-
公开(公告)号：US20130188842A1
公开(公告)日：2013-07-25
申请号：US13792840
申请日：2013-03-11
发明人： Rudolf HAUKE
IPC分类号： G06K9/00
CPC分类号： G06F17/30247 , A61B5/117 , A61B5/1171 , A61B5/1176 , A61B5/1178 , G06K9/00288 , G06K9/00718 , G06Q10/10
摘要： A method for finding and digitally evaluating illegal image material is provided, wherein a data memory is searched for image material. Image material that is found is classified as potentially illegal image material or as legal image material by means of a classification method on the basis of an image content that is presented. The image material graded as potentially illegal has the age of the persons shown determined, and potentially illegal image material which shows at least one person whose ascertained age is below a prescribed age is graded as illegal image material. Biometric features of the persons shown in the illegal image material are detected and are compared with at least one database which contains biometric features. In the illegal image material, at least one further feature which it contains is detected and is compared with at least one appropriate database.
摘要翻译： 提供了一种用于查找和数字评估非法图像材料的方法，其中搜索数据存储器以获取图像材料。 基于所呈现的图像内容，通过分类方法将找到的图像材料分类为潜在的非法图像材料或合法图像材料。 分级为潜在非法的图像材料具有被确定的人的年龄，并且显示至少一个确定年龄在规定年龄以下的人的潜在非法图像材料被分级为非法图像材料。 检测非法图像材料中显示的人的生物特征，并将其与包含生物特征的至少一个数据库进行比较。 在非法图像材料中，检测到其包含的至少一个另外的特征，并将其与至少一个适当的数据库进行比较。
-
公开(公告)号：US09065787B2
公开(公告)日：2015-06-23
申请号：US13870510
申请日：2013-04-25
发明人： Rudolf Hauke , Roger Kueffer , Markus Holzer
IPC分类号： G06F15/16 , G06F15/177 , G06F15/173 , H04L12/58 , G06Q10/10
摘要： A method for supervising a chat connection between at least two terminals is provided. The method includes verification of first conditions, including a camera at each terminal is operated, video streams of each camera are live streams, and/or each video stream contains images of a live person. The connection is allowed if all of the first conditions are met and if one second condition is met. A second condition can include one first subset of the persons is identified as belonging to one defined restricted group and an identity of a second subset of the persons is determined at least on the basis of facial and/or body features and the identified second person is classified as an allowed exception. The method also includes a pre-defined reaction if any of the first conditions and/or all of the second conditions are not met.
摘要翻译： 提供了一种用于监视至少两个终端之间的聊天连接的方法。 该方法包括第一条件的验证，包括每个终端被操作的相机，每个相机的视频流是直播流，和/或每个视频流包含活人的图像。 如果满足所有第一个条件并满足第二个条件，则允许连接。 第二条件可以包括人的第一子集被识别为属于一个限定的一组，并且至少基于面部和/或身体特征确定人的第二子集的身份，并且所识别的第二个人是 分类为允许异常。 如果不满足第一条件和/或所有第二条件中的任何一个，该方法还包括预定义的反应。
-
公开(公告)号：US20130325981A1
公开(公告)日：2013-12-05
申请号：US13870510
申请日：2013-04-25
发明人： Rudolf HAUKE , Roger KUEFFER , Markus HOLZER
IPC分类号： H04L12/58
摘要： A method for supervising a chat connection between at least two terminals is provided. The method includes verification of first conditions, including a camera at each terminal is operated, video streams of each camera are live streams, and/or each video stream contains images of a live person. The connection is allowed if all of the first conditions are met and if one second condition is met. A second condition can include one first subset of the persons is identified as belonging to one defined restricted group and an identity of a second subset of the persons is determined at least on the basis of facial and/or body features and the identified second person is classified as an allowed exception. The method also includes a pre-defined reaction if any of the first conditions and/or all of the second conditions are not met.
摘要翻译： 提供了一种用于监视至少两个终端之间的聊天连接的方法。 该方法包括第一条件的验证，包括每个终端被操作的相机，每个相机的视频流是直播流，和/或每个视频流包含活人的图像。 如果满足所有第一个条件并满足第二个条件，则允许连接。 第二条件可以包括人的第一子集被识别为属于一个限定的一组，并且至少基于面部和/或身体特征确定人的第二子集的身份，并且所识别的第二个人是 分类为允许异常。 如果不满足第一条件和/或所有第二条件中的任何一个，该方法还包括预定义的反应。
-
公开(公告)号：US09251403B2
公开(公告)日：2016-02-02
申请号：US13792840
申请日：2013-03-11
发明人： Rudolf Hauke
CPC分类号： G06F17/30247 , A61B5/117 , A61B5/1171 , A61B5/1176 , A61B5/1178 , G06K9/00288 , G06K9/00718 , G06Q10/10
摘要： A method for finding and digitally evaluating illegal image material is provided, wherein a data memory is searched for image material. Image material that is found is classified as potentially illegal image material or as legal image material by means of a classification method on the basis of an image content that is presented. The image material graded as potentially illegal has the age of the persons shown determined, and potentially illegal image material which shows at least one person whose ascertained age is below a prescribed age is graded as illegal image material. Biometric features of the persons shown in the illegal image material are detected and are compared with at least one database which contains biometric features. In the illegal image material, at least one further feature which it contains is detected and is compared with at least one appropriate database.
摘要翻译： 提供了一种用于查找和数字评估非法图像材料的方法，其中搜索数据存储器以获取图像材料。 基于所呈现的图像内容，通过分类方法将找到的图像材料分类为潜在的非法图像材料或合法图像材料。 分级为潜在非法的图像材料具有被确定的人的年龄，并且显示至少一个确定年龄在规定年龄以下的人的潜在非法图像材料被分级为非法图像材料。 检测非法图像材料中显示的人的生物特征，并将其与包含生物特征的至少一个数据库进行比较。 在非法图像材料中，检测到其包含的至少一个另外的特征，并将其与至少一个适当的数据库进行比较。
-
公开(公告)号：US20150110387A1
公开(公告)日：2015-04-23
申请号：US14396278
申请日：2013-04-18
发明人： Rainer Lienhart , Christian Ries
IPC分类号： G06K9/62
CPC分类号： G06K9/6228 , G06F16/5838 , G06K9/6262
摘要： The invention relates to a method for the training of a classifier based on weakly labeled images and for the binary classification of an image. The training of the classifier comprises the steps of automatically and iteratively determining initial regions of interest for a training set and further on refining said regions of interest and adapting the classifier onto the refined regions of interest by a classifier refinement procedure. Further on, for a query image with unknown classification, an initial region of interest is determined and refined as to maximize the probability value derived at the output of said classifier. The query image is automatically assigned a negative classification label if said probability value is lower than or equal to a predetermined first threshold. The query image is automatically assigned a positive classification label if said probability value is greater than a predetermined second threshold.
摘要翻译： 本发明涉及一种基于弱标记图像和图像的二进制分类来训练分类器的方法。 分类器的训练包括以下步骤：自动和迭代地确定训练集合的初始感兴趣区域，并进一步完善所述感兴趣区域，并通过分类器细化过程使分类器适应于精细的感兴趣区域。 此外，对于具有未知分类的查询图像，确定和细化初始感兴趣区域，以最大化在所述分类器的输出处导出的概率值。 如果所述概率值低于或等于预定的第一阈值，则查询图像被自动分配负分类标签。 如果所述概率值大于预定的第二阈值，则查询图像被自动分配正分类标签。
-
-
-
-
搜索结果
5 条记录 (耗时 0.02 秒)
