Patents by Inventor Scott David Cohen
Scott David Cohen 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: 11776237Abstract: Systems, methods, and software are described herein for removing people distractors from images. A distractor mitigation solution implemented in one or more computing devices detects people in an image and identifies salient regions in the image. The solution then determines a saliency cue for each person and classifies each person as wanted or as an unwanted distractor based at least on the saliency cue. An unwanted person is then removed from the image or otherwise reduced from the perspective of being an unwanted distraction.Type: GrantFiled: August 19, 2020Date of Patent: October 3, 2023Assignee: Adobe Inc.Inventors: Scott David Cohen, Zhihong Ding, Zhe Lin, Mingyang Ling, Luis Angel Figueroa
-
Patent number: 11756208Abstract: In implementations of object boundary generation, a computing device implements a boundary system to receive a mask defining a contour of an object depicted in a digital image, the mask having a lower resolution than the digital image. The boundary system maps a curve to the contour of the object and extracts strips of pixels from the digital image which are normal to points of the curve. A sample of the digital image is generated using the extracted strips of pixels which is input to a machine learning model. The machine learning model outputs a representation of a boundary of the object by processing the sample of the digital image.Type: GrantFiled: December 7, 2021Date of Patent: September 12, 2023Assignee: Adobe Inc.Inventors: Brian Lynn Price, Peng Zhou, Scott David Cohen, Gregg Darryl Wilensky
-
Patent number: 11631162Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.Type: GrantFiled: December 21, 2021Date of Patent: April 18, 2023Assignee: Adobe Inc.Inventors: Brian Lynn Price, Yinan Zhao, Scott David Cohen
-
Patent number: 11538170Abstract: Methods and systems are provided for optimal segmentation of an image based on multiple segmentations. In particular, multiple segmentation methods can be combined by taking into account previous segmentations. For instance, an optimal segmentation can be generated by iteratively integrating a previous segmentation (e.g., using an image segmentation method) with a current segmentation (e.g., using the same or different image segmentation method). To allow for optimal segmentation of an image based on multiple segmentations, one or more neural networks can be used. For instance, a convolutional RNN can be used to maintain information related to one or more previous segmentations when transitioning from one segmentation method to the next. The convolutional RNN can combine the previous segmentation(s) with the current segmentation without requiring any information about the image segmentation method(s) used to generate the segmentations.Type: GrantFiled: April 3, 2020Date of Patent: December 27, 2022Assignee: ADOBE INC.Inventors: Brian Lynn Price, Scott David Cohen, Henghui Ding
-
Patent number: 11514252Abstract: A discriminative captioning system generates captions for digital images that can be used to tell two digital images apart. The discriminative captioning system includes a machine learning system that is trained by a discriminative captioning training system that includes a retrieval machine learning system. For training, a digital image is input to the caption generation machine learning system, which generates a caption for the digital image. The digital image and the generated caption, as well as a set of additional images, are input to the retrieval machine learning system. The retrieval machine learning system generates a discriminability loss that indicates how well the retrieval machine learning system is able to use the caption to discriminate between the digital image and each image in the set of additional digital images. This discriminability loss is used to train the caption generation machine learning system.Type: GrantFiled: June 10, 2018Date of Patent: November 29, 2022Assignee: Adobe Inc.Inventors: Brian Lynn Price, Ruotian Luo, Scott David Cohen
-
Patent number: 11507800Abstract: Semantic segmentation techniques and systems are described that overcome the challenges of limited availability of training data to describe the potentially millions of tags that may be used to describe semantic classes in digital images. In one example, the techniques are configured to train neural networks to leverage different types of training datasets using sequential neural networks and use of vector representations to represent the different semantic classes.Type: GrantFiled: March 6, 2018Date of Patent: November 22, 2022Assignee: ADOBE INC.Inventors: Zhe Lin, Yufei Wang, Xiaohui Shen, Scott David Cohen, Jianming Zhang
-
Publication number: 20220114705Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.Type: ApplicationFiled: December 21, 2021Publication date: April 14, 2022Applicant: Adobe Inc.Inventors: Brian Lynn Price, Yinan Zhao, Scott David Cohen
-
Publication number: 20220092790Abstract: In implementations of object boundary generation, a computing device implements a boundary system to receive a mask defining a contour of an object depicted in a digital image, the mask having a lower resolution than the digital image. The boundary system maps a curve to the contour of the object and extracts strips of pixels from the digital image which are normal to points of the curve. A sample of the digital image is generated using the extracted strips of pixels which is input to a machine learning model. The machine learning model outputs a representation of a boundary of the object by processing the sample of the digital image.Type: ApplicationFiled: December 7, 2021Publication date: March 24, 2022Applicant: Adobe Inc.Inventors: Brian Lynn Price, Peng Zhou, Scott David Cohen, Gregg Darryl Wilensky
-
Publication number: 20220058777Abstract: Systems, methods, and software are described herein for removing people distractors from images. A distractor mitigation solution implemented in one or more computing devices detects people in an image and identifies salient regions in the image. The solution then determines a saliency cue for each person and classifies each person as wanted or as an unwanted distractor based at least on the saliency cue. An unwanted person is then removed from the image or otherwise reduced from the perspective of being an unwanted distraction.Type: ApplicationFiled: August 19, 2020Publication date: February 24, 2022Inventors: Scott David Cohen, Zhihong Ding, Zhe Lin, Mingyang Ling, Luis Angel Figueroa
-
Patent number: 11244430Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.Type: GrantFiled: March 25, 2020Date of Patent: February 8, 2022Assignee: Adobe Inc.Inventors: Brian Lynn Price, Yinan Zhao, Scott David Cohen
-
Patent number: 11244460Abstract: In implementations of object boundary generation, a computing device implements a boundary system to receive a mask defining a contour of an object depicted in a digital image, the mask having a lower resolution than the digital image. The boundary system maps a curve to the contour of the object and extracts strips of pixels from the digital image which are normal to points of the curve. A sample of the digital image is generated using the extracted strips of pixels which is input to a machine learning model. The machine learning model outputs a representation of a boundary of the object by processing the sample of the digital image.Type: GrantFiled: March 18, 2020Date of Patent: February 8, 2022Assignee: Adobe Inc.Inventors: Brian Lynn Price, Peng Zhou, Scott David Cohen, Gregg Darryl Wilensky
-
Publication number: 20210312635Abstract: Methods and systems are provided for optimal segmentation of an image based on multiple segmentations. In particular, multiple segmentation methods can be combined by taking into account previous segmentations. For instance, an optimal segmentation can be generated by iteratively integrating a previous segmentation (e.g., using an image segmentation method) with a current segmentation (e.g., using the same or different image segmentation method). To allow for optimal segmentation of an image based on multiple segmentations, one or more neural networks can be used. For instance, a convolutional RNN can be used to maintain information related to one or more previous segmentations when transitioning from one segmentation method to the next. The convolutional RNN can combine the previous segmentation(s) with the current segmentation without requiring any information about the image segmentation method(s) used to generate the segmentations.Type: ApplicationFiled: April 3, 2020Publication date: October 7, 2021Inventors: Brian Lynn PRICE, Scott David COHEN, Henghui DING
-
Publication number: 20210295525Abstract: In implementations of object boundary generation, a computing device implements a boundary system to receive a mask defining a contour of an object depicted in a digital image, the mask having a lower resolution than the digital image. The boundary system maps a curve to the contour of the object and extracts strips of pixels from the digital image which are normal to points of the curve. A sample of the digital image is generated using the extracted strips of pixels which is input to a machine learning model. The machine learning model outputs a representation of a boundary of the object by processing the sample of the digital image.Type: ApplicationFiled: March 18, 2020Publication date: September 23, 2021Applicant: Adobe Inc.Inventors: Brian Lynn Price, Peng Zhou, Scott David Cohen, Gregg Darryl Wilensky
-
Patent number: 10846524Abstract: A table layout determination system implemented on a computing device obtains an image of a table having multiple cells. The table layout determination system includes a row prediction machine learning system that generates, for each of multiple rows of pixels in the image of the table, a probability of the row being a row separator, and a column prediction machine learning system generates, for each of multiple columns of pixels in the image of the table, a probability of the column being a column separator. An inference system uses these probabilities of the rows being row separators and the columns being column separators to identify the row separators and column separators for the table. These row separators and column separators are the layout of the table.Type: GrantFiled: November 14, 2018Date of Patent: November 24, 2020Assignee: Adobe Inc.Inventors: Brian Lynn Price, Vlad Ion Morariu, Scott David Cohen, Christopher Alan Tensmeyer
-
Publication number: 20200226725Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.Type: ApplicationFiled: March 25, 2020Publication date: July 16, 2020Applicant: Adobe Inc.Inventors: Brian Lynn Price, Yinan Zhao, Scott David Cohen
-
Patent number: 10699388Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.Type: GrantFiled: January 24, 2018Date of Patent: June 30, 2020Assignee: Adobe Inc.Inventors: Brian Lynn Price, Yinan Zhao, Scott David Cohen
-
Publication number: 20200151444Abstract: A table layout determination system implemented on a computing device obtains an image of a table having multiple cells. The table layout determination system includes a row prediction machine learning system that generates, for each of multiple rows of pixels in the image of the table, a probability of the row being a row separator, and a column prediction machine learning system generates, for each of multiple columns of pixels in the image of the table, a probability of the column being a column separator. An inference system uses these probabilities of the rows being row separators and the columns being column separators to identify the row separators and column separators for the table. These row separators and column separators are the layout of the table.Type: ApplicationFiled: November 14, 2018Publication date: May 14, 2020Applicant: Adobe Inc.Inventors: Brian Lynn Price, Vlad Ion Morariu, Scott David Cohen, Christopher Alan Tensmeyer
-
Patent number: 10613726Abstract: Systems and techniques are described herein for directing a user conversation to obtain an editing query, and removing and replacing objects in an image based on the editing query. Pixels corresponding to an object in the image indicated by the editing query are ascertained. The editing query is processed to determine whether it includes a remove request or a replace request. A search query is constructed to obtain images, such as from a database of stock images, including fill material or replacement material to fulfill the remove request or replace request, respectively. Composite images are generated from the fill material or the replacement material and the image to be edited. Composite images are harmonized to remove editing artifacts and make the images look natural. A user interface exposes images, and the user interface accepts multi-modal user input during the directed user conversation.Type: GrantFiled: December 22, 2017Date of Patent: April 7, 2020Assignee: Adobe Inc.Inventors: Scott David Cohen, Brian Lynn Price, Abhinav Gupta
-
Publication number: 20190377987Abstract: A discriminative captioning system generates captions for digital images that can be used to tell two digital images apart. The discriminative captioning system includes a machine learning system that is trained by a discriminative captioning training system that includes a retrieval machine learning system. For training, a digital image is input to the caption generation machine learning system, which generates a caption for the digital image. The digital image and the generated caption, as well as a set of additional images, are input to the retrieval machine learning system. The retrieval machine learning system generates a discriminability loss that indicates how well the retrieval machine learning system is able to use the caption to discriminate between the digital image and each image in the set of additional digital images. This discriminability loss is used to train the caption generation machine learning system.Type: ApplicationFiled: June 10, 2018Publication date: December 12, 2019Applicant: Adobe Inc.Inventors: Brian Lynn Price, Ruotian Luo, Scott David Cohen
-
Publication number: 20190279074Abstract: Semantic segmentation techniques and systems are described that overcome the challenges of limited availability of training data to describe the potentially millions of tags that may be used to describe semantic classes in digital images. In one example, the techniques are configured to train neural networks to leverage different types of training datasets using sequential neural networks and use of vector representations to represent the different semantic classes.Type: ApplicationFiled: March 6, 2018Publication date: September 12, 2019Applicant: Adobe Inc.Inventors: Zhe Lin, Yufei Wang, Xiaohui Shen, Scott David Cohen, Jianming Zhang