John S Boreczky, Age 58516 Dutton Ave, San Leandro, CA 94577

6366296, Apr 2, 2002

Sep 11, 1998

09/151285

John S. Boreczky - San Leandro CA
Andreas Girgensohn - Menlo Park CA
Jonathan T. Foote - Menlo Park CA

Xerox Corporation - Stamford CT
Fuji Xerox Co., Ltd. - Tokyo

G06F 300

345719, 345716, 345721, 345968, 7071041

A media browser, graphical user interface and method for browsing a media file wherein a user selects at least one feature in a media file and is provided with information regarding the existence of the selected feature in the media file. Based on the information, the user can identify and playback portions of interest in a media file. Features in a media file, such as a speakers identity, applause, silence, motion, or video cuts, are preferably automatically time-wise evaluated in the media file using known methods. Metadata generated based on the time-wise feature evaluation are preferably mapped to confidence score values that represent a probability of a corresponding features existence in the media file. Confidence score information is preferably presented graphically to a user as part of a graphical user interface, and is used to interactively browse the media file.

6807306, Oct 19, 2004

May 28, 1999

09/322842

Andreas Girgensohn - Menlo Park CA
John S. Boreczky - San Leandro CA

Xerox Corporation - Stamford CT
FujiXerox Co., Ltd. - Tokyo

G06K 962

382225, 382226, 348701

A method for candidate frame selection involves sampling the source frames of the source video at a predetermined fixed periodic interval. The largest frame differences represent candidate boundaries, and the frames before and after the N/2 largest candidate boundaries are selected as candidate frames. A method for selecting keyframes involves clustering all candidate frames into a hierarchical binary tree using a hierarchical agglomerative clustering algorithm. Optionally, the pairwise distances for the members of the two clusters is modified according to class membership of the members, which is preferably determined statistically from image class statistical models. A method for selecting M clusters from which keyframes are extracted involves splitting the M-1 largest clusters of a hierarchical binary tree of clusters. Optionally, clusters not having at least one uninterrupted sequence of frames of at least a minimum duration are filtered out. The source video duration is divided into equal duration intervals.

6807361, Oct 19, 2004

Jul 18, 2000

09/618533

Andreas Girgensohn - Menlo Park CA
John J. Doherty - San Francisco CA
Lynn D. Wilcox - Palo Alto CA
John S. Boreczky - San Leandro CA
Patrick Chiu - Menlo Park CA
Jonathan T. Foote - Menlo Park CA

Fuji Xerox Co., Ltd. - Tokyo

H04N 593

386 52, 386 55, 386117

The present invention analyzes recorded video from a video camera to identify camera and object motion in the recorded video. Keyframes representative of clips of the recorded video are displayed on a user interface that allows a user to manipulate an order of the keyframes. Editing rules are then applied to the keyframes to intelligently splice together portions of the representative clips into a final output video.

6807362, Oct 19, 2004

Jul 18, 2000

09/618649

Andreas Girgensohn - Menlo Park CA
John S. Boreczky - San Leandro CA
John J. Doherty - San Francisco CA
Patrick Chiu - Menlo Park CA
Lynn D. Wilcox - Palo Alto CA

Fuji Xerox Co., Ltd. - Tokyo

H04N 593

386 52, 386 46, 386 83, 360 15

A heuristically derived unsuitability score is computed and used as an input for metaphorical springs in which each selected video segment from recorded video of a video camera is associated with a metaphorical spring that maintains the selected segment at an optimal length while being responsive to a global system spring whose spring strength determines a final length of a final edited output video. Accordingly, user-specified changes to the final length of the final output video automatically lengthen or shorten the lengths of individual segments in such a way that high quality video segments having low unsuitability scores are emphasized over low quality video segments having high unsuitability scores.

6839067, Jan 4, 2005

Jul 26, 2002

10/205739

Qiong Liu - Milpitas CA, US
Don Kimber - Montara CA, US
Lynn D. Wilcox - Palo Alto CA, US
Jonathan T. Foote - Menlo Park CA, US
John Boreczky - San Leandro CA, US
Patrick Chiu - Menlo Park CA, US
Shingo Uchihashi - Pittsburgh PA, US
Hai Tao - Santa Cruz CA, US

Fuji Xerox Co., Ltd. - Tokyo

G09G 500

345647

A method and apparatus for providing multi-resolution video to multiple users under hybrid human and automatic control. Initial environment and close-up images are captured using a first camera and a PTZ camera. The initial images are then stored in memory. Current environment and close-up images are captured and the an estimated difference between the initial and current images and the true image is determined. The estimated differences are weighted and compared and the stored images are updated. A close-up image is then provided to each user of the system. The close-up camera is then directed to a portion of the environment image having high distortion, and current environment and close-up images are captured again.

7015954, Mar 21, 2006

Aug 9, 1999

09/370406

Jonathan Foote - Menlo Park CA, US
John Boreczky - San Leandro CA, US

Fuji Xerox Co., Ltd. - Tokyo

H04N 5/225
H04N 7/18
H04N 5/232

3482181, 348159, 34821111

A camera array captures plural component images which are combined into a single scene from which “panning” and “zooming” within the scene are performed. In one embodiment, each camera of the array is a fixed digital camera. The images from each camera are warped and blended such that the combined image is seamless with respect to each of the component images. Warping of the digital images is performed via pre-calculated non-dynamic equations that are calculated based on a registration of the camera array. The process of registering each camera in the arrays is performed either manually, by selecting corresponding points or sets of points in two or more images, or automatically, by presenting a source object (laser light source, for example) into a scene being captured by the camera array and registering positions of the source object as it appears in each of the images. The warping equations are calculated based on the registration data and each scene captured by the camera array is warped and combined using the same equations determined therefrom. A scene captured by the camera array is zoomed, or selectively steered to an area of interest.

7051271, May 23, 2006

May 31, 2000

09/584205

Patrick Chiu - Menlo Park CA, US
Jonathan T. Foote - Menlo Park CA, US
Andreas Girgensohn - Menlo Park CA, US
John S. Boreczky - San Leandro CA, US

Fuji Xerox Co., Ltd. - Tokyo

G06F 17/00

7155001, 715513

Video recordings of meetings and scanned paper documents are natural digital documents that come out of a meeting. These can be placed on the Internet for easy access, with links generated between them by matching scanned documents to a segment of the video referencing the scanned document. Furthermore, annotations made on the paper documents during the meeting can be extracted and used as indexes to the video. An orthonormal transform, such as a Digital Cosine Transform (DCT) is used to compare scanned documents to video frames.

7068723, Jun 27, 2006

Feb 28, 2002

10/086817

Jonathan T. Foote - Menlo Park CA, US
John Boreczky - San Leandro CA, US

Fuji Xerox Co., Ltd. - Tokyo

H04N 7/18

37524025, 382224, 382165, 382225

Optimal summaries of a linear media source are automatically produced by parameterizing a linear media source. The parameterized linear media source is used to create a similarity array in which each array element includes the value of a similarity measurement between a two portions of the parameterized media signal. A segment fitness function, adapted for measuring the similarity between a segment of the parameterized media signal and the entire parameterized media signal, is optimized to find an optimal segment location. The portion of the linear media source corresponding to the optimal segment location is selected as the optimal summary. This method produces optimal summaries of any type of linear media, such as video, audio, or text information.