-
公开(公告)号：US09563825B2
公开(公告)日：2017-02-07
申请号：US14549350
申请日：2014-11-20
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Haoxiang Li , Zhe Lin , Jonathan W. Brandt
CPC classification number: G06K9/66 , G06K9/4628 , G06K9/6267 , G06K9/6272 , G06N3/04 , G06N3/0454
Abstract: A convolutional neural network is trained to analyze input data in various different manners. The convolutional neural network includes multiple layers, one of which is a convolution layer that performs a convolution, for each of one or more filters in the convolution layer, of the filter over the input data. The convolution includes generation of an inner product based on the filter and the input data. Both the filter of the convolution layer and the input data are binarized, allowing the inner product to be computed using particular operations that are typically faster than multiplication of floating point values. The possible results for the convolution layer can optionally be pre-computed and stored in a look-up table. Thus, during operation of the convolutional neural network, rather than performing the convolution on the input data, the pre-computed result can be obtained from the look-up table.
Abstract translation: 训练卷积神经网络以各种不同的方式分析输入数据。 卷积神经网络包括多个层，其中之一是卷积层，其对于卷积层中的一个或多个滤波器的每一个，通过输入数据执行滤波器的卷积。 卷积包括基于滤波器和输入数据生成内积。 卷积层的滤波器和输入数据都被二值化，允许使用通常快于浮点值乘法的特定运算来计算内积。 可以可选地预先计算卷积层的可能结果并将其存储在查找表中。 因此，在卷积神经网络的操作期间，不是对输入数据执行卷积，可以从查找表中获得预先计算的结果。
-
公开(公告)号：US09269017B2
公开(公告)日：2016-02-23
申请号：US14081577
申请日：2013-11-15
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jonathan W. Brandt , Xiaohui Shen , Haoxiang Li
CPC classification number: G06K9/4604 , G06K9/6282 , G06K9/6857
Abstract: Cascaded object detection techniques are described. In one or more implementations, cascaded coarse-to-dense object detection techniques are utilized to detect objects in images. In a first stage, coarse features are extracted from an image, and non-object regions are rejected. Then, in one or more subsequent stages, dense features are extracted from the remaining non-rejected regions of the image to detect one or more objects in the image.
Abstract translation: 描述了级联对象检测技术。 在一个或多个实现中，使用级联的粗到密集对象检测技术来检测图像中的对象。 在第一阶段，从图像中提取粗糙特征，并且拒绝非对象区域。 然后，在一个或多个后续阶段，从图像的剩余未拒绝区域中提取密集特征以检测图像中的一个或多个对象。
-
公开(公告)号：US20150139538A1
公开(公告)日：2015-05-21
申请号：US14081489
申请日：2013-11-15
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jonathan W. Brandt , Xiaohui Shen , Haoxiang Li
CPC classification number: G06K9/6269 , G06K9/00234 , G06K9/00288 , G06K9/6257
Abstract: In techniques for object detection with boosted exemplars, weak classifiers of a real-adaboost technique can be learned as exemplars that are collected from example images. The exemplars are examples of an object that is detectable in image patches of an image, such as faces that are detectable in images. The weak classifiers of the real-adaboost technique can be applied to the image patches of the image, and a confidence score is determined for each of the weak classifiers as applied to an image patch of the image. The confidence score of a weak classifier is an indication of whether the object is detected in the image patch of the image based on the weak classifier. All of the confidence scores of the weak classifiers can then be summed to generate an overall object detection score that indicates whether the image patch of the image includes the object.
Abstract translation: 在通过增强的样本进行物体检测的技术中，可以从实例图像中收集真实adaboost技术的弱分类器作为样本。 示例是在图像的图像块中可检测到的对象的示例，例如在图像中可检测的面。 真实adaboost技术的弱分类器可以应用于图像的图像斑块，并且对于每个弱分类器确定应用于图像的图像块的置信度分数。 弱分类器的置信度分数是基于弱分类器在图像的图像块中是否检测到对象的指示。 然后可以将弱分类器的所有置信分数相加以生成指示图像的图像块是否包括对象的整体对象检测分数。
-
公开(公告)号：US20160148079A1
公开(公告)日：2016-05-26
申请号：US14550800
申请日：2014-11-21
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Haoxiang Li , Zhe Lin , Jonathan W. Brandt
CPC classification number: G06K9/00288 , G06K9/4628 , G06K9/6257 , G06N3/0454
Abstract: Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image.
Abstract translation: 识别图像中的不同候选窗口，例如通过在图像上滑动不同尺寸的矩形或其他几何形状以识别图像（图像中的像素组）的部分。 候选窗口由一组卷积神经网络进行分析，这些网络级联，使得一个卷积神经网络层的输入基于另一个卷积神经网络层的输入。 每个卷积神经网络层丢弃或拒绝卷积神经网络层确定的一个或多个候选窗口不包括对象（例如，面部）。 识别为包括对象（例如脸部）的候选窗口由另一个卷积神经网络层分析。 由最后的卷积神经网络层识别的候选窗口是图像中的对象（例如，面部）的指示。
-
公开(公告)号：US20180336401A1
公开(公告)日：2018-11-22
申请号：US16049322
申请日：2018-07-30
Applicant: Adobe Systems Incorporated
Inventor： Jonathan Brandt , Zhe Lin , Xiaohui Shen , Haoxiang Li
CPC classification number: G06K9/00295 , G06K9/00369 , G06K9/00677 , G06K9/6218 , G06K9/66
Abstract: Methods and systems for recognizing people in images with increased accuracy are disclosed. In particular, the methods and systems divide images into a plurality of clusters based on common characteristics of the images. The methods and systems also determine an image cluster to which an image with an unknown person instance most corresponds. One or more embodiments determine a probability that the unknown person instance is each known person instance in the image cluster using a trained cluster classifier of the image cluster. Optionally, the methods and systems determine context weights for each combination of an unknown person instance and each known person instance using a conditional random field algorithm based on a plurality of context cues associated with the unknown person instance and the known person instances. The methods and systems calculate a contextual probability based on the cluster-based probabilities and context weights to identify the unknown person instance.
-
Patent Agency Ranking
公开(公告)号：US20160148078A1
公开(公告)日：2016-05-26
申请号：US14549350
申请日：2014-11-20
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Haoxiang Li , Zhe Lin , Jonathan W. Brandt
CPC classification number: G06K9/66 , G06K9/4628 , G06K9/6267 , G06K9/6272 , G06N3/04 , G06N3/0454
Abstract: A convolutional neural network is trained to analyze input data in various different manners. The convolutional neural network includes multiple layers, one of which is a convolution layer that performs a convolution, for each of one or more filters in the convolution layer, of the filter over the input data. The convolution includes generation of an inner product based on the filter and the input data. Both the filter of the convolution layer and the input data are binarized, allowing the inner product to be computed using particular operations that are typically faster than multiplication of floating point values. The possible results for the convolution layer can optionally be pre-computed and stored in a look-up table. Thus, during operation of the convolutional neural network, rather than performing the convolution on the input data, the pre-computed result can be obtained from the look-up table
Abstract translation: 训练卷积神经网络以各种不同的方式分析输入数据。 卷积神经网络包括多个层，其中之一是卷积层，其对于卷积层中的一个或多个滤波器的每一个，通过输入数据执行滤波器的卷积。 卷积包括基于滤波器和输入数据生成内积。 卷积层的滤波器和输入数据都被二值化，允许使用通常快于浮点值乘法的特定运算来计算内积。 可以可选地预先计算卷积层的可能结果并将其存储在查找表中。 因此，在卷积神经网络的操作期间，不是对输入数据执行卷积，所以可以从查找表中获得预先计算的结果
-
公开(公告)号：US09208404B2
公开(公告)日：2015-12-08
申请号：US14081489
申请日：2013-11-15
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jonathan W. Brandt , Xiaohui Shen , Haoxiang Li
CPC classification number: G06K9/6269 , G06K9/00234 , G06K9/00288 , G06K9/6257
Abstract: In techniques for object detection with boosted exemplars, weak classifiers of a real-adaboost technique can be learned as exemplars that are collected from example images. The exemplars are examples of an object that is detectable in image patches of an image, such as faces that are detectable in images. The weak classifiers of the real-adaboost technique can be applied to the image patches of the image, and a confidence score is determined for each of the weak classifiers as applied to an image patch of the image. The confidence score of a weak classifier is an indication of whether the object is detected in the image patch of the image based on the weak classifier. All of the confidence scores of the weak classifiers can then be summed to generate an overall object detection score that indicates whether the image patch of the image includes the object.
Abstract translation: 在通过增强的样本进行物体检测的技术中，可以从实例图像中收集真实adaboost技术的弱分类器作为样本。 示例是在图像的图像块中可检测到的对象的示例，例如在图像中可检测的面。 真实adaboost技术的弱分类器可以应用于图像的图像斑块，并且对于每个弱分类器确定应用于图像的图像块的置信度分数。 弱分类器的置信度分数是基于弱分类器在图像的图像块中是否检测到对象的指示。 然后可以将弱分类器的所有置信分数相加以生成指示图像的图像块是否包括对象的整体对象检测分数。
-
公开(公告)号：US10068129B2
公开(公告)日：2018-09-04
申请号：US14945198
申请日：2015-11-18
Applicant: Adobe Systems Incorporated
Inventor： Jonathan Brandt , Zhe Lin , Xiaohui Shen , Haoxiang Li
Abstract: Methods and systems for recognizing people in images with increased accuracy are disclosed. In particular, the methods and systems divide images into a plurality of clusters based on common characteristics of the images. The methods and systems also determine an image cluster to which an image with an unknown person instance most corresponds. One or more embodiments determine a probability that the unknown person instance is each known person instance in the image cluster using a trained cluster classifier of the image cluster. Optionally, the methods and systems determine context weights for each combination of an unknown person instance and each known person instance using a conditional random field algorithm based on a plurality of context cues associated with the unknown person instance and the known person instances. The methods and systems calculate a contextual probability based on the cluster-based probabilities and context weights to identify the unknown person instance.
-
公开(公告)号：US20170140213A1
公开(公告)日：2017-05-18
申请号：US14945198
申请日：2015-11-18
Applicant: Adobe Systems Incorporated
Inventor： Jonathan Brandt , Zhe Lin , Xiaohui Shen , Haoxiang Li
CPC classification number: G06K9/00295 , G06K9/00369 , G06K9/00677 , G06K9/6218 , G06K9/66
Abstract: Methods and systems for recognizing people in images with increased accuracy are disclosed. In particular, the methods and systems divide images into a plurality of clusters based on common characteristics of the images. The methods and systems also determine an image cluster to which an image with an unknown person instance most corresponds. One or more embodiments determine a probability that the unknown person instance is each known person instance in the image cluster using a trained cluster classifier of the image cluster. Optionally, the methods and systems determine context weights for each combination of an unknown person instance and each known person instance using a conditional random field algorithm based on a plurality of context cues associated with the unknown person instance and the known person instances. The methods and systems calculate a contextual probability based on the cluster-based probabilities and context weights to identify the unknown person instance.
-
公开(公告)号：US20160307074A1
公开(公告)日：2016-10-20
申请号：US15196478
申请日：2016-06-29
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Haoxiang Li , Zhe Lin , Jonathan W. Brandt
CPC classification number: G06K9/00288 , G06K9/4628 , G06K9/6257 , G06N3/0454
Abstract: Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image.
Abstract translation: 识别图像中的不同候选窗口，例如通过在图像上滑动不同尺寸的矩形或其他几何形状以识别图像（图像中的像素组）的部分。 候选窗口由一组卷积神经网络进行分析，这些网络级联，使得一个卷积神经网络层的输入基于另一个卷积神经网络层的输入。 每个卷积神经网络层丢弃或拒绝卷积神经网络层确定的一个或多个候选窗口不包括对象（例如，面部）。 识别为包括对象（例如脸部）的候选窗口由另一个卷积神经网络层分析。 由最后的卷积神经网络层识别的候选窗口是图像中的对象（例如，面部）的指示。
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.015 seconds)
