-
公开(公告)号：US09858524B2
公开(公告)日：2018-01-02
申请号：US14941454
申请日：2015-11-13
Applicant: Google Inc.
Inventor： Samy Bengio , Oriol Vinyals , Alexander Toshkov Toshev , Dumitru Erhan
CPC classification number: G06N3/0472 , G06F17/28 , G06N3/0454
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image.
-
公开(公告)号：US09514389B1
公开(公告)日：2016-12-06
申请号：US15185613
申请日：2016-06-17
Applicant: Google Inc.
Inventor： Dumitru Erhan , Christian Szegedy , Dragomir Anguelov
CPC classification number: G06K9/6256 , G06K9/3241 , G06K9/4628 , G06K9/6202 , G06K9/66 , G06N3/0454 , G06N3/084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to detect object in images. One of the methods includes receiving a training image and object location data for the training image; providing the training image to a neural network and obtaining bounding box data for the training image from the neural network, wherein the bounding box data comprises data defining a plurality of candidate bounding boxes in the training image and a respective confidence score for each candidate bounding box in the training image; determining an optimal set of assignments using the object location data for the training image and the bounding box data for the training image, wherein the optimal set of assignments assigns a respective candidate bounding box to each of the object locations; and training the neural network on the training image using the optimal set of assignments.
-
公开(公告)号：US09594984B2
公开(公告)日：2017-03-14
申请号：US14821128
申请日：2015-08-07
Applicant: Google Inc.
Inventor： Qian Yu , Liron Yatziv , Martin Christian Stumpe , Vinay Damodar Shet , Christian Szegedy , Dumitru Erhan , Sacha Christophe Arnoud
CPC classification number: G06K9/66 , G06K9/3258 , G06K9/4628 , G06K9/6201 , G06K9/6256 , G06K9/6277 , G06N3/02 , G06N3/08
Abstract: Aspects of the present disclosure relate to a method includes training a deep neural network using training images and data identifying one or more business storefront locations in the training images. The deep neural network outputs tight bounding boxes on each image. At the deep neural network, a first image may be received. The first image may be evaluated using the deep neural network. Bounding boxes may then be generated identifying business storefront locations in the first image.
Abstract translation: 本公开的方面涉及一种方法，包括使用训练图像和识别训练图像中的一个或多个商业店面位置的数据来训练深层神经网络。 深层神经网络在每个图像上输出紧密的边界框。 在深神经网络中，可以接收第一图像。 可以使用深层神经网络来评估第一图像。 然后可以生成标识框，识别第一图像中的商店店面位置。
-
Patent Agency Ranking
公开(公告)号：US20150170002A1
公开(公告)日：2015-06-18
申请号：US14288194
申请日：2014-05-27
Applicant: Google Inc.
Inventor： Christian Szegedy , Dumitru Erhan , Alexander Toshkov Toshev
IPC: G06K9/66
CPC classification number: G06K9/66 , G06K9/4628
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes receiving an input image. A full object mask is generated by providing the input image to a first deep neural network object detector that produces a full object mask for an object of a particular object type depicted in the input image. A partial object mask is generated by providing the input image to a second deep neural network object detector that produces a partial object mask for a portion of the object of the particular object type depicted in the input image. A bounding box is determined for the object in the image using the full object mask and the partial object mask.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于检测图像中的对象。 其中一种方法包括接收输入图像。 通过将输入图像提供给产生输入图像中描绘的特定对象类型的对象的完整对象掩模的第一深层神经网络对象检测器来生成完整对象掩码。 通过将输入图像提供给第二深神经网络对象检测器来产生部分对象掩模，该第二深神经网络对象检测器为输入图像中描绘的特定对象类型的对象的一部分产生部分对象掩模。 使用完整对象掩码和部分对象掩码，为图像中的对象确定边框。
-
公开(公告)号：US20170039457A1
公开(公告)日：2017-02-09
申请号：US14821128
申请日：2015-08-07
Applicant: Google Inc.
Inventor： Qian Yu , Liron Yatziv , Martin Christian Stumpe , Vinay Damodar Shet , Christian Szegedy , Dumitru Erhan , Sacha Christophe Arnoud
CPC classification number: G06K9/66 , G06K9/3258 , G06K9/4628 , G06K9/6201 , G06K9/6256 , G06K9/6277 , G06N3/02 , G06N3/08
Abstract: Aspects of the present disclosure relate to a method includes training a deep neural network using training images and data identifying one or more business storefront locations in the training images. The deep neural network outputs tight bounding boxes on each image. At the deep neural network, a first image may be received. The first image may be evaluated using the deep neural network. Bounding boxes may then be generated identifying business storefront locations in the first image.
Abstract translation: 本公开的方面涉及一种方法，包括使用训练图像和识别训练图像中的一个或多个商业店面位置的数据来训练深层神经网络。 深层神经网络在每个图像上输出紧密的边界框。 在深神经网络中，可以接收第一图像。 可以使用深层神经网络来评估第一图像。 然后可以生成标识框，识别第一图像中的商店店面位置。
-
公开(公告)号：US09373057B1
公开(公告)日：2016-06-21
申请号：US14528815
申请日：2014-10-30
Applicant: Google Inc.
Inventor： Dumitru Erhan , Christian Szegedy , Dragomir Anguelov
CPC classification number: G06K9/6256 , G06K9/3241 , G06K9/4628 , G06K9/6202 , G06K9/66 , G06N3/0454 , G06N3/084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to detect object in images. One of the methods includes receiving a training image and object location data for the training image; providing the training image to a neural network and obtaining bounding box data for the training image from the neural network, wherein the bounding box data comprises data defining a plurality of candidate bounding boxes in the training image and a respective confidence score for each candidate bounding box in the training image; determining an optimal set of assignments using the object location data for the training image and the bounding box data for the training image, wherein the optimal set of assignments assigns a respective candidate bounding box to each of the object locations; and training the neural network on the training image using the optimal set of assignments.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于训练神经网络以检测图像中的对象。 其中一种方法包括接收训练图像和训练图像的对象位置数据; 将训练图像提供给神经网络并从神经网络获得用于训练图像的边界框数据，其中边界框数据包括定义训练图像中的多个候选边界框的数据和每个候选边界框的相应置信度分数 在训练形象中; 使用所述训练图像的所述对象位置数据和所述训练图像的所述边界框数据来确定最佳的分配集合，其中所述最佳分配集合将相应的候选边界框分配给每个所述对象位置; 并使用最佳赋值集在训练图像上训练神经网络。
-
公开(公告)号：US20160140435A1
公开(公告)日：2016-05-19
申请号：US14941454
申请日：2015-11-13
Applicant: Google Inc.
Inventor： Samy Bengio , Oriol Vinyals , Alexander Toshkov Toshev , Dumitru Erhan
CPC classification number: G06N3/0472 , G06F17/28 , G06N3/0454
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于产生输入图像的描述。 方法之一包括获取输入图像; 使用第一神经网络处理所述输入图像以生成所述输入图像的替代表示; 以及使用第二神经网络处理所述输入图像的替代表示，以生成描述所述输入图像的目标自然语言中的多个单词的序列。
-
公开(公告)号：US09275308B2
公开(公告)日：2016-03-01
申请号：US14288194
申请日：2014-05-27
Applicant: Google Inc.
Inventor： Christian Szegedy , Dumitru Erhan , Alexander Toshkov Toshev
CPC classification number: G06K9/66 , G06K9/4628
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes receiving an input image. A full object mask is generated by providing the input image to a first deep neural network object detector that produces a full object mask for an object of a particular object type depicted in the input image. A partial object mask is generated by providing the input image to a second deep neural network object detector that produces a partial object mask for a portion of the object of the particular object type depicted in the input image. A bounding box is determined for the object in the image using the full object mask and the partial object mask.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于检测图像中的对象。 其中一种方法包括接收输入图像。 通过将输入图像提供给产生输入图像中描绘的特定对象类型的对象的完整对象掩模的第一深层神经网络对象检测器来生成完整对象掩码。 通过将输入图像提供给第二深神经网络对象检测器来产生部分对象掩模，该第二深神经网络对象检测器为输入图像中描绘的特定对象类型的对象的一部分产生部分对象掩模。 使用完整对象掩码和部分对象掩码，为图像中的对象确定边框。
-
-
-
-
-
-
-
Search Results
8
records
(took 0.017 seconds)
