Patents by Inventor George Toderici
George Toderici 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: 11849113Abstract: Artificial image generation may include obtaining a source image, identifying quantization information from the source image, wherein identifying the quantization information includes identifying multiresolution quantization interval information from the source image, generating a restoration filtered image by restoration filtering the source image, generating a constrained restoration filtered image by constraining the restoration filtered image based on the quantization information, obtaining an unconstrained artificial image based on the constrained restoration filtered image and a generative artificial neural network obtained using a generative adversarial network, obtaining the artificial image by constraining the unconstrained artificial image based on the quantization information, and outputting the artificial image.Type: GrantFiled: October 20, 2021Date of Patent: December 19, 2023Assignee: GOOGLE LLCInventors: Jyrki Alakuijala, George Toderici
-
Publication number: 20220046242Abstract: Artificial image generation may include obtaining a source image, identifying quantization information from the source image, wherein identifying the quantization information includes identifying multiresolution quantization interval information from the source image, generating a restoration filtered image by restoration filtering the source image, generating a constrained restoration filtered image by constraining the restoration filtered image based on the quantization information, obtaining an unconstrained artificial image based on the constrained restoration filtered image and a generative artificial neural network obtained using a generative adversarial network, obtaining the artificial image by constraining the unconstrained artificial image based on the quantization information, and outputting the artificial image.Type: ApplicationFiled: October 20, 2021Publication date: February 10, 2022Inventors: Jyrki Alakuijala, George Toderici
-
Patent number: 11166022Abstract: Artificial image generation may include obtaining a source image, identifying quantization information from the source image, wherein identifying the quantization information includes identifying multiresolution quantization interval information from the source image, generating a restoration filtered image by restoration filtering the source image, generating a constrained restoration filtered image by constraining the restoration filtered image based on the quantization information, obtaining an unconstrained artificial image based on the constrained restoration filtered image and a generative artificial neural network obtained using a generative adversarial network, obtaining the artificial image by constraining the unconstrained artificial image based on the quantization information, and outputting the artificial image.Type: GrantFiled: June 4, 2019Date of Patent: November 2, 2021Assignee: GOOGLE LLCInventors: Jyrki Alakuijala, George Toderici
-
Publication number: 20200389645Abstract: Artificial image generation may include obtaining a source image, identifying quantization information from the source image, wherein identifying the quantization information includes identifying multiresolution quantization interval information from the source image, generating a restoration filtered image by restoration filtering the source image, generating a constrained restoration filtered image by constraining the restoration filtered image based on the quantization information, obtaining an unconstrained artificial image based on the constrained restoration filtered image and a generative artificial neural network obtained using a generative adversarial network, obtaining the artificial image by constraining the unconstrained artificial image based on the quantization information, and outputting the artificial image.Type: ApplicationFiled: June 4, 2019Publication date: December 10, 2020Inventors: Jyrki Alakuijala, George Toderici
-
Patent number: 8990134Abstract: A classifier training system trains classifiers for inferring the geographic locations of videos. A number of classifiers are provided, where each classifier corresponds to a particular location and is trained from a training set of videos that have been labeled as representing the location. In one embodiment, the training set is further restricted to those videos in which a landmark matching the location label is detected. The classifier training system extracts, from each of these videos, features that characterize the video, such as audiovisual features, text features, address features, landmark features, and category features. Based on these features, the classifier training system trains a location classifier for the corresponding location. Each of the location classifiers can be applied to videos without associated location labels to predict whether, or how strongly, the video represents the corresponding location.Type: GrantFiled: September 13, 2010Date of Patent: March 24, 2015Assignee: Google Inc.Inventors: Jasper Snoek, Luciano Sbaiz, Hrishikesh Aradhye, George Toderici
-
Patent number: 8819024Abstract: A classifier training system learns classifiers for categories by combining data from a category-instance repository comprising relationships between categories and more specific instances of those categories with a set of video classifiers for different concepts. The category-instance repository is derived from the domain of textual documents, such as web pages, and the concept classifiers are derived from the domain of video. Taken together, the category-instance repository and the concept classifiers provide sufficient data for obtaining accurate classifiers for categories that encompass other lower-level concepts, where the categories and their classifiers may not be obtainable solely from the video domain.Type: GrantFiled: November 19, 2010Date of Patent: August 26, 2014Assignee: Google Inc.Inventors: George Toderici, Hrishikesh Aradhye, Alexandru Marius Pasca, Luciano Sbaiz, Jay Yagnik
-
Patent number: 8537175Abstract: A video enhancement server enhances a video. A scene segmentation module detects scene boundaries and segments the video into a number of scenes. For each frame in a given scene, a local white level and a local black level are determined from the distribution of pixel luminance values in the frame. A global white level and global black level are also determined from the distribution of pixel luminance values throughout the scene. Weighted white levels and black levels are determined for each frame as a weighted combination of the local and global levels. The video segmentation server then applies histogram stretching and saturation adjustment to each frame using the weighted white levels and black levels to determine enhanced pixel luminance values. An enhanced video comprising the enhanced pixel luminance values is stored to a video server for serving to clients.Type: GrantFiled: November 25, 2009Date of Patent: September 17, 2013Assignee: Google Inc.Inventors: George Toderici, Jay Yagnik
-
Patent number: 8396286Abstract: A concept learning module trains video classifiers associated with a stored set of concepts derived from textual metadata of a plurality of videos, the training based on features extracted from training videos. Each of the video classifiers can then be applied to a given video to obtain a score indicating whether or not the video is representative of the concept associated with the classifier. The learning process does not require any concepts to be known a priori, nor does it require a training set of videos having training labels manually applied by human experts. Rather, in one embodiment the learning is based solely upon the content of the videos themselves and on whatever metadata was provided along with the video, e.g., on possibly sparse and/or inaccurate textual metadata specified by a user of a video hosting service who submitted the video.Type: GrantFiled: June 24, 2010Date of Patent: March 12, 2013Assignee: Google Inc.Inventors: Hrishikesh Aradhye, George Toderici, Jay Yagnik
-
Patent number: 8090160Abstract: A novel method and system for 3d-aided-2D face recognition under large pose and illumination variations is disclosed. The method and system includes enrolling a face of a subject into a gallery database using raw 3D data. The method also includes verifying and/or identifying a target face form data produced by a 2D imagining or scanning device. A statistically derived annotated face model is fitted using a subdivision-based deformable model framework to the raw 3D data. The annotated face model is capable of being smoothly deformed into any face so it acts as a universal facial template. During authentication or identification, only a single 2D image is required. The subject specific fitted annotated face model from the gallery is used to lift a texture of a face from a 2D probe image, and a bidirectional relighting algorithm is employed to change the illumination of the gallery texture to match that of the probe.Type: GrantFiled: October 13, 2008Date of Patent: January 3, 2012Assignee: The University of Houston SystemInventors: Ioannis A. Kakadiaris, George Toderici, Theoharis Theoharis, Georgios Passalis
-
Publication number: 20090310828Abstract: A novel method and system for 3d-aided-2D face recognition under large pose and illumination variations is disclosed. The method and system includes enrolling a face of a subject into a gallery database using raw 3D data. The method also includes verifying and/or identifying a target face form data produced by a 2D imagining or scanning device. A statistically derived annotated face model is fitted using a subdivision-based deformable model framework to the raw 3D data. The annotated face model is capable of being smoothly deformed into any face so it acts as a universal facial template. During authentication or identification, only a single 2D image is required. The subject specific fitted annotated face model from the gallery is used to lift a texture of a face from a 2D probe image, and a bidirectional relighting algorithm is employed to change the illumination of the gallery texture to match that of the probe.Type: ApplicationFiled: October 13, 2008Publication date: December 17, 2009Applicant: The University of Houston SystemInventors: Ioannis A. Kakadiaris, George Toderici, Theoharis Theoharis, Georgios Passalis