-
公开(公告)号：US20180024974A1
公开(公告)日：2018-01-25
申请号：US15658289
申请日：2017-07-24
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Peter N. Belhumeur , Ying Xiong , Jongmin Baek , Simon Kozlov , Thomas Berg , David J. Kriegman
Abstract: The present disclosure is directed toward systems and methods that efficiently and effectively generate an enhanced document image of a displayed document in an image frame captured from a live image feed. For example, systems and methods described herein apply a document enhancement process to a displayed document in an image frame that result in an enhanced document image that is cropped, rectified, un-shadowed, and with dark text against a mostly white background. Additionally, systems and method described herein determine whether a stored digital content item includes a displayed document. In response to determining that a stored digital content item does include a displayed document, systems and methods described herein generate an enhanced document image of a displayed document included in the stored digital content item.
-
公开(公告)号：US20160323332A1
公开(公告)日：2016-11-03
申请号：US15207244
申请日：2016-07-11
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Thomas Kleinpeter , Thomas Wright , Ramesh Balakrishnan , Tina Wen , Rajeev Nayak
IPC: H04L29/06 , H04L12/58 , H04L29/08 , G06F3/0482 , G06F3/0484
CPC classification number: H04L65/403 , G06F3/0481 , G06F3/0482 , G06F3/0484 , G06F9/542 , G06F11/2082 , H04L51/04 , H04L51/046 , H04L67/06 , H04L67/1097 , H04L67/141
Abstract: Systems and methods are provided for creating shared virtual spaces (“rooms”). A room may be created when a user first shares images with another user. A user may send a request to a content management system to share one or more images with various contacts. In response, a room is created by the content management system in which a copy of each image is stored. Images added to a room are copied to a separate “rooms” database, and “locked,” being saved in the room for a period of time, which may be indefinitely. Changes made by the user to a room via a user device may be displayed as soon as indicated, without waiting for the information to be sent to a system server or its state to be made consistent with that of the user device. Room activity notifications may be sent to members in various ways.
-
公开(公告)号：US20160203585A1
公开(公告)日：2016-07-14
申请号：US15076394
申请日：2016-03-21
Applicant: Dropbox, Inc.
Inventor： Nils Peter Welinder , Szu-Po Wang
CPC classification number: G06T3/40 , G06F17/30256 , G06K9/00979 , G06K9/3233 , G06K9/4671 , G06K9/52 , G06K9/6215 , G06K2009/4666 , G06T7/60 , G06T11/60 , G06T2210/22
Abstract: Systems and methods in accordance with embodiments of the invention automatically crop images based upon the location of one or more regions of interest (ROIs) identified within the cropped image. In one embodiment, an image cropping application configures a processor to utilize at least one object detector to identify at least one region of interest within an image. A plurality of candidate cropped images within the image are selected and for each candidate cropped image, an output is generated by weighting each of the at least one region of interest contained within the candidate cropped image as a function of its position within the candidate cropped image. A crop location can then be selected based upon the candidate cropped image having the largest output.
Abstract translation: 根据本发明的实施例的系统和方法基于在裁剪图像内识别的一个或多个感兴趣区域（ROI）的位置来自动裁剪图像。 在一个实施例中，图像裁剪应用程序配置处理器以利用至少一个对象检测器来识别图像内的至少一个感兴趣区域。 选择图像内的多个候选裁剪图像，并且对于每个候选剪切图像，通过对包含在候选裁剪图像内的至少一个感兴趣区域中的每一个作为其在候选裁剪图像内的位置的函数来加权来生成输出 。 然后可以基于具有最大输出的候选裁剪图像来选择裁剪位置。
-
公开(公告)号：US20210271807A1
公开(公告)日：2021-09-02
申请号：US17323838
申请日：2021-05-18
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Peter N. Belhumeur , Ying Xiong , Jongmin Baek , Simon Kozlov , Thomas Berg , David J. Kriegman
IPC: G06F40/166 , G06T7/194 , G06T11/00 , G06K9/00 , G06F16/93 , G06T5/00 , G06F40/106 , G06F40/123 , G06F40/197 , G06K9/46 , G06K9/78
Abstract: The present disclosure is directed toward systems and methods that efficiently and effectively generate an enhanced document image of a displayed document in an image frame captured from a live image feed. For example, systems and methods described herein apply a document enhancement process to a displayed document in an image frame that result in an enhanced document image that is cropped, rectified, un-shadowed, and with dark text against a mostly white background. Additionally, systems and method described herein determine whether a stored digital content item includes a displayed document. In response to determining that a stored digital content item does include a displayed document, systems and methods described herein generate an enhanced document image of a displayed document included in the stored digital content item.
-
公开(公告)号：US20210264098A1
公开(公告)日：2021-08-26
申请号：US17315027
申请日：2021-05-07
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Peter N. Belhumeur , Ying Xiong , Jongmin Baek , Simon Kozlov , Thomas Berg , David J. Kriegman
IPC: G06F40/166 , G06T7/194 , G06T11/00 , G06K9/00 , G06F16/93 , G06T5/00 , G06F40/106 , G06F40/123 , G06F40/197 , G06K9/46 , G06K9/78
Abstract: The present disclosure is directed toward systems and methods to quickly and accurately identify boundaries of a displayed document in a live camera image feed, and provide a document boundary indicator within the live camera image feed. For example, systems and methods described herein utilize different display document detection processes in parallel to generate and provide a document boundary indicator that accurately corresponds with a displayed document within a live camera image feed. Thus, a user of the mobile computing device can easily see whether the document identification system has correctly identified the displayed document within the camera viewfinder feed.
-
Patent Agency Ranking
公开(公告)号：US11003841B2
公开(公告)日：2021-05-11
申请号：US16830077
申请日：2020-03-25
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Peter N. Belhumeur , Ying Xiong , Jongmin Baek , Simon Kozlov , Thomas Berg , David J. Kriegman
IPC: G06F40/166 , G06T7/194 , G06T11/00 , G06K9/00 , G06F16/93 , G06T5/00 , G06F40/106 , G06F40/123 , G06F40/197 , G06K9/46 , G06K9/78 , G06F3/0484 , G06K9/40 , G06K9/32 , G06T11/60 , G06F3/12 , G06F40/103 , G06F40/169 , G06F17/00
Abstract: The present disclosure is directed toward systems and methods that efficiently and effectively generate an enhanced document image of a displayed document in an image frame captured from a live image feed. For example, systems and methods described herein apply a document enhancement process to a displayed document in an image frame that result in an enhanced document image that is cropped, rectified, un-shadowed, and with dark text against a mostly white background. Additionally, systems and method described herein determine whether a stored digital content item includes a displayed document. In response to determining that a stored digital content item does include a displayed document, systems and methods described herein generate an enhanced document image of a displayed document included in the stored digital content item.
-
公开(公告)号：US20200226319A1
公开(公告)日：2020-07-16
申请号：US16830077
申请日：2020-03-25
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Peter N. Belhumeur , Ying Xiong , Jongmin Baek , Simon Kozlov , Thomas Berg , David J. Kriegman
IPC: G06F40/166 , G06T7/194 , G06T11/00 , G06K9/00 , G06F16/93 , G06T5/00 , G06F40/106 , G06F40/123 , G06F40/197 , G06K9/46 , G06K9/78
Abstract: The present disclosure is directed toward systems and methods that efficiently and effectively generate an enhanced document image of a displayed document in an image frame captured from a live image feed. For example, systems and methods described herein apply a document enhancement process to a displayed document in an image frame that result in an enhanced document image that is cropped, rectified, un-shadowed, and with dark text against a mostly white background. Additionally, systems and method described herein determine whether a stored digital content item includes a displayed document. In response to determining that a stored digital content item does include a displayed document, systems and methods described herein generate an enhanced document image of a displayed document included in the stored digital content item.
-
公开(公告)号：US10255527B2
公开(公告)日：2019-04-09
申请号：US15711469
申请日：2017-09-21
Applicant: DROPBOX, INC.
Inventor： David J. Kriegman , Peter N. Belhumeur , Thomas Berg , Nils Peter Welinder
Abstract: The present disclosure is directed toward systems and methods that enable more accurate digital object classification. In particular, disclosed systems and methods address inaccuracies in digital object classification introduced by variations in classification scores. Specifically, in one or more embodiments, disclosed systems and methods generate probability functions utilizing digital test objects and transform classifications scores into normalized classification scores utilizing probability functions. Disclosed systems and methods utilize normalized classification scores to more accurately classify and identify digital objects in a variety of applications.
-
公开(公告)号：US10140517B2
公开(公告)日：2018-11-27
申请号：US14453284
申请日：2014-08-06
Applicant: Dropbox, Inc.
Inventor： Boris Babenko , Nils Peter Welinder
IPC: G06K9/00
Abstract: Embodiments of the present invention analyze and score each image associated with a group to determine representative image or images for the group. Such analysis can include detecting objects shown in the images, determining the quality of the images, and/or contextually analyzing the images as a group. In some embodiments, each image in a group (e.g., an event) of images can be analyzed by one or more image analysis modules that calculate a score for the image based on a different image characteristic. A composite image score can then be calculated based on the various image characteristic scores to identify the image or images to be used as to represent the group.
-
公开(公告)号：US20180025251A1
公开(公告)日：2018-01-25
申请号：US15658291
申请日：2017-07-24
Applicant: DROPBOX, INC.
Inventor： Nils Peter Welinder , Peter N. Belhumeur , Ying Xiong , Jongmin Baek , Simon Kozlov , Thomas Berg , David J. Kriegman
CPC classification number: G06F17/24 , G06F3/04842 , G06F16/93 , G06F17/212 , G06F17/2205 , G06F17/2288 , G06K9/00442 , G06K9/00456 , G06K9/00463 , G06K9/00744 , G06K9/3208 , G06K9/40 , G06K9/4604 , G06K9/78 , G06T5/002 , G06T5/007 , G06T7/194 , G06T11/001 , G06T2207/20056 , G06T2207/20081 , G06T2207/20084 , G06T2207/30176 , G06T2210/22
Abstract: The present disclosure is directed toward systems and methods to quickly and accurately identify boundaries of a displayed document in a live camera image feed, and provide a document boundary indicator within the live camera image feed. For example, systems and methods described herein utilize different display document detection processes in parallel to generate and provide a document boundary indicator that accurately corresponds with a displayed document within a live camera image feed. Thus, a user of the mobile computing device can easily see whether the document identification system has correctly identified the displayed document within the camera viewfinder feed.
-
-
-
-
-
-
-
-
-
Search Results
50
records
(took 0.017 seconds)
