-
公开(公告)号：US09183226B2
公开(公告)日：2015-11-10
申请号：US14336692
申请日：2014-07-21
申请人： Google Inc.
CPC分类号： G06F17/30253 , G06F17/30244 , G06F17/30864 , G06K9/4676 , G06K9/6256 , G06K9/66 , G06K2209/01
摘要： An image classification system trains an image classification model to classify images relative to text appearing with the images. Training images are iteratively selected and classified by the image classification model according to feature vectors of the training images. An independent model is trained for unique n-grams of text. The image classification system obtains text appearing with an image and parses the text into candidate labels for the image. The image classification system determines whether an image classification model has been trained for the candidate labels. When an image classification model corresponding to a candidate label has been trained, the image classification subsystem classifies the image relative to the candidate label. The image is labeled based on candidate labels for which the image is classified as a positive image.
摘要翻译： 图像分类系统训练图像分类模型，以便相对于与图像一起出现的文本来分类图像。 根据训练图像的特征向量，通过图像分类模型迭代地选择和分类训练图像。 对独特的n克文本进行了独立的模型训练。 图像分类系统获得与图像一起出现的文本，并将文本解析为图像的候选标签。 图像分类系统确定是否针对候选标签训练了图像分类模型。 当对应于候选标签的图像分类模型已经被训练时，图像分类子系统将图像相对于候选标签进行分类。 基于将图像分类为正图像的候选标签来标记图像。
-
公开(公告)号：US09076270B2
公开(公告)日：2015-07-07
申请号：US13894335
申请日：2013-05-14
申请人： Google Inc.
发明人： Erik Murphy-Chutorian , Matthew Steiner , Vivek Kwatra , Shengyang Dai , John Spiegel , Nicholas Butko , Falk Sticken , Florian Kriener , Tom Binder , John Flynn , Troy Chinen , Steven VanDeBogart , Nikolaos Trogkanis , Ingo Wehmeyer , Matthias Grundmann
CPC分类号： G06K9/6218 , G06F17/30247 , G06K9/00228 , G06K9/00677 , G06T11/60
摘要： Implementations generally relate to generating compositional media content. In some implementations, a method includes receiving a plurality of photos from a user, and determining one or more composition types from the photos. The method also includes generating compositions from the selected photos based on the one or more determined composition types. The method also includes providing the one or more generated compositions to the user.
摘要翻译： 实现通常涉及生成组合媒体内容。 在一些实现中，一种方法包括从用户接收多张照片，以及从照片中确定一个或多个合成类型。 该方法还包括基于一种或多种所确定的组合物类型从所选择的照片生成组合物。 该方法还包括向使用者提供一种或多种生成的组合物。
-
公开(公告)号：US20150169754A1
公开(公告)日：2015-06-18
申请号：US13780848
申请日：2013-02-28
申请人： Google Inc.
IPC分类号： G06F17/30
CPC分类号： G06F17/30256
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for analyzing image search result relevance. In one aspect, a method includes receiving result data specifying a search query and responsive image search results that reference images that are responsive to the search query. A determination is made that the search query matches an indexed query. An image relevance model is identified for the indexed query. The image relevance model can output a relevance score adjustment factor for an image search result based on image feature values of the image that is referenced by the search result. A relevance score adjustment factor is determined for each image search result using the identified image relevance model. A relevance score for each image search result is adjusted using the image's image relevance score adjustment factor. The images are ranked based on the adjusted relevance scores.
摘要翻译： 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，用于分析图像搜索结果相关性。 一方面，一种方法包括接收指定搜索查询的结果数据和引用响应于搜索查询的图像的响应图像搜索结果。 确定搜索查询与索引查询匹配。 为索引查询识别图像相关性模型。 图像相关性模型可以基于由搜索结果引用的图像的图像特征值输出图像搜索结果的相关性分数调整因子。 使用所识别的图像相关性模型，针对每个图像搜索结果确定相关性得分调整因子。 使用图像的图像相关性得分调整因子来调整每个图像搜索结果的相关性分数。 图像根据调整的相关性分数进行排名。
-
公开(公告)号：US20140233811A1
公开(公告)日：2014-08-21
申请号：US13894341
申请日：2013-05-14
申请人： Google Inc.
发明人： Erik Murphy-Chutorian , Shengyang Dai , Ehud Rivlin , Chuck Joseph Rosenberg , Mei Han , Kyle Heath
IPC分类号： G06K9/62
CPC分类号： G06K9/6267 , G06K9/00677 , G06K9/62
摘要： Embodiments generally relate to summarizing a photo album. In one embodiment, a method includes grouping photos into a plurality of groups of photos, and selecting a plurality of representative photos, where each representative photo represents a respective group from the plurality of groups, where the selecting is based on a quality score of each of the photos, and where each quality score is based on different types of attributes. The method also includes providing the plurality of representative photos to a user.
摘要翻译： 实施例通常涉及总结相册。 在一个实施例中，一种方法包括将照片分组成多组照片，并且选择多个代表照片，其中每个代表照片表示来自多个组的相应组，其中选择基于每个组的质量得分 的照片，每个质量得分都基于不同类型的属性。 该方法还包括向用户提供多个有代表性的照片。
-
公开(公告)号：US09858295B2
公开(公告)日：2018-01-02
申请号：US14747079
申请日：2015-06-23
申请人： Google Inc.
CPC分类号： G06F17/30256 , G06K9/46 , G06K9/52 , G06K9/6267 , G06Q10/00
摘要： Implementations generally relate to ranking and selecting images for display from a set of images. In some implementations, a computer-implemented method includes providing selected images for display, including examining characteristics of a plurality of images, where the examined characteristics include two or more of: visual capture characteristics, visual content characteristics, and social popularity characteristics of the images. The method determines individual scores for the respective examined characteristics of the images, determines overall scores of the images based on a combination of the individual scores for the examined characteristics of the images, and determines a ranking of the images based on the overall scores. The method selects one or more images based on the ranking of the images, and causes a display of the one or more selected images.
-
公开(公告)号：US09690980B2
公开(公告)日：2017-06-27
申请号：US13840744
申请日：2013-03-15
申请人： Google Inc.
发明人： Peter J. Hong , Ajmal A. Asver , Chandrashekar Raghavan , Denise Ho , Darwin Yamamoto , Erik Murphy-Chutorian
CPC分类号： G06K9/00288 , G06F17/30244 , G06K9/00221 , G06K9/036
摘要： The disclosed subject matter relates to computer implemented methods for automatic curation of digital images. In one aspect, the method includes selecting one of every two or more duplicate digital images of a plurality of digital images. The method further includes calculating an image quality score for each of the selected digital images. The method further includes associating a ranking with each of the selected digital images based on its respective calculated image quality score.
-
公开(公告)号：US09460533B2
公开(公告)日：2016-10-04
申请号：US14064164
申请日：2013-10-27
申请人： Google Inc.
CPC分类号： G06T11/60 , G06T7/73 , G06T2207/10004 , G06T2207/20221
摘要： Implementations generally relate to generating image compositions. In some implementations, a method includes receiving a plurality of photos from a user and determining one or more composition types from the photos. The method further includes generating one or more compositions from the received photos based on the one or more determined composition types, where each composition is based on modified foregrounds of the photos. The method further includes providing the one or more generated compositions to the user.
摘要翻译： 实现通常涉及生成图像组合。 在一些实现中，一种方法包括从用户接收多张照片并从照片中确定一个或多个合成类型。 该方法还包括基于一个或多个确定的组合类型从所接收的照片生成一个或多个合成，其中每个组合基于照片的修改前景。 该方法还包括向用户提供一种或多种生成的组合物。
-
公开(公告)号：US20150161172A1
公开(公告)日：2015-06-11
申请号：US13966737
申请日：2013-08-14
申请人： Google Inc
IPC分类号： G06F17/30
CPC分类号： G06F17/30256 , G06F17/30271 , G06K9/6223 , G06K9/6262
摘要： Methods, systems, and apparatus, including computer program products, for identifying images relevant to a query are disclosed. An image search subsystem selects images to reference in image search results that are responsive to a query based on an image relevance model that is trained for the query. An independent image relevance model is trained for each unique query that is identified by the image search subsystem. The image relevance models can be applied to images to order image search results obtained for the query. Each relevance model is trained based on content feature values of images that are identified as being relevant to the query (e.g., frequently selected from the image search results) and images that are identified as being relevant to another unique query. The trained model is applied to the content feature values of all known images to generate an image relevance score that can be used to order search results for the query.
摘要翻译： 公开了用于识别与查询相关的图像的方法，系统和装置，包括计算机程序产品。 图像搜索子系统基于针对查询进行训练的图像相关性模型，在响应于查询的图像搜索结果中选择图像进行参考。 对由图像搜索子系统识别的每个唯一查询训练独立的图像相关性模型。 图像相关性模型可以应用于图像以订购为查询获得的图像搜索结果。 基于被识别为与查询相关（例如，从图像搜索结果中频繁选择）的图像的内容特征值以及被识别为与另一唯一查询相关的图像来训练每个相关性模型。 经过训练的模型被应用于所有已知图像的内容特征值，以生成可用于对查询进行搜索结果的图像相关性分数。
-
公开(公告)号：US20140340409A1
公开(公告)日：2014-11-20
申请号：US13894198
申请日：2013-05-14
申请人： Google Inc.
发明人： Erik Murphy-Chutorian , Josh Wills , Nicholas Butko , Matthew Steiner , Vivek Kwatra , Dave Cohen
IPC分类号： G06T13/00
摘要： Implementations generally relate to generating photo animations. In some implementations, a method includes receives a plurality of photos from a user. The method also includes selecting photos from the plurality of photos that meet one or more predetermined similarity criteria. The method also includes generating an animation using the selected photos.
摘要翻译： 实现通常涉及生成照片动画。 在一些实现中，一种方法包括从用户接收多张照片。 该方法还包括从满足一个或多个预定相似性标准的多个照片中选择照片。 该方法还包括使用所选择的照片生成动画。
-
公开(公告)号：US09582731B1
公开(公告)日：2017-02-28
申请号：US14686635
申请日：2015-04-14
申请人： Google Inc.
CPC分类号： G06K9/209 , G06K9/00664
摘要： Implementations relate to detecting spherical images. In some implementations, a computer-executed method includes obtaining an image, examining at least one characteristic of the image, and determining that the image is a spherical image based on the at least one examined characteristic. The method modifies metadata associated with the image to designate the image for spherical display.
摘要翻译： 实现涉及检测球形图像。 在一些实现中，计算机执行的方法包括获得图像，检查图像的至少一个特征，以及基于至少一个被检查的特征来确定图像是球面图像。 该方法修改与图像相关联的元数据，以指定用于球面显示的图像。
-
-
-
-
-
-
-
-
-
搜索结果
23 条记录 (耗时 0.018 秒)
