Hewlett-packard Development Company, L.P.

Hewlett-packard Company

Darryl Greig

Carl Staelin

Ruth Bergman

Mani Fischer

Shlomo Harush

Oded Shmueli

Daniel Maack Bloom

Marie Vans

Gregory Braverman

Clay Jessen

Doron Shaked

Maurizio Pilu

Ron Maurer

Hila Nachlieli

Eyal Shelef

Gitit Ruckenstein

Michael Elad

Eyol Shalef

Manl Flacher

Tami Tamir

Disclosed are embodiments for determining detection certainty in a cascade classifier (). A first sequence () of detection stages () determines whether an image () is associated with a rare object. Each of the stages () rejects the image () when the image () is unassociated with the rare object and propagates the image () to a next stage () when the image () is unrejected. A second sequence () of detection stages () is configured for post-processing operation. If the image () is unrejected in a final stage () of the first sequence (), the second sequence () determines whether the image () is associated with the rare object. Each of the stages () propagates the image to a next stage (), recording a rejection when the image () is unassociated with the rare object. A probability that the image () is associated with the rare object is determined.

Determining detection certainty in a cascade classifier

Systems, methods, and other embodiments associated with increasing face detection speed are described. One example method includes determining whether to control a face detection process to selectively perform a face detection in a patch in a digital image. The face detection may be based, at least in part, on determining whether the patch overlaps a face previously identified by the face detection process. The example method may also include providing a signal to control the face detection process to perform the face detection upon determining that a patch overlap does not exceed an overlap factor.

Increasing face detection speed

Systems and methods are disclosed that determine a largest patch size to traverse a digital image, analyze the digital image to detect one or more first objects of a size approximately the same as the largest patch size, and discontinue analyzing the digital image when the digital image includes the first object(s) of a size approximately the same as the largest patch size. The patch size is decremented to progressively smaller patch sizes if the first object(s) of a size approximately the same as the largest patch size is not detected and the digital image is further analyzed to detect one or more first objects of a size approximately the same as the smaller patch size until the first object(s) are detected or the patch size is decremented below a predetermined smallest size.

Systems and methods to increase speed of object detection in a digital image

A method of pre-processing an image to identify processes for subsequent processing of the image, comprising the steps of:

Pre-filter for object detection

A method of tracking an object such as a face in a video stream comprises running an object detector at a plurality of locations on a first frame, defining a coarse grid. This is repeated for second and subsequent frames, with the grid slightly offset each time so that, ultimately, all of the points on a fine grid are covered but in several passes. When an object such as a face is located on one frame, positional and/or scale information is propagated to the next frame to assist in the tracking of that object onto the next frame.

Method of tracking an object in a video stream

Detectors capable of accurately detecting and tracking moving features of such as faces within a video stream are sometimes too slow to be run in real-time. The present invention rapidly scans video footage in real-time and generates a series of preattemptive triggers indicating the frames and locations within the frames at our deserving of further investigation by a sub real-time detector. The triggers are generated by looking for peaks in a time variant measure such as the amount of symmetry within a frame or portion of a frame.

Method of triggering a detector to detect a moving feature within a video stream

A method of annotating audio-visual data is disclosed. The method includes detecting a plurality of facial expressions in an audience based on a stimulus, determining an emotional response to the stimulus based on the facial expressions and generating at least one annotation of the stimulus based on the determined emotional response.

Annotating stimulus based on determined emotional response

Systems and methods of face and skin sensitive image enhancement are disclosed. In one aspect, a face map that includes for each pixel of an input image a respective face probability value indicating a degree to which the pixel corresponds to a human face is calculated. A skin map that includes for each pixel of the input image a respective skin probability value indicating a degree to which the pixel corresponds to human skin is ascertained. The input image is enhanced with an enhancement level that varies pixel-by-pixel in accordance with the respective face probability values and the respective skin probability values. In another aspect, a facial content measurement value indicating a degree to which an input image contains human face content is ascertained. A tone-correction process is tuned in accordance with the facial content measurement value. The input image is enhanced in accordance with the tuned tone-correction process.

Face and skin sensitive image enhancement

A method for a digital printing press includes estimating a developer voltage by applying a developer voltage estimation model to measurements of state parameters of the digital printing press.

Ink thickness consistency in digital printing presses

A neural network is trained with input data. The neural network is used to rescale the input data. Errors for the rescaled values are determined, and neighborhoods of the errors are used adjust connection weights of the neural network.

Neural network trained with spatial errors

The present invention generally provides methods and systems for printing. A statistical learning system is used to determine dot gain.

Systems and methods for dot gain determination and dot gain based printing

A method of quickly and automatically comparing a new document to a large number of previously seen documents and identifying the document type. First, provide a plurality of document type distributions, each document type distribution describes layout characteristics of an independent document type and may include a plurality of data points. Each document type distribution includes data derived from at least one basis document signature which may include data defining pixels of a low-resolution image of the independent basis document resolved to between 1 and 75 dots per inch or may include document segmentation data derived from the independent basis document. Next provide a new electronic document. Then create new document signature from the new electronic document. Next, distances between the new document signature and each of the plurality of document type distributions are calculated using an algorithm based on a Bayesian framework for a Gaussian distribution. The distances calculated may be Euclidean distances or may be Mahalanobis distances. Additionally, calculating the distances may include weighting the value given each of a plurality of data points in the document signatures based on the usefulness of each of the plurality of data points in distinguishing between the document signatures. Next, select at least one candidate document type for the new electronic document from among the independent document types described by the plurality of document type distributions. The selection of the at least one candidate document type may include selecting a preselected fixed number of the independent document types or may include selecting the independent document types described by those of the plurality of document type distributions having calculated distances that are within a preselected threshold distance of the smallest of the distances calculated. In addition, the invention provides for a program storage medium readable by computer, tangibly embodying a program of instructions executable by the computer to perform the method steps described above.

Automatic categorization of documents using document signatures

A method of automatically extracting metadata from a document. The method of the invention provides a computer readable document that includes blocks comprised of words, an authority list that includes common uses of a set of words, and a neural network trained to extract metadata from groupings of data called compounds. Compounds are created with one compound describing each of the blocks. Each compound includes the words making up the block, descriptive information about the blocks, and authority information associated with some of the words. The descriptive information may include such items as bounding box information, describing the size and position of the block, and font information, describing the size and type of font the words of the block use. The authority information is located by comparing each the words from the block to the authority list. The compounds are processed through the neural network to generate metadata guesses including word guesses, compound guesses and document guesses along with confidence factors associated with the guesses indicating the likelihood that each of the guesses is correct. The method may additionally include providing a document knowledge base of positioning information and size information for metadata in known documents. If the document knowledge base is provided, then the method includes deriving analysis data from the metadata guess and comparing the analysis data to the document knowledge base to determine metadata output.

Growing community of inventors

Bristol, United Kingdom

Darryl Greig