公开(公告)号：WO2016114960A1

公开(公告)日：2016-07-21

申请号：PCT/US2016/012371

申请日：2016-01-06

Applicant: EBAY INC.

Inventor： HARA, Kota ,  JAGADEESH, Vignesh ,  PIRAMUTHU, Robinson

IPC: G06K9/62

CPC classification number: G06Q30/0271 ,  G06K9/00369 ,  G06K9/6269 ,  G06K9/6277 ,  G06K9/72 ,  G06Q30/0258 ,  G06T11/60

Abstract: For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the persons body, such as the waist, head, hands, and feet of the person. A convolutional neural network receives the portions of the input image defined by the bounding boxes and generates a feature vector for each image portion. The feature vectors are input to one or more support vector machine classifiers, which generate an output representing a probability of a match with an item. The distance between the bounding box and a joint associated with the item is used to modify the probability. The modified probabilities for the support vector machine are then compared with a threshold and each other to identify the item.

Abstract translation: 对于人的输入图像，以边界框的形式生成一组对象提议。 姿势检测器识别对应于人体上的位置（例如人的腰部，头部，手和脚）的图像中的坐标。 卷积神经网络接收由边界框定义的输入图像的部分，并为每个图像部分生成特征向量。 特征向量被输入到一个或多个支持向量机分类器，其产生表示与项目匹配的概率的输出。 边界框与与项目关联的关节之间的距离用于修改概率。 然后将支持向量机的修改后的概率与阈值进行比较，以确定项目。