Patents by Inventor Peer-Timo Bremer
Peer-Timo Bremer 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: 11735311Abstract: A system for classifying a target image with segments having attributes is provided. The system generates a graph for the target image that includes vertices representing segments of the image and edges representing relationships between the connected vertices. For each vertex, the system generates a subgraph that includes the vertex as a home vertex and neighboring vertices representing segments of the target image within a neighborhood of the segment represented by the home vertex. The system applies an autoencoder to each subgraph to generate latent variables to represent the subgraph. The system applies a machine learning algorithm to a feature vector comprising a universal image representation of the target image that is derived from the generated latent variables of the subgraphs to generate a classification for the target image.Type: GrantFiled: September 9, 2021Date of Patent: August 22, 2023Assignee: LAWRENCE LIVERMORE NATIONAL SECURITY, LLCInventors: Peer-Timo Bremer, Rushil Anirudh, Jayaraman Jayaraman Thiagarajan
-
Publication number: 20220181006Abstract: A system for classifying a target image with segments having attributes is provided. The system generates a graph for the target image that includes vertices representing segments of the image and edges representing relationships between the connected vertices. For each vertex, the system generates a subgraph that includes the vertex as a home vertex and neighboring vertices representing segments of the target image within a neighborhood of the segment represented by the home vertex. The system applies an autoencoder to each subgraph to generate latent variables to represent the subgraph. The system applies a machine learning algorithm to a feature vector comprising a universal image representation of the target image that is derived from the generated latent variables of the subgraphs to generate a classification for the target image.Type: ApplicationFiled: September 9, 2021Publication date: June 9, 2022Inventors: Peer-Timo Bremer, Rushil Anirudh, Jayaraman Jayaraman Thiagarajan
-
Patent number: 11145403Abstract: A system for classifying a target image with segments having attributes is provided. The system generates a graph for the target image that includes vertices representing segments of the image and edges representing relationships between the connected vertices. For each vertex, the system generates a subgraph that includes the vertex as a home vertex and neighboring vertices representing segments of the target image within a neighborhood of the segment represented by the home vertex. The system applies an autoencoder to each subgraph to generate latent variables to represent the subgraph. The system applies a machine learning algorithm to a feature vector comprising a universal image representation of the target image that is derived from the generated latent variables of the subgraphs to generate a classification for the target image.Type: GrantFiled: November 14, 2019Date of Patent: October 12, 2021Assignee: Lawrence Livermore National Security, LLCInventors: Peer-Timo Bremer, Rushil Anirudh, Jayaraman Jayaraman Thiagarajan
-
Patent number: 11126895Abstract: Methods and systems are provided to generate an uncorrupted version of an image given an observed image that is a corrupted version of the image. In some embodiments, a corruption mimicking (“CM”) system iteratively trains a corruption mimicking network (“CMN”) to generate corrupted images given modeled images, updates latent vectors based on differences between the corrupted images and observed images, and applies a generator to the latent vectors to generate modeled images. The training, updating, and applying are performed until modeled images that are input to the CMN result in corrupted images that approximate the observed images. Because the CMN is trained to mimic the corruption of the observed images, the final modeled images represented the uncorrupted version of the observed images.Type: GrantFiled: April 4, 2020Date of Patent: September 21, 2021Assignee: Lawrence Livermore National Security, LLCInventors: Rushil Anirudh, Peer-Timo Bremer, Jayaraman Jayaraman Thiagarajan, Bhavya Kailkhura
-
Publication number: 20210151168Abstract: A system for classifying a target image with segments having attributes is provided. The system generates a graph for the target image that includes vertices representing segments of the image and edges representing relationships between the connected vertices. For each vertex, the system generates a subgraph that includes the vertex as a home vertex and neighboring vertices representing segments of the target image within a neighborhood of the segment represented by the home vertex. The system applies an autoencoder to each subgraph to generate latent variables to represent the subgraph. The system applies a machine learning algorithm to a feature vector comprising a universal image representation of the target image that is derived from the generated latent variables of the subgraphs to generate a classification for the target image.Type: ApplicationFiled: November 14, 2019Publication date: May 20, 2021Inventors: Peer-Timo Bremer, Rushil Anirudh, Jayaraman Jayaraman thiagarajan
-
Publication number: 20200372308Abstract: Methods and systems are provided to generate an uncorrupted version of an image given an observed image that is a corrupted version of the image. In some embodiments, a corruption mimicking (“CM”) system iteratively trains a corruption mimicking network (“CMN”) to generate corrupted images given modeled images, updates latent vectors based on differences between the corrupted images and observed images, and applies a generator to the latent vectors to generate modeled images. The training, updating, and applying are performed until modeled images that are input to the CMN result in corrupted images that approximate the observed images. Because the CMN is trained to mimic the corruption of the observed images, the final modeled images represented the uncorrupted version of the observed images.Type: ApplicationFiled: April 4, 2020Publication date: November 26, 2020Inventors: Rushil Anirudh, Peer-Timo Bremer, Jayaraman Jayaraman Thiagarajan, Bhavya Kailkhura
-
Patent number: 10592774Abstract: A system for identifying in an image an object that is commonly found in a collection of images and for identifying a portion of an image that represents an object based on a consensus analysis of segmentations of the image. The system collects images of containers that contain objects for generating a collection of common objects within the containers. To process the images, the system generates a segmentation of each image. The image analysis system may also generate multiple segmentations for each image by introducing variations in the selection of voxels to be merged into a segment. The system then generates clusters of the segments based on similarity among the segments. Each cluster represents a common object found in the containers. Once the clustering is complete, the system may be used to identify common objects in images of new containers based on similarity between segments of images and the clusters.Type: GrantFiled: August 11, 2017Date of Patent: March 17, 2020Assignee: Lawrence Livermore National Security, LLCInventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Patent number: 10521699Abstract: A system for identifying objects in an image is provided. The system identifies segments of an image that may contain objects. For each segment, the system generates a segment score by inputting to a multi-scale neural network windows of multiple scales that include the segment that have been resampled to a fixed window size. A multi-scale neural network includes a feature extracting convolutional neural network (“feCNN”) for each scale and a classifier that inputs each feature of each feCNN. The segment score indicates whether the segment contains an object. The system generates a pixel score for pixels of the image. The pixel score for a pixel indicates that that pixel is within an object based on the segment scores of segments that contain that pixel. The system then identifies the object based on the pixel scores of neighboring pixels.Type: GrantFiled: October 12, 2017Date of Patent: December 31, 2019Assignee: Lawrence Livermore National Security, LLCInventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Publication number: 20190114510Abstract: A system for identifying objects in an image is provided. The system identifies segments of an image that may contain objects. For each segment, the system generates a segment score by inputting to a multi-scale neural network windows of multiple scales that include the segment that have been resampled to a fixed window size. A multi-scale neural network includes a feature extracting convolutional neural network (“feCNN”) for each scale and a classifier that inputs each feature of each feCNN. The segment score indicates whether the segment contains an object. The system generates a pixel score for pixels of the image. The pixel score for a pixel indicates that that pixel is within an object based on the segment scores of segments that contain that pixel. The system then identifies the object based on the pixel scores of neighboring pixels.Type: ApplicationFiled: October 12, 2017Publication date: April 18, 2019Inventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Publication number: 20180025253Abstract: A system for identifying in an image an object that is commonly found in a collection of images and for identifying a portion of an image that represents an object based on a consensus analysis of segmentations of the image. The system collects images of containers that contain objects for generating a collection of common objects within the containers. To process the images, the system generates a segmentation of each image. The image analysis system may also generate multiple segmentations for each image by introducing variations in the selection of voxels to be merged into a segment. The system then generates clusters of the segments based on similarity among the segments. Each cluster represents a common object found in the containers. Once the clustering is complete, the system may be used to identify common objects in images of new containers based on similarity between segments of images and the clusters.Type: ApplicationFiled: August 11, 2017Publication date: January 25, 2018Inventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Patent number: 9760801Abstract: A system for identifying in an image an object that is commonly found in a collection of images and for identifying a portion of an image that represents an object based on a consensus analysis of segmentations of the image. The system collects images of containers that contain objects for generating a collection of common objects within the containers. To process the images, the system generates a segmentation of each image. The image analysis system may also generate multiple segmentations for each image by introducing variations in the selection of voxels to be merged into a segment. The system then generates clusters of the segments based on similarity among the segments. Each cluster represents a common object found in the containers. Once the clustering is complete, the system may be used to identify common objects in images of new containers based on similarity between segments of images and the clusters.Type: GrantFiled: May 12, 2015Date of Patent: September 12, 2017Assignee: Lawrence Livermore National Security, LLCInventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Publication number: 20160335524Abstract: A system for identifying in an image an object that is commonly found in a collection of images and for identifying a portion of an image that represents an object based on a consensus analysis of segmentations of the image. The system collects images of containers that contain objects for generating a collection of common objects within the containers. To process the images, the system generates a segmentation of each image. The image analysis system may also generate multiple segmentations for each image by introducing variations in the selection of voxels to be merged into a segment. The system then generates clusters of the segments based on similarity among the segments. Each cluster represents a common object found in the containers. Once the clustering is complete, the system may be used to identify common objects in images of new containers based on similarity between segments of images and the clusters.Type: ApplicationFiled: May 12, 2015Publication date: November 17, 2016Inventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan