-
公开(公告)号：US20150161466A1
公开(公告)日：2015-06-11
申请号：US14102477
申请日：2013-12-10
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：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：US10147163B2
公开(公告)日：2018-12-04
申请号：US15076394
申请日：2016-03-21
Applicant: Dropbox, Inc.
Inventor： Nils Peter Welinder , Szu-Po Wang
IPC: G06K9/00 , G06T3/40 , G06F17/30 , G06K9/46 , G06K9/52 , G06K9/62 , G06T7/60 , G06K9/32 , G06T11/60
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.
-
公开(公告)号：US09292756B2
公开(公告)日：2016-03-22
申请号：US14102477
申请日：2013-12-10
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。
-
-
-
Search Results
4
records
(took 0.01 seconds)
