公开(公告)号：US20160300121A1

公开(公告)日：2016-10-13

申请号：US15188729

申请日：2016-06-21

申请人： SUPERFISH LTD.

发明人： Michael CHERTOK ,  Alexander LORBERT ,  Adi PINHAS

IPC分类号： G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/46 ,  G06K7/14

CPC分类号： G06K9/627 ,  G06K7/1482 ,  G06K9/469 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/084 ,  G06N7/046 ,  G06T2207/20084

摘要： A method for representing an input image, the method including the steps of applying a trained neural network (NN) on the input image, selecting a plurality of feature maps, determining a location of each of the feature maps in an image space of the input image, defining a plurality of interest points of the input image, representing the input image as a graph according to the interest points and geometric relations between the interest points, and employing the graph for performing a visual task, the graph including a plurality of vertices and edges, and maintaining the data respective of the geometric relations, the feature maps being selected of an output of at least one selected layer of the trained NN according to values attributed to the feature maps by the trained NN, the interest points of the input image being defined based on the locations corresponding to the feature maps.

摘要翻译： 一种用于表示输入图像的方法，所述方法包括以下步骤：在所述输入图像上应用经过训练的神经网络（NN），选择多个特征图，确定所述输入的图像空间中的每个特征图的位置 图像，定义输入图像的多个兴趣点，根据兴趣点和兴趣点之间的几何关系将输入图像表示为图形，并且使用用于执行视觉任务的图，该图包括多个顶点 和边缘，并且保持数据相应的几何关系，特征图被选择为训练的NN的至少一个所选层的输出，根据经训练的NN归因于特征图的值，输入的兴趣点 基于与特征图对应的位置来定义图像。

公开(公告)号：US20150278642A1

公开(公告)日：2015-10-01

申请号：US14676404

申请日：2015-04-01

申请人： SUPERFISH LTD.

发明人： Michael CHERTOK ,  Alexander LORBERT ,  Adi PINHAS

IPC分类号： G06K9/66

CPC分类号： G06K9/627 ,  G06K7/1482 ,  G06K9/469 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/084 ,  G06N7/046 ,  G06T2207/20084

摘要： A method for representing an input image includes the steps of applying a trained neural network on the input image, selecting a plurality of feature maps, determining a location of each of the plurality of feature maps in an image space of the input image, defining a plurality of interest points of the input image, and employing the plurality of interest points for representing the input image for performing a visual task. The plurality of feature maps are selected of an output of at least one selected layer of the trained neural network according to values attributed to the plurality of feature maps by the trained neural network. The plurality of interest points of the input image are defined based on the locations corresponding to the plurality of feature maps.

摘要翻译： 用于表示输入图像的方法包括以下步骤：在输入图像上应用经过训练的神经网络，选择多个特征图，确定输入图像的图像空间中的多个特征图中的每一个的位置， 输入图像的多个兴趣点，并且使用多个兴趣点来表示用于执行视觉任务的输入图像。 根据被训练的神经网络归因于多个特征图的值，选择多个特征图，该训练神经网络的至少一个选定层的输出。 基于对应于多个特征图的位置来定义输入图像的多个兴趣点。

公开(公告)号：US20160196672A1

公开(公告)日：2016-07-07

申请号：US14987479

申请日：2016-01-04

申请人： SUPERFISH LTD.

发明人： Michael CHERTOK ,  Alexander LORBERT

IPC分类号： G06T11/20 ,  G06T7/00 ,  G06K9/66

CPC分类号： G06T11/206 ,  G06K9/4628 ,  G06K9/469 ,  G06N3/0454

摘要： A method for producing a graph representation of an input image, the method including the procedures of applying convolutional layers of a trained convolutional neural network on the input image, defining a receptive field of a last convolutional layer of the trained convolutional neural network as a vertex of the graph representation, defining a vector of a three dimensional output matrix of the last convolutional layer that is mapped to the receptive field as a descriptor for the vertex and determining an edge between a pair of vertices of the graph representation by applying an operator on a pair of descriptors respective of the pair of vertices.

摘要翻译： 一种用于产生输入图像的图形表示的方法，该方法包括在训练的卷积神经网络上对输入图像应用卷积层的过程，将经训练的卷积神经网络的最后卷积层的接收场定义为顶点 定义图形表示的最后卷积层的三维输出矩阵的向量，其被映射到接收场作为顶点的描述符，并且通过将算子应用于图表表示的一对顶点之间的边缘 一对对应的一对顶点的描述符。

公开(公告)号：US20160196479A1

公开(公告)日：2016-07-07

申请号：US14987520

申请日：2016-01-04

申请人： SUPERFISH LTD.

发明人： Michael CHERTOK ,  Alexander LORBERT

IPC分类号： G06K9/66 ,  G06K9/52 ,  G06K9/62

CPC分类号： G06K9/4628 ,  G06K9/621 ,  G06K9/6272

摘要： A method for determining image similarity as a function of weighted descriptor similarities, including the procedures of feeding a query image to a network including a plurality of layers and defining an output of each of the layers as a descriptor of the query image, feeding a reference image to the network and defining an output of each of the layers as a descriptor of the reference image, determining a descriptor similarity score for respective descriptors that were produced by the same layer of the network fed the query image and the reference image, assigning a respective weight to each descriptor similarity score and defining an image similarity between the query image and the reference image as a function of the weighted descriptor similarity scores.

摘要翻译： 一种用于确定作为加权描述符相似性的函数的图像相似度的方法，包括将查询图像馈送到包括多个层的网络并将每个层的输出定义为查询图像的描述符的过程，馈送参考 映射到网络并且将每个层的输出定义为参考图像的描述符，确定由馈送查询图像和参考图像的网络的相同层产生的各个描述符的描述符相似性得分， 相应于每个描述符相似性分数的权重，并且根据加权描述符相似性得分来定义查询图像和参考图像之间的图像相似度。