Patents by Inventor Mei Han
Mei Han has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8867859Abstract: An image comprising varying illumination is selected. Instances of a repeating pattern in the image is determined. Illumination values for pixels at locations within instances of the repeating pattern are calculated responsive to pixel intensities of pixels at corresponding locations in other instances of the repeating pattern. The varying illumination is removed form the image responsive to the illumination values.Type: GrantFiled: September 11, 2012Date of Patent: October 21, 2014Assignee: Google Inc.Inventors: Vivek Kwatra, Mei Han, Shengyang Dai
-
Publication number: 20140301653Abstract: Embodiments generally relate to summarizing a photo album in a social network system. In one embodiment, a method includes grouping photos into a plurality of groups of photos, and selecting a plurality of representative photos, where each representative photo represents a respective group from the plurality of groups, where the selecting is based on a quality score of each of the photos, and where each quality score is based on different types of attributes. The method also includes enabling the plurality of representative photos to be shared.Type: ApplicationFiled: June 5, 2012Publication date: October 9, 2014Applicant: GOOGLE INC.Inventors: Erik Murphy-Chutorian, Chuck Joseph Rosenberg, Shengyang Dai, Ehud Rivlin, Mei Han, Kyle Heath
-
Patent number: 8855437Abstract: Compression of an image is performed based on prediction of target blocks of an image from candidate source blocks of the image. Heuristics are used for identifying the candidate source blocks, for example, source blocks are selected from within a cluster of similar blocks obtained by K-means clustering. For each target block, a region adjacent to the target block is identified and a set of candidate source blocks along with candidate source regions adjacent to the candidate source blocks are identified. The candidate source regions are ranked based on the differences between the candidate source regions and the target source region. Each candidate source block is described using its rank and residual information describing differences between the candidate source block and the target block. The candidate source block that can be described using a minimum amount of information is selected for predicting the target block.Type: GrantFiled: May 31, 2013Date of Patent: October 7, 2014Assignee: Google Inc.Inventors: Jing-yu Cui, Vivek Kwatra, Michele Covell, Mei Han, Saurabh Mathur
-
Publication number: 20140233811Abstract: Embodiments generally relate to summarizing a photo album. In one embodiment, a method includes grouping photos into a plurality of groups of photos, and selecting a plurality of representative photos, where each representative photo represents a respective group from the plurality of groups, where the selecting is based on a quality score of each of the photos, and where each quality score is based on different types of attributes. The method also includes providing the plurality of representative photos to a user.Type: ApplicationFiled: May 14, 2013Publication date: August 21, 2014Inventors: Erik Murphy-Chutorian, Shengyang Dai, Ehud Rivlin, Chuck Joseph Rosenberg, Mei Han, Kyle Heath
-
Patent number: 8805104Abstract: An image processing system is provided for encoding images based on example-based compression. The system selects a set of candidate dictionary predictor entries to encode a portion of an image based at least in part on the neighbors of the portion. The spatial continuity between portions of the image is exploited by the image processing system by selecting corresponding dictionary predictor entries that have the same offset vector as the portion of the image and its neighboring portions.Type: GrantFiled: May 11, 2011Date of Patent: August 12, 2014Assignee: Google Inc.Inventors: Michele Covell, Vivek Kwatra, Mei Han, Saurabh Mathur, Shumeet Baluja
-
Patent number: 8798393Abstract: An image comprising varying illumination is selected. Patches of pixels from among the plurality of pixels with the image are identified. Similarities between pairs of patches of pixels based on pixel intensities associated with the pairs of patches of pixels are calculated. Illumination values for the plurality of pixels within the image based on the calculated similarities between the pairs of patches of pixels is calculated. The illumination variation from the image is removed based on the calculated illumination values for the plurality of pixels within the image.Type: GrantFiled: November 30, 2011Date of Patent: August 5, 2014Assignee: Google Inc.Inventors: Vivek Kwatra, Mei Han
-
Patent number: 8787692Abstract: An exemplar dictionary is built from example image blocks for determining predictor blocks for encoding and decoding images. The exemplar dictionary comprises a hierarchical organization of example image blocks. The hierarchical organization of image blocks is obtained by clustering a set of example image blocks, for example, based on k-means clustering. Performance of clustering is improved by transforming feature vectors representing the image blocks to fewer dimensions. Principal component analysis is used for determining feature vectors with fewer dimensions. The clustering performed at higher levels of the hierarchy uses fewer dimensions of feature vectors compared to lower levels of hierarchy. Performance of clustering is improved by processing only a sample of the image blocks of a cluster. The clustering performed at higher levels of the hierarchy uses lower sampling rates as compared to lower levels of hierarchy.Type: GrantFiled: July 19, 2013Date of Patent: July 22, 2014Assignee: Google Inc.Inventors: Mei Han, Michele Covell, Saurabh Mathur, Shumeet Baluja, Vivek Kwatra
-
Patent number: 8724701Abstract: An image processing system is provided for encoding videos based on example-based compression. To select the dictionary predictor entries to encode a video, the image processing system reduces the complexity of the video by decomposing the video into smaller pieces. By breaking the video into the simpler pieces, it is easier to locate dictionary predictor entries that are similar to the pieces of the video. The image processing system may decompose the video into one more space-time tubes. For each space-time tube, the image processing system selects dictionary predictor entries to encode the tube.Type: GrantFiled: April 18, 2011Date of Patent: May 13, 2014Assignee: Google Inc.Inventors: Michele Covell, Vivek Kwatra, Mei Han, Saurabh Mathur, Shumeet Baluja
-
Patent number: 8712930Abstract: An exemplar dictionary is built from exemplars of digital content for determining predictor blocks for encoding and decoding digital content. The exemplar dictionary organizes the exemplars as clusters of similar exemplars. Each cluster is mapped to a label. Machine learning techniques are used to generate a prediction model for predicting a label for an exemplar. The exemplar dictionary is used to encode digital content. Clusters of exemplars are obtained by applying a prediction model to a target block of digital content for encoding. A predictor block is selected for encoding the target block based on frequency of occurrence of exemplars in the clusters. The target block is encoded using the predictor block.Type: GrantFiled: May 4, 2011Date of Patent: April 29, 2014Assignee: Google Inc.Inventors: Michele Covell, Mei Han, Saurabh Mathur, Shumeet Baluja, Vivek Kwatra
-
Patent number: 8660370Abstract: Clustering algorithms such as k-means clustering algorithm are used in applications that process entities with spatial and/or temporal characteristics, for example, media objects representing audio, video, or graphical data. Feature vectors representing characteristics of the entities are partitioned using clustering methods that produce results sensitive to an initial set of cluster seeds. The set of initial cluster seeds is generated using principal component analysis of either the complete feature vector set or a subset thereof. The feature vector set is divided into a desired number of initial clusters and a seed determined from each initial cluster.Type: GrantFiled: January 31, 2013Date of Patent: February 25, 2014Assignee: Google Inc.Inventors: Sangho Yoon, Jay N. Yagnik, Mei Han, Vivek Kwatra
-
Patent number: 8618145Abstract: The invention provides small molecule compounds capable of accelerating proliferation of stem cells and uses thereof. The compounds play an important role in the research of stem cell proliferation mechanism. The invention further relates to the uses of the compounds and relevant compounds thereof in the preparation of stem cell proliferation accelerators and the preparation of medicines accelerating stem cell proliferation. The invention also relates to the uses of the compounds in the preparation of medicines for the treatment of various diseases arising from functional cells loss or damage. The diseases arising from stem cell trauma comprise diseases related to the degeneration or damage of nervous system cells, blood system diseases, diseases related to the loss or damage of cardiovascular cells, skin burn and the like.Type: GrantFiled: May 12, 2009Date of Patent: December 31, 2013Inventors: Mei Han, Yan Feng, Yuanyuan Sun
-
Patent number: 8620077Abstract: A video is segmented to produce volumetric video regions. Descriptors are created for the video regions. A region graph is created for the video, where the region graph has weighted edges incident to video regions and the weight of an edge is calculated responsive to the descriptors of the video regions incident to the edge. The region graph is segmented responsive to the weights of the edges incident to the video regions to produce a new region graph having new volumetric video regions comprised of merged video regions of the first region graph. The descriptions of the region graphs are stored in a data storage.Type: GrantFiled: July 1, 2009Date of Patent: December 31, 2013Assignee: Google Inc.Inventors: Matthias Grundmann, Vivek Kwatra, Mei Han
-
Patent number: 8611695Abstract: An image processing server enhances an original image using image data from other images. The server generates global descriptors of a set of received images and creates an image data structure therefrom. The server also identifies a set of patches for each of the received images, generates descriptors of the patches, and generates a patch data structure therefrom. The image processing system identifies a patch in an original image for which enhancement is desired. The image processing server uses a global descriptor of the original image to search the image data structure for a set of related images that are visually similar to the original image. The image processing server uses a patch descriptor of the patch for which enhancement is desired to search the patch data structures for the related images to identify a set of patches that are visually similar to the patch in the original image.Type: GrantFiled: April 27, 2009Date of Patent: December 17, 2013Assignee: Google Inc.Inventors: Mei Han, Vivek Kwatra, Hui Fang
-
Patent number: 8571349Abstract: An image processing system enhances the resolution of an original image using higher-resolution image data from other images. The image processing system defines a plurality of overlapping partitions for the original image, each partition defining a set of non-overlapping site patches. During an optimization phase, the system identifies, for site patches of the original images, label patches within related images that are of most relevance. During a rendering phase independent of the optimization phase, an output image with enhanced resolution is synthesized by substituting, for site patches of the original image, the identified relevant label patches from the related images.Type: GrantFiled: September 14, 2012Date of Patent: October 29, 2013Assignee: Google IncInventors: Vivek Kwatra, Mei Han, Jay N. Yagnik
-
Patent number: 8515193Abstract: An exemplar dictionary is built from example image blocks for determining predictor blocks for encoding and decoding images. The exemplar dictionary comprises a hierarchical organization of example image blocks. The hierarchical organization of image blocks is obtained by clustering a set of example image blocks, for example, based on k-means clustering. Performance of clustering is improved by transforming feature vectors representing the image blocks to fewer dimensions. Principal component analysis is used for determining feature vectors with fewer dimensions. The clustering performed at higher levels of the hierarchy uses fewer dimensions of feature vectors compared to lower levels of hierarchy. Performance of clustering is improved by processing only a sample of the image blocks of a cluster. The clustering performed at higher levels of the hierarchy uses lower sampling rates as compared to lower levels of hierarchy.Type: GrantFiled: April 8, 2011Date of Patent: August 20, 2013Assignee: Google Inc.Inventors: Mei Han, Michele Covell, Saurabh Mathur, Shumeet Baluja, Vivek Kwatra
-
Patent number: 8478057Abstract: Compression of an image is performed based on prediction of target blocks of an image from candidate source blocks of the image. Heuristics are used for identifying the candidate source blocks, for example, source blocks are selected from within a cluster of similar blocks obtained by K-means clustering. For each target block, a region adjacent to the target block is identified and a set of candidate source blocks along with candidate source regions adjacent to the candidate source blocks are identified. The candidate source regions are ranked based on the differences between the candidate source regions and the target source region. Each candidate source block is described using its rank and residual information describing differences between the candidate source block and the target block. The candidate source block that can be described using a minimum amount of information is selected for predicting the target block.Type: GrantFiled: January 22, 2010Date of Patent: July 2, 2013Assignee: Google Inc.Inventors: Jingyu Cui, Vivek Kwatra, Michele Covell, Mei Han, Saurabh Mathur
-
Patent number: 8396325Abstract: An image processing system enhances the resolution of an original image using higher-resolution image data from other images. The image processing system defines a plurality of overlapping partitions for the original image, each partition defining a set of non-overlapping site patches. During an optimization phase, the system identifies, for site patches of the original images, label patches within related images that are of most relevance. During a rendering phase independent of the optimization phase, an output image with enhanced resolution is synthesized by substituting, for site patches of the original image, the identified relevant label patches from the related images.Type: GrantFiled: April 27, 2009Date of Patent: March 12, 2013Assignee: Google Inc.Inventors: Vivek Kwatra, Mei Han, Jay Yagnik
-
Patent number: 8391634Abstract: An image comprising varying illumination is selected. Instances of a repeating pattern in the image is determined. Illumination values for pixels at locations within instances of the repeating pattern are calculated responsive to pixel intensities of pixels at corresponding locations in other instances of the repeating pattern. The varying illumination is removed form the image responsive to the illumination values.Type: GrantFiled: April 28, 2009Date of Patent: March 5, 2013Assignee: Google Inc.Inventors: Vivek Kwatra, Mei Han, Shengyang Dai
-
Patent number: 8385662Abstract: Clustering algorithms such as k-means clustering algorithm are used in applications that process entities with spatial and/or temporal characteristics, for example, media objects representing audio, video, or graphical data. Feature vectors representing characteristics of the entities are partitioned using clustering methods that produce results sensitive to an initial set of cluster seeds. The set of initial cluster seeds is generated using principal component analysis of either the complete feature vector set or a subset thereof. The feature vector set is divided into a desired number of initial clusters and a seed determined from each initial cluster.Type: GrantFiled: April 30, 2009Date of Patent: February 26, 2013Assignee: Google Inc.Inventors: Sangho Yoon, Jay Yagnik, Mei Han, Vivek Kwatra
-
Patent number: 8335403Abstract: Systems and methods are disclosed for processing a low resolution image by performing a high resolution edge segment extraction on the low resolution image; performing an image super resolution on each edge segment; performing reconstruction constraint reinforcement; and generating a high quality image from the low quality image.Type: GrantFiled: October 10, 2007Date of Patent: December 18, 2012Assignee: NEC Laboratories America, Inc.Inventors: Shengyang Dai, Mei Han, Wei Xu, Ying Wu, Yihong Gong