International Business Machines Corporation

Giridharan R Iyengar

Jonathan Bruno Rohrer

Leiguang Gong

Chalapathy Venkata Neti

Dimitri Kanevsky

Edward Emile Kelley

Sara H Basson

Arnon Amir

Ganesh Nachiappa Ramaswamy

Ran D Zilca

Gerasimos Potamianos

Sarah Louise Conrod

Philippe De Cuetos

Harriet J Nock

A system and method for recognizing and labeling anatomical structures in an image includes creating a list of objects such that one or more objects on the list appear before a target object and setting the image as a context for a first object on the list. The first object is detected and labeled by subtracting a background of the image. A local context is set for a next object on the list using the first object. The next object is detected and labeled by registration using the local context. Setting a local context and detecting and labeling the next object are repeated until the target object is detected and labeled. Labeling of the target object is refined using region growing.

System and method for automatic recognition and labeling of anatomical structures and vessels in medical imaging scans

A method for optimizing images, the method comprising, receiving a designation of a first feature of interest, receiving a designation of a second feature of interest, receiving a target image, receiving an atlas image including labels of first and second features of interest of the target image and a first optimization parameter associated with the first feature of interest and a second optimization parameter associated with the second feature of interest, mapping the atlas image onto the target image resulting in a global mapped image, defining an area of the first feature of interest and an area of the second feature of interest, mapping the reference image onto the area of the first feature of interest on the global mapped image using the first optimization parameter, and mapping the reference image onto the area of the second feature of interest on the global mapped image using the second optimization parameter.

Methods involving optimizing and mapping images

Using metadata to detect alteration of data. A first set of metadata characteristics including at least one respective semantic description are recorded for a first set of data representing original data. A second set of metadata characteristics including at least one corresponding semantic description are recorded for a second set of data representing data under test. The first and second sets of metadata characteristics are compared. If the first and second sets of metadata characteristics are not identical, these sets are processed to identify locations in the first set of data that have been altered. Using the at least one semantic description for the first set of data and the at least one corresponding semantic description for the second set of data, one or more metadata characteristics that have changed from the first set of data to the second set of data are identified.

Methods, systems, and computer program products for detecting alteration of audio or image data

A computer program product includes machine readable instructions for providing enhanced video output by: receiving footage including likeness information in a plurality of modalities; demultiplexing the plurality of modalities to provide information for each modality; comparing information from at least two of the modalities for determining a correlation in the likeness information; using the correlation, obtaining semantic information for association with the likeness; and combining the semantic information with the likeness information for providing the enhanced video output. A system for implementing the computer program product includes resources for receiving the footage.

Multimodal identification and tracking of speakers in video

A method of generating a positional representation of a document, including identifying each unique term in a document and positions in the document at which the unique term appears, and for the each unique term, storing positional information derived from the positions into a positional representation.

System and method for positional representation of content for efficient indexing, search, retrieval, and compression

The use of multiple complementary classes of measure to assess face and speech consistency in video. In an exemplary embodiment, both synchrony measures and plausibility measures are employed.

Assessing consistency between facial motion and speech signals in video

A system for activating a microphone based on visual speech cues, in accordance with the invention, includes a feature tracker coupled to an image acquisition device. The feature tracker tracks features in an image of a user. A region of interest extractor is coupled to the feature tracker. The region of interest extractor extracts a region of interest from the image of the user. A visual speech activity detector is coupled to the region of interest extractor and measures changes in the region of interest to determine if a visual speech cue has been generated by the user. A microphone is turned on by the visual speech activity detector when a visual speech cue has been determined by the visual speech activity detector. Methods for activating a microphone based on visual speech cues are also included.

Growing community of inventors

Nanuet, NY, United States of America

Giridharan R Iyengar