Koninklijke Philips Corporation N.v.

U.S. Philips Corporation

Philips Intellectual Property & Standards Gmbh

Eric Thelen

Stefan Besling

Jan Kneissler

Holger R Scholl

Meinhard Ullrich

Juergen Weese

Jochen Peters

Helko Lehmann

Peter Beyerlein

Andreas Kellner

Gundolf Kiefer

Heribert Wutte

Reinhold Hab-Umbach

Steven DeJarnett

Ali Majidi

The invention describes a method for controlling a display, which method comprises the steps of displaying a portion of a visual presentation (VP) on the display () and aiming a pointing device () comprising a camera () at a target area (A) to indicate a target (P) in the visual presentation (VP), whereby the target (P) may be inside or outside of a portion () of the visual presentation (VP) currently visible on the display (). An image () of the target area (A) aimed at by the pointing device () is generated and interpreted to determine the location of the target (P) within the visual presentation (VP). The visual presentation (VP) is adjusted as necessary to display that portion of the visual presentation (VP) which encompasses the target (P). The invention also describes a pointing device (), a display control interface () and a system comprising such a pointing device () and display control interface () suitable for applying this method.

Method and system for controlling a display

The invention describes a method of controlling a position (x', y&#x2032;) of a control point (c) on a command area (A). This method comprises the steps of: Moreover the invention describes an adequate system and a pointing device () for controlling a control point position (P) on a command area (A).

Method of controlling a control point position on a command area and method for control of a device

The invention describes a method of controlling a position (x', y&#x2032;) of a control point (c) on a command area (A). This method comprises the steps of: &#x2014;aiming a pointing device () comprising a camera () in the direction of the command area (A); &#x2014;generating an image (I) of a target area (A) aimed at by the pointing device; &#x2014;processing the target area image (I) to determine a target point (T) at which the pointing device () is aimed; &#x2014;determining position (x&#x2032;, y&#x2032;) of the control point (C) according to the position (x, y) of the target point (T) within a currently defined control area (A), which control area (A) includes at least partially the command area (A). Moreover the invention describes an adequate system and a pointing device () for controlling a control point position (P) on a command area (A).

A method, computer program and device for creating a viewing protocol for medical images is described. At least a first site of interest is identified in a medical imaging data set captured from the patient. Patient record data or computer assisted detection information can be used to identify the site of interest, which may be a potential lesion. A viewing protocol for displaying medical images to a user is planned. The viewing protocol includes a viewing path along which an image of the site of interest will be displayed. The viewing protocol also includes a trigger associated with the site of interest. When the trigger event is encountered the dynamic mode of image display is reconfigured to dynamically highlight the site of interest. The viewing protocol can then be used to control the display of images so as to provide, for example, a virtual endoscope.

Medical image viewing protocols

The invention describes a method for control of a device (). The method comprises visually presenting a number of user options for the device to be controlled (), aiming a pointing device () comprising a camera () at the visual presentation () of the user options to choose a desired option, generating an image () of a target area () aimed at by the pointing device () and comparing the target area image () with a pre-defined template of the visual presentation () to determine the chosen option.

Method and system for control of a device

A system and a method for program recommendation are described. In order to present a user a recommendation for a choice of audio or video content pieces broadcast consecutively at a plurality of different channels, (a) piece scores of content pieces are calculated, indicating a match of a corresponding content description with a profile, (b) and sequence scores are calculated for a plurality of sequences of content pieces, said sequence scores being based at least on said piece scores and on a correlation of content descriptions of at least two pieces contained in the sequence. A recommended sequence is chosen according to the sequence score. Preferably, one or, more preferred sequences are shown to the user in a lattice representation.

Program recommendation system

In a method in which an information unit ( ) enabling a speech input is stored on a server ( ) and can be retrieved by a client ( ) and in which the client can be coupled to one or more speech recognizers ( ) through a communications network ( ), the information unit ( ) is assigned additional information ( ) which is provided for determining a combination of a client ( ) for recognizing an uttered speech signal and at least one of the speech recognizers ( ), to dynamically assign the speech recognizers ( ) in a communications network ( ) to the information units ( ) and thus ensure an acceptable processing time for the recognition of a speech input with a high recognition quality.

Method of speech recognition

With a method of and an arrangement for speech recognition a measurement of the speech velocity rate is carried out in a measuring unit ( ) so as to reduce the error rate of the recognition result, which speech velocity is announced to the speaker via an output unit ( ) and warning is given if the velocity is out of speech recognition adaptation range.

Method of an arrangement for speech recognition with speech velocity adaptation

A huge vocabulary speech recognition system for recognizing a sequence of spoken words, having an input means for receiving a time-sequential input pattern representative of the sequence of spoken words. The system further includes a plurality of large vocabulary speech recognizers each being associated with a respective, different large vocabulary recognition model. Each of the recognition models is targeted to a specific part of the huge vocabulary. The system comprises a controller operative to direct the input pattern to a plurality of the speech recognizers and to select a recognized word sequence from the word sequences recognized by the plurality of speech recognizers.

Speech recognition system having parallel large vocabulary recognition engines

A system includes means for creating a vocabulary and/or statistical language model from a textual training corpus. The vocabulary and/or language model are used in a pattern recognition system, such as a speech recognition system or a handwriting recognition system, for recognizing a time-sequential input pattern. The system includes means for determining at least one context identifier and means for deriving at least one search criterion, such as a keyword, from the context identifier. The system further includes means for selecting documents from a set of documents based on the search criterion. Advantageously, an Internet search engine is used for selecting the documents. Means are used for composing the training corpus from the selected documents.

Vocabulary and/or language model training

A distributed pattern recognition system includes at least one user station and a server station. The server station and the user station are connected via a network, such as Internet. The server station includes different recognition models of a same type. As part of a recognition enrolment, the user station transfers model improvement data associated with a user of the user station to the server station. The server station selects a recognition model from the different recognition models of a same type in dependence on the model improvement data. For each recognition session, the user station transfers an input pattern representative of time sequential input generated by the user to the server station. The server station retrieves a recognition model selected for the user and provides the retrieved recognition model to a recognition unit for recognising the input pattern using the recognition models.

User model-improvement-data-driven selection and update of user-oriented recognition model of a given type for word recognition at network server

For speech recognition a new word is represented as based on a stored inventory of models of sub-word units. First a plurality of utterances are presented that all should conform to the word. For building a word model from the utterances, these are represented by a sequence of feature vectors. First, the utterances are used to train a whole-word model that is independent of the models of the sub-word units. The length of the whole-word model equals the average length of the utterances. Next, a sequence of Markov states and associated probability densities of acoustic events of the whole-word model is interpreted as a reference template represented by a string of averaged feature vectors. Finally, the string is recognized by matching to models in the inventory and storing a recognition result as a model of the utterances.

Growing community of inventors

Aachen, Germany

Eric Thelen