-
公开(公告)号：US20160180151A1
公开(公告)日：2016-06-23
申请号：US14972670
申请日：2015-12-17
Applicant: Google Inc.
Inventor： James William Philbin , Gerhard Florian Schroff , Dmitry Kalenichenko
CPC classification number: G06K9/00288 , G06K9/4619 , G06K9/6218 , G06K9/6256 , G06K9/6267 , G06K9/66 , G06N3/0454 , G06N3/08 , G06N3/084 , G06T2207/20081 , G06T2207/20084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating numeric embeddings of images. One of the methods includes obtaining training images; generating a plurality of triplets of training images; and training a neural network on each of the triplets to determine trained values of a plurality of parameters of the neural network, wherein training the neural network comprises, for each of the triplets: processing the anchor image in the triplet using the neural network to generate a numeric embedding of the anchor image; processing the positive image in the triplet using the neural network to generate a numeric embedding of the positive image; processing the negative image in the triplet using the neural network to generate a numeric embedding of the negative image; computing a triplet loss; and adjusting the current values of the parameters of the neural network using the triplet loss.
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，用于生成图像的数字嵌入。 其中一种方法包括获取训练图像; 产生训练图像的多个三元组; 并训练每个三元组上的神经网络以确定神经网络的多个参数的训练值，其中对于每个三元组训练神经网络包括：使用神经网络来处理三元组中的锚图像以产生 锚图像的数字嵌入; 使用神经网络处理三重态中的正像，以生成正像的数字嵌入; 使用神经网络处理三联体中的负图像以生成负图像的数字嵌入; 计算三元损失; 并使用三元组损失调整神经网络的参数的当前值。
-
12.发明申请公开(公告)号：US20180137406A1
公开(公告)日：2018-05-17
申请号：US15707064
申请日：2017-09-18
Applicant: Google Inc.
Inventor： Andrew Gerald Howard , Bo Chen , Dmitry Kalenichenko , Tobias Christoph Weyand , Menglong Zhu , Marco Andreetto , Weijun Wang
CPC classification number: G06N3/04 , G06N3/0454 , G06N3/082 , G06N3/084 , G06T7/32 , G06T2207/20081 , G06T2207/20084
Abstract: The present disclosure provides systems and methods to reduce computational costs associated with convolutional neural networks. In addition, the present disclosure provides a class of efficient models termed “MobileNets” for mobile and embedded vision applications. MobileNets are based on a straight-forward architecture that uses depthwise separable convolutions to build light weight deep neural networks. The present disclosure further provides two global hyper-parameters that efficiently trade-off between latency and accuracy. These hyper-parameters allow the entity building the model to select the appropriately sized model for the particular application based on the constraints of the problem. MobileNets and associated computational cost reduction techniques are effective across a wide range of applications and use cases.
-
公开(公告)号：US09619803B2
公开(公告)日：2017-04-11
申请号：US14701517
申请日：2015-04-30
Applicant: GOOGLE INC.
CPC classification number: G06Q20/202 , G06K9/00255 , G06K9/00261 , G06K9/00288 , G06K9/00744 , G06Q20/206 , G06Q20/3224 , G06Q20/40145 , G06T7/74 , G06T2207/10016 , G06T2207/30201 , G06T2207/30232
Abstract: A merchant and a user register with a payment processing system, which establishes a facial template based on a user image. The user signs into a payment application via a user computing device, which receives an identifier from a merchant beacon device to transmit to the payment processing system. The payment processing system transmits facial templates to the merchant camera device for other users who are also signed in to the payment application in range of the merchant beacon device. The merchant camera device compares a captured facial image against the received facial templates to identify the user. A merchant POS device operator selects an account of the user. The merchant POS device transmits transaction details to the payment processing system, which processes the transaction with an issuer system. The payment processing system receives an approval of the transaction authorization request and transmits a receipt to the merchant POS device.
-
-
Search Results
13
records
(took 0.022 seconds)
