matrix h(m) is convolved with the image over the whole image in the image pixel domain to produce an image with reduced blur. The method may be applied to a video sequence allowing the sequence of images to be deblurred in real time.

Real-time video deblurring

Automated imposition wherein a print job comprises multiple documents, and the documents comprise pages having different dimensions. Pages of different dimensions of the same document may be imposed on a single sheet, and pages of equal dimensions may be lined up in a layer across the sheet, forming a cut line along the layer and across the sheet.

Automated imposition

Method and system embodiments of the present invention are directed to restoration of corrupted images using spatial-domain image-processing methods that can effectively employ spatial-domain information both in order to avoid various types of artifacts and distortions produced by frequency-domain image-processing operations and to achieve computational efficiency. The various method and system embodiments of the present invention employ a family of penalty functions to constrain iterative restoration images corrupted by both deterministic corruptions, such as motion-induced blur and blurring due to optical misalignment, incorrect positioning of optical components, and defective optical components as well as essentially non-deterministic noise corruption introduced at various stages of image acquisition, image encoding, image storage, and image transmission.

Method and system for image restoration in the spatial domain

A deblurred digital image is generated from a blurred digital image. The blurred digital image is received. The blurred digital image has a number of objects and a number of edges. Each edge demarcates boundaries of two of the objects. One or more selected edges within the blurred digital image are identified. The selected edges are blurry within the blurred digital image but were originally sharp edges. A blur kernel is determined based on the identified selected edges. The blur kernel denotes how the blurred digital image is blurry. The blur kernel is applied to the blurred digital image to generate the deblurred digital image. The deblurred digital image is output.

Blurred digital image deblurring

In a method for estimating a point spread function of an image capture device, a first function representing a captured version of a first test image is obtained, where the first test image containing a substantially ideal vertical transition. A second function representing a captured version of a second test image is also obtained, where the second test image contains a substantially ideal horizontal transition. In addition, the point spread function is estimated from the first function and the second function. Also disclosed herein is a method for image degradation compensation that employs the method for estimating a point spread function.

Estimating a point spread function of an image capture device

A method for reducing blur from an image is described. The method includes accessing a blurred image, wherein the blurred image has a width and a length that can be different. The method further includes converting the blurred image into a frequency domain representation of the blurred image and determining an angle of blur from the frequency domain of the blurred image. The method further includes rotating the frequency domain representation of the blurred image by the angle of blur and determining a size of the blur from the rotated frequency domain representation of the blurred image. The method further includes determining a blur kernel associated with the blur, the blur kernel comprising the angle of blur and the size of said blur and de-convoluting the blurred image according to the blur kernel to reduce the blur.

Growing community of inventors

Haifa, Israel

Ron Banner