Patents by Inventor Vitaly Glazkov
Vitaly Glazkov 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: 11995299Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: GrantFiled: March 22, 2023Date of Patent: May 28, 2024Assignee: Bending Spoons S.p.A.Inventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P. J. Tanzillo
-
Publication number: 20230326223Abstract: Methods and systems for detecting images in documents are described. A method implemented by an electronic device having one or more processors for determining whether a document is an image includes partitioning a document into a plurality of cells. The method includes scaling each of the cells to a standardized number of pixels to provide a corresponding snippet for each of the cells, classifying the snippets, using a neural network, to determine a set of cells classified as text, and determining a volume of text for the document based on a sum of an amount of text in each cell of the set of cells. The method further includes in response to a determination that the volume of text for the document is below a predetermined threshold, determining that the document is an image.Type: ApplicationFiled: June 13, 2023Publication date: October 12, 2023Inventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Patent number: 11715316Abstract: Methods and systems for training a neural network to distinguish between text documents and image documents are described. A corpus of text and image documents is obtained. A page of a text document is scanned by shifting a text window to a plurality of locations. In accordance with a determination that the text in the window at a respective location meets text line criteria, the text in the window is stored as a respective text snippet. A plurality of image windows are superimposed over at least one page of an image document. In accordance with a determination that the content of a respective image window meets image criteria, content of the image window is stored as a respective image snippet. The respective text snippet and the respective image snippet are provided to a classifier.Type: GrantFiled: December 6, 2021Date of Patent: August 1, 2023Assignee: Evernote CorporationInventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Publication number: 20230229292Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: ApplicationFiled: March 22, 2023Publication date: July 20, 2023Inventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P.J. Tanzillo
-
Patent number: 11620038Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: GrantFiled: April 5, 2022Date of Patent: April 4, 2023Assignee: Evernote CorporationInventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P. J. Tanzillo
-
Publication number: 20220269396Abstract: Selecting objects in a video stream of a smart phone includes detecting quiescence of frame content in the video stream, detecting objects in a scene corresponding to the frame content, presenting at least one of the objects to a user of the smart phone, and selecting at least one of the objects in a group of objects in response to input by the user. Detecting quiescence of frame content in the video stream may include using motion sensors in the smart phone to determine an amount of movement of the smart phone. Detecting quiescence of frame content in the video stream may include detecting changes in view angles and distances of the smart phone with respect to the scene. Detecting objects in a scene may use heuristics, custom user preferences, and/or specifics of scene layout. At least one of the objects may be a person or a document.Type: ApplicationFiled: May 10, 2022Publication date: August 25, 2022Inventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Publication number: 20220270386Abstract: Methods and systems for training a neural network to distinguish between text documents and image documents are described. A corpus of text and image documents is obtained. A page of a text document is scanned by shifting a text window to a plurality of locations. In accordance with a determination that the text in the window at a respective location meets text line criteria, the text in the window is stored as a respective text snippet. A plurality of image windows are superimposed over at least one page of an image document. In accordance with a determination that the content of a respective image window meets image criteria, content of the image window is stored as a respective image snippet. The respective text snippet and the respective image snippet are provided to a classifier.Type: ApplicationFiled: December 6, 2021Publication date: August 25, 2022Inventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Publication number: 20220229543Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: ApplicationFiled: April 5, 2022Publication date: July 21, 2022Inventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P.J. Tanzillo
-
Patent number: 11334228Abstract: Selecting objects in a video stream of a smart phone includes detecting quiescence of frame content in the video stream, detecting objects in a scene corresponding to the frame content, presenting at least one of the objects to a user of the smart phone, and selecting at least one of the objects in a group of objects in response to input by the user. Detecting quiescence of frame content in the video stream may include using motion sensors in the smart phone to determine an amount of movement of the smart phone. Detecting quiescence of frame content in the video stream may include detecting changes in view angles and distances of the smart phone with respect to the scene. Detecting objects in a scene may use heuristics, custom user preferences, and/or specifics of scene layout. At least one of the objects may be a person or a document.Type: GrantFiled: March 24, 2016Date of Patent: May 17, 2022Assignee: EVERNOTE CORPORATIONInventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Patent number: 11294553Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: GrantFiled: August 7, 2020Date of Patent: April 5, 2022Assignee: Evernote CorporationInventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P. J. Tanzillo
-
Patent number: 11195003Abstract: Methods and systems for training a neural network to distinguish between text documents and image documents are described. A corpus of text and image documents is obtained. A page of a text document is scanned by shifting a text window to a plurality of locations. In accordance with a determination that the text in the window at a respective location meets text line criteria, the text in the window is stored as a respective text snippet. A plurality of image windows are superimposed over at least one page of an image document. In accordance with a determination that the content of a respective image window meets image criteria, content of the image window is stored as a respective image snippet. The respective text snippet and the respective image snippet are provided to a classifier.Type: GrantFiled: June 27, 2019Date of Patent: December 7, 2021Assignee: EVERNOTE CORPORATIONInventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Publication number: 20210240757Abstract: This application is directed to a method for automatically identifying and transferring relevant image data. The method includes obtaining a plurality of content items from a personal content collection and determining attributes based on the plurality of content items. The method includes generating a plurality of relevance rules. The method further includes obtaining unclassified content items and determining for a first unclassified content item a plurality of aggregate relevance scores using the plurality of relevance rules. The method include determining whether a first aggregate relevance score and/or a second aggregate relevance score satisfy threshold score.Type: ApplicationFiled: February 8, 2021Publication date: August 5, 2021Inventors: Dylan Marriott, Daniel Nicolae, Ruben Bakker, Alexander Pashintsev, Zdzislaw Pawel Losvik, Eugene Livshitz, Vitaly Glazkov, Boris Gorbatov, Ilya Buryak
-
Publication number: 20210055855Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: ApplicationFiled: August 7, 2020Publication date: February 25, 2021Inventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P.J. Tanzillo
-
Patent number: 10929461Abstract: This application is directed to a method for automatically identifying and transferring relevant image data implemented at a server with a processor and memory including one or programs executable by the processor. The server obtains content items from a personal content collection of a user, analyzes the content items to identify attributes associated with the images, generates rule sets based on the identified attributes, applies the generated rule sets to a plurality of unclassified images, identifies a first set of one or more of the unclassified images, associates each image of the first set with the content items and stores the first set in the personal content collection. A second set of unclassified images is placed in a candidate list to be periodically, without user intervention, monitored and updated for storing in the personal content collection. The generated rule sets are updated after images are stored in the content collection.Type: GrantFiled: July 24, 2017Date of Patent: February 23, 2021Assignee: EVERNOTE CORPORATIONInventors: Dylan Marriott, Daniel Nicolae, Ruben Bakker, Alexander Pashintsev, Zdzislaw Pawel Losvik, Eugene Livshitz, Vitaly Glazkov, Boris Gorbatov, Ilya Buryak
-
Patent number: 10739962Abstract: Searching for documents includes retrieving objects from a physical media image using a camera from a smartphone, a user selecting a subset of the objects, forming a search query based on the subset of objects, and applying the search query to a search engine to search for the documents. Retrieving objects from a media image may include waiting for a view of the camera to stabilize. Waiting for the view of the camera to stabilize may include detecting changing content of a video flow provided to the camera and/or using motion sensors of the camera to detect movement. Retrieving objects may include the smartphone identifying possible subsets of objects in the media image. The user selecting a subset of the objects may include the smartphone presenting at least some of the possible subsets to the user and the user selecting one of the possible subsets.Type: GrantFiled: August 19, 2016Date of Patent: August 11, 2020Assignee: EVERNOTE CORPORATIONInventors: Alexander Pashintsev, Eugene Livshitz, Vitaly Glazkov, P. J. Tanzillo
-
Publication number: 20190318163Abstract: Methods and systems for training a neural network to distinguish between text documents and image documents are described. A corpus of text and image documents is obtained. A page of a text document is scanned by shifting a text window to a plurality of locations. In accordance with a determination that the text in the window at a respective location meets text line criteria, the text in the window is stored as a respective text snippet. A plurality of image windows are superimposed over at least one page of an image document. In accordance with a determination that the content of a respective image window meets image criteria, content of the image window is stored as a respective image snippet. The respective text snippet and the respective image snippet are provided to a classifier.Type: ApplicationFiled: June 27, 2019Publication date: October 17, 2019Inventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Patent number: 10372981Abstract: Determining if a document is a text page includes partitioning the document into a plurality of cells, scaling each of the cells to a standardized number of pixels to provide a corresponding snippet for each of the cells, using a classifier to examine the snippets to determine which of the cells are classified as text and which of the cells are not classified as text, determining a volume of text for the document based on a total amount of text in the document corresponding to a sum of an amount of text in each of the cells classified as text, and determining that the document is a text page in response to the total amount exceeding a pre-determined threshold. In response to the total amount being less than the pre-determined threshold, cells not classified as text may be examined further. The classifier may be provided by training a neural net.Type: GrantFiled: September 22, 2016Date of Patent: August 6, 2019Assignee: EVERNOTE CORPORATIONInventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
-
Publication number: 20180025003Abstract: This application is directed to a method for automatically identifying and transferring relevant image data implemented at a server with a processor and memory including one or programs executable by the processor. The server obtains content items from a personal content collection of a user, analyzes the content items to identify attributes associated with the images, generates rule sets based on the identified attributes, applies the generated rule sets to a plurality of unclassified images, identifies a first set of one or more of the unclassified images, associates each image of the first set with the content items and stores the first set in the personal content collection. A second set of unclassified images is placed in a candidate list to be periodically, without user intervention, monitored and updated for storing in the personal content collection. The generated rule sets are updated after images are stored in the content collection.Type: ApplicationFiled: July 24, 2017Publication date: January 25, 2018Inventors: Dylan Marriott, Daniel Nicolae, Ruben Bakker, Alexander Pashintsev, Zdzislaw Pawel Losvik, Eugene Livshitz, Vitaly Glazkov, Boris Gorbatov, Ilya Buryak