专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明申请

US20170372169A1 METHOD AND APPARATUS FOR RECOGNIZING IMAGE CONTENT 审中-公开
公开(公告)号：US20170372169A1
公开(公告)日：2017-12-28
申请号：US15701136
申请日：2017-09-11
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xianglin LI
IPC分类号： G06K9/62
CPC分类号： G06K9/6202 , G06F16/5838 , G06K9/4628 , G06K9/6215 , G06K9/6223 , G06K9/6227 , G06K9/6269 , G06K9/6273 , G06K9/628
摘要： The present disclosure provides a method performed at a computing device for recognizing an image's content. The method includes: extracting one or more features from an image to be recognized; comparing the features of the image with a set of image classifiers and obtaining a probability value for each image classifier; selecting, from the set of image classifiers, at least one image classifier as a target image classifier according to the probability value of the image classifier; determining a degree of similarity between each image and the image to be recognized, and selecting, from the target image classifier, multiple images as target images when their respective degrees of similarity with the image to be recognized exceed a predefined threshold; and labeling, the image to be recognized according to a class label corresponding to the target image classifier and entity labels corresponding to the target images in the target image classifier.

52. 发明授权

US09807473B2 Jointly modeling embedding and translation to bridge video and language 有权
公开(公告)号：US09807473B2
公开(公告)日：2017-10-31
申请号：US14946988
申请日：2015-11-20
申请人： Microsoft Technology Licensing, LLC
发明人： Tao Mei , Ting Yao , Yong Rui
IPC分类号： H04N5/445 , H04N21/8405 , G06F17/27 , G06K9/00 , G06N3/08
CPC分类号： H04N21/8405 , G06F17/274 , G06F17/2785 , G06K9/00718 , G06K9/6273 , G06N3/08 , H04N21/26603
摘要： Video description generation using neural network training based on relevance and coherence is described. In some examples, long short-term memory with visual-semantic embedding (LSTM-E) can maximize the probability of generating the next word given previous words and visual content and can create a visual-semantic embedding space for enforcing the relationship between the semantics of an entire sentence and visual content. LSTM-E can include a 2-D and/or 3-D deep convolutional neural networks for learning powerful video representation, a deep recurrent neural network for generating sentences, and a joint embedding model for exploring the relationships between visual content and sentence semantics.

53. 发明授权

US09721334B2 Work-piece defect inspection via optical images and CT images 有权
公开(公告)号：US09721334B2
公开(公告)日：2017-08-01
申请号：US14957662
申请日：2015-12-03
申请人： International Business Machines Corporation
发明人： Boliang Chen , Min Gong , Dong Sheng Li , Junchi Yan , Chao Zhang , Wei Peng Zhang
IPC分类号： G06T7/00 , G06K9/62 , H04N5/232
CPC分类号： G06K9/6256 , G06K9/4628 , G06K9/6273 , G06K9/6857 , G06K2209/05 , G06T7/001 , G06T2207/10081 , G06T2207/10116 , G06T2207/20016 , G06T2207/30164
摘要： A computer-implemented method, computer program product, and system for detecting work-piece defects. The computer-implemented method may include: receiving a first image of a training work-piece captured using a non-destructive imaging process and a second image of the training work-piece captured using a destructive imaging process; receiving an image of a work-piece captured using a non-destructive imaging process, wherein the work-piece is substantially similar to the training work-piece, and the non-destructive imaging process used to capture the work-piece is substantially similar to the non-destructive imaging process used to capture the training work-piece; matching the image of the work-piece to the first image of the training work-piece; and enhancing the image of the work-piece using the second image of the training work-piece, in response to the image of the work-piece matching the first image of the training work-piece.

54. 发明申请

US20170150235A1 Jointly Modeling Embedding and Translation to Bridge Video and Language 有权
公开(公告)号：US20170150235A1
公开(公告)日：2017-05-25
申请号：US14946988
申请日：2015-11-20
申请人： Microsoft Technology Licensing, LLC
发明人： Tao Mei , Ting Yao , Yong Rui
IPC分类号： H04N21/8405 , G06K9/00 , G06N3/08 , G06F17/27
CPC分类号： H04N21/8405 , G06F17/274 , G06F17/2785 , G06K9/00718 , G06K9/6273 , G06N3/08 , H04N21/26603
摘要： Video description generation using neural network training based on relevance and coherence is described. In some examples, long short-term memory with visual-semantic embedding (LSTM-E) can maximize the probability of generating the next word given previous words and visual content and can create a visual-semantic embedding space for enforcing the relationship between the semantics of an entire sentence and visual content. LSTM-E can include a 2-D and/or 3-D deep convolutional neural networks for learning powerful video representation, a deep recurrent neural network for generating sentences, and a joint embedding model for exploring the relationships between visual content and sentence semantics.

55. 发明授权

US09582726B2 Systems and methods for image processing in a deep convolution network 有权
标题翻译：深卷积网络中图像处理的系统和方法
公开(公告)号：US09582726B2
公开(公告)日：2017-02-28
申请号：US14749387
申请日：2015-06-24
申请人： QUALCOMM Incorporated
发明人： Yunke Pan , Dashan Gao , Xin Zhong , Shuxue Quan
IPC分类号： G06K9/00 , G06T5/20 , G06T11/60
CPC分类号： G06K9/00986 , G06K9/4623 , G06K9/6273 , G06N3/0454 , G06T5/20
摘要： A method performed by an electronic device is described. The method includes interleaving multiple input image channels to produce an interleaved multi-channel input. The method also includes loading the interleaved multi-channel input to a single-instruction multiple data (SIMD) processor. The method further includes convolving the interleaved multi-channel input with a multi-channel filter.
摘要翻译：描述由电子设备执行的方法。该方法包括交织多个输入图像通道以产生交织的多通道输入。该方法还包括将交织的多通道输入加载到单指令多数据（SIMD）处理器。该方法还包括用交错多通道输入与多通道滤波器进行卷积。

56. 发明授权

US09547913B2 Information processing device, information processing apparatus, information processing method, and program 有权
标题翻译：信息处理装置，信息处理装置，信息处理方法和程序
公开(公告)号：US09547913B2
公开(公告)日：2017-01-17
申请号：US14845462
申请日：2015-09-04
申请人： NEC Corporation
发明人： Takashi Shibata
IPC分类号： G06T7/00 , G06T7/20
CPC分类号： G06T7/30 , G06K9/00261 , G06K9/3241 , G06K9/6273 , G06T7/32 , G06T7/37 , G06T2207/20048 , G06T2207/20212
摘要： An information processing device, apparatus, method and non-transitory computer-readable storage medium are disclosed. An information processing device may include a memory storing instructions, and at least one processor configured to process the instructions to generate a comparison image by transforming a reference image, associate the comparison image with a class variable representing an object included in the reference image, calculate a degree of difference between an input patch which is an image representing a sub-region of an input image and a comparison patch which is an image representing a sub-region of the comparison image, estimate a displacement vector between the input patch and the comparison patch, calculate a first degree of reliability corresponding to the displacement vector and the class variable on the basis of the displacement vector and the degree of difference, calculate a second degree of reliability for each comparison patch on the basis of the first degree of reliability, and identify the object is represented by the class variable associated with the comparison image including the comparison patch whose second degree of reliability is greater than a predetermined threshold value, as a recognition target.
摘要翻译：公开了一种信息处理设备，设备，方法和非暂时性计算机可读存储介质。信息处理装置可以包括存储指令的存储器，以及至少一个处理器，被配置为通过变换参考图像来处理指令以生成比较图像，将比较图像与表示参考图像中包括的对象的类变量相关联，计算作为表示输入图像的子区域的图像的输入贴片与作为表示比较图像的子区域的图像的比较贴片之间的差异程度，估计输入贴片和比较之间的位移矢量基于位移矢量和差异度计算与位移矢量和类变量相对应的第一可靠度，基于第一可靠度计算每个比较片的第二可靠度，并且识别对象由与比较图像相关联的类变量包括将第二可靠度大于预定阈值的比较补丁作为识别目标。

57. 发明授权

US09349193B2 Method and apparatus for moving object detection using principal component analysis based radial basis function network 有权
标题翻译：使用基于主成分分析的径向基函数网络来移动物体检测的方法和装置
公开(公告)号：US09349193B2
公开(公告)日：2016-05-24
申请号：US14231637
申请日：2014-03-31
申请人： National Taipei University of Technology
发明人： Bo-Hao Chen , Shih-Chia Huang
IPC分类号： G06T7/00 , G06T7/20 , G06K9/00 , G06K9/62 , G06K9/32
CPC分类号： G06T7/208 , G06K9/00785 , G06K9/6273 , G06K2009/3291 , G06T7/194 , G06T7/248 , G06T7/277 , G06T2207/10016 , G06T2207/20021 , G06T2207/20048 , G06T2207/20076 , G06T2207/20084 , G06T2207/30236
摘要： A method for moving object detection based on a Principal Component Analysis-based Radial Basis Function network (PCA-based RBF network) includes the following steps. A sequence of incoming frames of a fixed location delivered over a network are received. A plurality of Eigen-patterns are generated from the sequence of incoming frames based on a Principal Component Analysis (PCA) model. A background model is constructed from the sequence of incoming frames based on a Radial Basis Function (RBF) network model. A current incoming frame is received and divided into a plurality of current incoming blocks. Each of the current incoming blocks is classified as either a background block or a moving object block according to the Eigen-patterns. Whether a current incoming pixel of the moving object blocks among the current incoming blocks is a moving object pixel or a background pixel is determined according to the background model.
摘要翻译：基于主成分分析的径向基函数网络（基于PCA的RBF网络）移动物体检测的方法包括以下步骤：接收通过网络传送的固定位置的输入帧序列。基于主成分分析（PCA）模型，从入站帧序列生成多个特征模式。基于径向基函数（RBF）网络模型的入站帧序列构建背景模型。当前输入帧被接收并被分成多个当前传入块。根据本征模式，当前输入块中的每一个被分类为背景块或移动物体块。根据背景模型确定当前输入块中的移动物体块的当前输入像素是移动物体像素还是背景像素。

58. 发明申请

US20160100080A1 IMAGE DATA CLUSTERING AND COLOR CONVERSION 有权
标题翻译：图像数据聚合和颜色转换
公开(公告)号：US20160100080A1
公开(公告)日：2016-04-07
申请号：US14959342
申请日：2015-12-04
申请人： Yue Qiao
发明人： Yue Qiao
IPC分类号： H04N1/54 , G06K15/02 , G06K9/46 , G06K9/62 , H04N1/52 , H04N1/60
CPC分类号： H04N1/54 , G06K9/4652 , G06K9/6226 , G06K9/6272 , G06K9/6273 , G06K15/02 , H04N1/52 , H04N1/6008 , H04N1/6058 , H04N1/6061 , H04N1/6063 , H04N1/6066 , H04N1/6069
摘要： Methods and systems herein provide for color conversion of image data to another color space. Such color conversion includes converting image data to a color space by identifying color regions in the image data. One color conversion system herein includes a color region identifier operable to select color values in the image data, determine numerical centers of the selected color values, and generate color regions, or color value “clusters”, based on the selected color values and the numerical centers. The color conversion system also includes an optimization module operable to refine the numerical center of each color region, determine a boundary for each color region based on the refined center, and remove a portion of the color cluster centers to optimize a number of the color regions for color conversion processing.
摘要翻译：这里的方法和系统提供图像数据到另一个颜色空间的颜色转换。这种颜色转换包括通过识别图像数据中的颜色区域来将图像数据转换为颜色空间。这里的一种颜色转换系统包括颜色区域标识符，其可操作以基于所选择的颜色值和数字来选择图像数据中的颜色值，确定所选颜色值的数值中心，并生成颜色区域或颜色值“聚类” 中心。颜色转换系统还包括优化模块，其可操作以细化每个颜色区域的数字中心，基于精炼的中心确定每个颜色区域的边界，并移除一部分颜色聚类中心以优化多个颜色区域用于颜色转换处理。

59. 发明申请

US20160098844A1 SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR SEARCHING AND SORTING IMAGES BY AESTHETIC QUALITY 有权
标题翻译：通过美学质量搜索和分类图像的系统，方法和计算机程序产品
公开(公告)号：US20160098844A1
公开(公告)日：2016-04-07
申请号：US14726172
申请日：2015-05-29
申请人： EyeEm Mobile GmbH
发明人： Appu SHAJI , Ramzi RIZK
IPC分类号： G06T9/00 , G06N3/08 , G06T7/40 , G06F17/30 , G06K9/62 , G06T7/00
CPC分类号： G06T9/002 , G06F17/30256 , G06K9/00677 , G06K9/6267 , G06K9/6273 , G06K2209/27 , G06N3/0445 , G06N3/0454 , G06T9/00
摘要： A system, method, and computer program product for assigning an aesthetic score to an image. A method of the present invention includes receiving an image. The method further includes executing a neural network on the image to generate learned features. The method further includes applying a machine-learned model to assign an aesthetic score to the image, where a more aesthetically-pleasing image is given a higher aesthetic score and a less aesthetically-pleasing image is given a lower aesthetic score. The learned features are inputs to the machine-learned model.
摘要翻译：一种用于将美学分数分配给图像的系统，方法和计算机程序产品。本发明的方法包括接收图像。该方法还包括在图像上执行神经网络以产生学习特征。该方法还包括应用机器学习模型来为图像分配美学分数，其中给予更美观的图像具有更高的审美分数，并且较少的美学图像被给予较低的审美分数。学习的功能是机器学习模型的输入。

60. 发明申请

US20150278641A1 INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS 审中-公开
标题翻译：使用SPIKING神经网络的图像的不确定对象表示
公开(公告)号：US20150278641A1
公开(公告)日：2015-10-01
申请号：US14228065
申请日：2014-03-27
申请人： QUALCOMM Incorporated
发明人： Pulkit AGRAWAL , Somdeb MAJUMDAR
IPC分类号： G06K9/66 , G06K9/68 , G06K9/46
CPC分类号： G06K9/4623 , G06K9/4647 , G06K9/6273 , G06N3/049 , G06N3/10
摘要： A method for invariantly representing an object using a spiking neural network includes representing the object by a spike sequence. The method also includes determining a reference feature of the object representation. The method further includes transforming the object representation to a canonical form based on the reference feature.
摘要翻译：使用尖峰神经网络不变地表示对象的方法包括通过尖峰序列表示对象。该方法还包括确定对象表示的参考特征。该方法还包括基于参考特征将对象表示转换为规范形式。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式