Hewlett-packard Development Company, L.p.

Mei Chen

Debargha Mukherjee

Suk Hwan Lim

D Amnon Silverstein

Tong Zhang

Ramin Samadani

Qian Lin

Niranjan Damera-Venkata

Amir Said

Gary Lee Vondran, Jr

Pere Obrador

Huitao Luo

Jonathan Yen

Nelson Liang An Chang

Stephen Philip Cheatle

Xiaofan Lin

Ken Kengkuan Lin

C Brian Atkins

Dominic Lee

Charles A Untulis

Nirmalya Ray

Methods, machines, and machine-readable media for enhancing image resolution are described. In one aspect, a respective motion map is computed for each pairing of a reference image and a respective image neighboring the reference image in a sequence of base images. Each motion map includes a set of motion vectors mapping reference image pixels to respective neighboring image pixels. Respective regions of a target image are assigned to motion classes based on the computed motion maps. The target image has a target resolution level and the base images have a base resolution level equal to or lower than the target resolution level. Pixel values for the target image are computed based on corresponding pixel value contributions from the motion-compensated neighboring base images selected in accordance with the motion classes assigned to the target image regions.

Enhancing image resolution

A method performed by a processing system includes building a first image pyramid of a first frame of a first channel of a digital video, building a second image pyramid of a second frame of a second channel of the digital video, the second frame corresponding to the first frame, and determining a first global motion estimation for the first frame to the second frame based on the first image pyramid and the second image pyramid.

Color registration in a digital video

A method and system for automatically producing a page using frames of a video stream. A plurality of video frames from a video stream or clip are read, and multiple frames are extracted from the video stream, based on the content of each frame. Frames which neighbor the extracted frames in the video stream are also extracted, with the number of neighboring frames to be extracted being controlled by parameters provided to the page production system. The resolution of the images in the extracted video frames is enhanced, based on the information in each extracted frame and each respective extracted neighboring frame. The enhanced images are automatically cropped to enhance the important features in each image, and the cropped images are composed into one or more pages that are representative of the content of the video stream.

System and method for producing a page using frames of a video stream

A machine-implemented image processing method includes segmenting a scene into a background scene portion and a foreground scene portion, forming a mosaic for the background scene portion, enhancing the foreground scene portion, and constructing a composite of the background mosaic and the enhanced foreground.

Image processing system and method

Methods, machines, and machine-readable media for processing multiple exposure source images, including a reference image and one or more non-reference images, are described. In one aspect, respective sets of motion vectors that establish correspondences between respective pairs of the source images are calculated. Ones of the source images are warped to a reference coordinate system based on the sets of motion vectors. For each of the non-reference ones of the warped images, a respective set of one or more measures of alignment confidence between the non-reference warped image and the reference image in the reference coordinate system is computed. Saturated pixels and unsaturated pixels are identified in the warped images. An output image with pixel value contributions from unsaturated pixels in the warped images is generated based on the computed alignment confidence measures.

Combining multiple exposure images to increase dynamic range

An exemplary method for providing an optimized digital image comprises obtaining digital image data by a digital image capture device, based on the digital image data, automatically determining at least two setting types, and a plurality of setting values therefor, for capturing a plurality of digital images, automatically capturing the plurality of digital images using the digital image capture device, each image being captured with at least one setting value different than another image, and providing an optimized digital image based on the plurality of digital images. In one exemplary embodiment, the optimized image is selected from the plurality of digital images. In another exemplary embodiment, the optimized image is synthesized based on the plurality of digital images.

Providing optimized digital images

Respective sets of motion vectors are computed for pairs of image frames. The computed motion vectors are classified into motion classes. Motion clusters are identified in the image frames based at least in part on the motion classes. An identified motion cluster is selected as a motion stabilization reference based on spatiotemporal consistency of the selected motion cluster across multiple image frames.

Stabilizing a sequence of image frames

Methods, machines, and machine-readable media for computing dissimilarity measures are described. In one aspect, a first set of pixel neighborhood values (PNVs) is computed from respective sets of pixel values of a first image corresponding to different spatially-shifted pixel neighborhoods each encompassing a mutual target pixel in the first image. A second set of PNVs is computed from respective sets of pixel values of a second image corresponding to different spatially-shifted pixel neighborhoods each encompassing a mutual target pixel in the second image. A measure of dissimilarity is computed based at least in part on the first and second sets of computed PNVs. The computed dissimilarity measure is stored on a machine-readable medium.

Computing dissimilarity measures

A method for estimating motion of each of a plurality of tessels in an intermediate image relative to a reference image, which includes searching the reference image to find points that lie along epipolar lines in the reference image corresponding to upper-left and lower-right vertices of the tessel, respectively, that result in a best-matching shape; estimating a depth of each of at least two of the vertices of the tessel; and using the depth estimates of the at least two vertices of the tessel to estimate the motion of the tessel relative to the best-matching shape.

Motion estimation for compression of calibrated multi-view image sequences

A method for removing undesired motion from a sequential plurality of related images utilizes adaptive filtering of image motion to determine image shifts. Differences between sequential image motions are taken with respect to a reference frame and a smoothing filter is applied to such differences of a sample of images adjacent a test image. Image shift values are calculated by subtracting the difference associated with a test frame from a filtered sample that includes the test frame. The image shift values are compared to an image shift parameter and sample sizes adjusted and image shift values calculated in accordance with the adjusted sample sizes so that image stability is obtained without boundary flicker.

Method for image stabilization by adaptive filtering

A system and method of transmitting an image adapted to a first display area size, such as a standard computer screen having a particular pixel-by-pixel resolution, to an apparatus having a smaller second display area size by scaling the image through coefficient cropping its frequency domain representation. When the cropped frequency coefficients are used to display an image within the second smaller display area, a scaled version of the image is displayed. In a specific embodiment, frequency domain coefficients are cropped such that a region of interest of the image is scaled down less than the remainder of the image when displayed in the second smaller display area. Scaling in this manner provides the user with a readable region of interest with the remainder of the image scaled down so as to facilitate easy image navigation by the user.

Growing community of inventors

Los Altos, CA, United States of America

Mei Chen