-
1.发明申请OBJECT CLASSIFICATION WITH CONSTRAINED MULTIPLE INSTANCE SUPPORT VECTOR MACHINE 有权具有约束多个实例支持向量机的对象分类公开(公告)号：US20150242708A1
公开(公告)日：2015-08-27
申请号：US14186337
申请日：2014-02-21
Applicant: Xerox Corporation
Inventor： Kun Duan , Luca Marchesotti
CPC classification number: G06K9/6269 , G06K9/4642 , G06K2209/23
Abstract: This disclosure provides method and systems of classifying a digital image of an object. Specifically, according to one exemplary embodiment, an object classifier is trained using a constrained MI-SVM (multiple instance-support vector machine) approach whereby training images of objects are sampled to generate a collection of image regions associated with an object type and viewpoint, and the classifier is trained to determine an appropriate mid-level representation of the training image which is discriminative.
Abstract translation: 本公开提供了对对象的数字图像进行分类的方法和系统。 具体地，根据一个示例性实施例，使用受约束的MI-SVM（多实例支持向量机）方法训练对象分类器，由此对对象的训练图像进行采样以生成与对象类型和视点相关联的图像区域的集合， 并且分类器被训练以确定鉴别性的训练图像的适当中级表示。
-
2.发明授权公开(公告)号：US09443169B2
公开(公告)日：2016-09-13
申请号：US14186337
申请日：2014-02-21
Applicant: Xerox Corporation
Inventor： Kun Duan , Luca Marchesotti
CPC classification number: G06K9/6269 , G06K9/4642 , G06K2209/23
Abstract: This disclosure provides method and systems of classifying a digital image of an object. Specifically, according to one exemplary embodiment, an object classifier is trained using a constrained MI-SVM (multiple instance-support vector machine) approach whereby training images of objects are sampled to generate a collection of image regions associated with an object type and viewpoint, and the classifier is trained to determine an appropriate mid-level representation of the training image which is discriminative.
Abstract translation: 本公开提供了对对象的数字图像进行分类的方法和系统。 具体地，根据一个示例性实施例，使用受约束的MI-SVM（多实例支持向量机）方法训练对象分类器，由此对对象的训练图像进行采样以生成与对象类型和视点相关联的图像区域的集合， 并且分类器被训练以确定鉴别性的训练图像的适当中级表示。
-
Search Results
2
records
(took 0.009 seconds)
