公开(公告)号：US20130156301A1

公开(公告)日：2013-06-20

申请号：US13431993

申请日：2012-03-28

申请人： Chung-Chia Kang ,  Jian-Ren Chen ,  Chih-Wei Chen ,  Leii H. Chang

发明人： Chung-Chia Kang ,  Jian-Ren Chen ,  Chih-Wei Chen ,  Leii H. Chang

IPC分类号： G06K9/62

CPC分类号： G06K9/00268 ,  G06K9/6255

摘要： A method and a system for recognizing at least one testing image according to classes are provided, wherein each of the classes includes sample images. The method includes generating an average image of each class according to the sample images, generating a feature enhancement mask according to differences between the average images of the classes, enhancing the sample images of each class by using the feature enhancement mask to generate a plurality of enhanced sample images corresponding to each class, and training a classifier according to the enhanced sample images of each class. The method also includes enhancing the at least one testing image by using the feature enhancement mask to generate an enhanced testing image, classifying the enhanced testing image into one of the classes by using the classifier, and recognizing that the testing image belongs to the classified class. Thereby, this method can effectively recognize the testing image.

摘要翻译： 提供了一种用于根据类识别至少一个测试图像的方法和系统，其中每个类包括样本图像。 该方法包括根据样本图像生成每个类的平均图像，根据类的平均图像之间的差异生成特征增强掩模，通过使用特征增强掩模来增强每个类的样本图像，以生成多个 对应于每个类的增强的样本图像，并且根据每个类的增强的样本图像训练分类器。 该方法还包括通过使用特征增强掩模来增强至少一个测试图像以生成增强的测试图像，通过使用分类器将增强的测试图像分类为类之一，并且识别测试图像属于分类的类 。 因此，该方法可以有效地识别测试图像。

公开(公告)号：US08244002B2

公开(公告)日：2012-08-14

申请号：US12563329

申请日：2009-09-21

申请人： Jian-Ren Chen ,  Leii H. Chang ,  Yi-Fei Luo

发明人： Jian-Ren Chen ,  Leii H. Chang ,  Yi-Fei Luo

IPC分类号： G06K9/00 ,  G06F21/00

CPC分类号： G06K9/00979 ,  G06K9/00288

摘要： A system and a method for performing rapid facial recognition are provided. The rapid facial recognition system includes an image capture device, a broadcasting feature computing unit and several response recognition computing units scattered on the network. Each of the broadcasting feature computing unit and the response recognition computing units includes a feature recognition module, wherein the broadcasting feature computing unit further includes a feature extraction module and an identification module. The image capture device captures a facial image, and the feature extraction module extracts features of the facial image to generate a set of feature data that is broadcasted to the response recognition computing units. The feature recognition modules, in accordance with the set of the feature data and their classes allocated, perform distributed facial recognition for generating recognition results as a response. The identification module identifies the recognition results to accomplish the recognition of an individual's identity.

摘要翻译： 提供一种执行快速面部识别的系统和方法。 快速面部识别系统包括分散在网络上的图像捕获装置，广播特征计算单元和若干响应识别计算单元。 广播特征计算单元和响应识别计算单元中的每一个包括特征识别模块，其中广播特征计算单元还包括特征提取模块和识别模块。 图像捕获装置捕获面部图像，并且特征提取模块提取面部图像的特征以生成广播到响应识别计算单元的一组特征数据。 特征识别模块根据特征数据集合及其分配的类别，执行分布式面部识别，以产生识别结果作为响应。 识别模块识别识别结果以完成个体身份的识别。

公开(公告)号：US20090160942A1

公开(公告)日：2009-06-25

申请号：US12060859

申请日：2008-04-01

申请人： Vincent Kuo ,  Jian-Ren Chen ,  Leii H. Chang ,  Chii-Yah Yuan

发明人： Vincent Kuo ,  Jian-Ren Chen ,  Leii H. Chang ,  Chii-Yah Yuan

IPC分类号： H04N5/225

CPC分类号： G06K17/00 ,  G01S5/0018 ,  G01S5/0294 ,  G06K7/10079 ,  G06K2017/0045

摘要： Disclosed is a tagging and path reconstruction method utilizing unique identification characteristics and the system thereof. The tagging and path reconstruction system comprises a plurality of readers for reading identification information having unique IDs, a plurality of cameras for taking object's image data, and a server. The server includes an identifying and tagging module, an interlaced fusion and identification module, and a path reconstruction module. The identifying and tagging module identifies and tags the object image data with unique IDs. The interlaced fusion and identification module filters, checks and updates the tagged object image data. The path reconstruction module recovers the tagged object image data, lets them regress to their original identity data, and reconstructs the motion path of each object.

摘要翻译： 公开了利用独特识别特征的标签和路径重建方法及其系统。 标签和路径重建系统包括用于读取具有唯一ID的识别信息的多个读取器，用于拍摄对象的图像数据的多个摄像机和服务器。 服务器包括识别和标记模块，隔行融合和识别模块以及路径重建模块。 识别和标记模块使用唯一ID识别和标记对象图像数据。 隔行融合和识别模块过滤，检查和更新标记的对象图像数据。 路径重建模块恢复标记的对象图像数据，让它们回归到其原始身份数据，并重建每个对象的运动路径。

公开(公告)号：US08818050B2

公开(公告)日：2014-08-26

申请号：US13431993

申请日：2012-03-28

申请人： Chung-Chia Kang ,  Jian-Ren Chen ,  Chih-Wei Chen ,  Leii H. Chang

发明人： Chung-Chia Kang ,  Jian-Ren Chen ,  Chih-Wei Chen ,  Leii H. Chang

IPC分类号： G06K9/00

CPC分类号： G06K9/00268 ,  G06K9/6255

摘要： A method and a system for recognizing at least one testing image according to classes are provided, wherein each of the classes includes sample images. The method includes generating an average image of each class according to the sample images, generating a feature enhancement mask according to differences between the average images of the classes, enhancing the sample images of each class by using the feature enhancement mask to generate a plurality of enhanced sample images corresponding to each class, and training a classifier according to the enhanced sample images of each class. The method also includes enhancing the at least one testing image by using the feature enhancement mask to generate an enhanced testing image, classifying the enhanced testing image into one of the classes by using the classifier, and recognizing that the testing image belongs to the classified class. Thereby, this method can effectively recognize the testing image.

摘要翻译： 提供了一种用于根据类识别至少一个测试图像的方法和系统，其中每个类包括样本图像。 该方法包括根据样本图像生成每个类的平均图像，根据类的平均图像之间的差异生成特征增强掩模，通过使用特征增强掩模来增强每个类的样本图像，以生成多个 对应于每个类的增强的样本图像，并且根据每个类的增强的样本图像训练分类器。 该方法还包括通过使用特征增强掩模来增强至少一个测试图像以生成增强的测试图像，通过使用分类器将增强的测试图像分类为类之一，并且识别测试图像属于分类的类 。 因此，该方法可以有效地识别测试图像。

公开(公告)号：US20130307979A1

公开(公告)日：2013-11-21

申请号：US13585795

申请日：2012-08-14

申请人： Yi-Yuan Chen ,  Jian-Ren Chen ,  Leii H. Chang ,  Shang-Chih Hung

发明人： Yi-Yuan Chen ,  Jian-Ren Chen ,  Leii H. Chang ,  Shang-Chih Hung

IPC分类号： H04N7/18

CPC分类号： G08G1/0175 ,  B60R25/305 ,  G06K9/00785

摘要： A method and a system for integrating multiple camera images to track a vehicle are provided. In the method, a security request of a vehicle to be tracked is received from a user, in which the security request comprises registration information and position information of the vehicle. Next, images captured by multiple cameras in a specific range around a location of the position information are retrieved. The retrieved images are analyzed according to the registration information, so as to recognize the images comprising the vehicle. Finally, a message is issued when the images comprising the vehicle are recognized.

摘要翻译： 提供了一种用于集成多个摄像机图像以跟踪车辆的方法和系统。 在该方法中，从用户接收到要跟踪的车辆的安全请求，其中安全请求包括车辆的登记信息和位置信息。 接下来，检索在位置信息的位置周围的特定范围内的多个摄像机拍摄的图像。 根据注册信息分析检索到的图像，以便识别包括车辆的图像。 最后，当识别到包括车辆的图像时，发出消息。

公开(公告)号：US20110140892A1

公开(公告)日：2011-06-16

申请号：US12839425

申请日：2010-07-20

申请人： Jian-Ren Chen ,  Leii H. Chang ,  Ho-Hsin Lee ,  Yi-Fei Luo ,  Chii-Yah Yuan

发明人： Jian-Ren Chen ,  Leii H. Chang ,  Ho-Hsin Lee ,  Yi-Fei Luo ,  Chii-Yah Yuan

IPC分类号： G08B13/22 ,  H04N7/18 ,  G06K9/62

CPC分类号： H04N7/181 ,  G08B13/19602 ,  G08B13/19645

摘要： A system and a method for detecting multi-level intrusion events are provided. The system includes an area recognition module and an area classification module. The area recognition module performs a geometric topology operation to recognize a plurality of areas in a ground plane that has a plurality of boundaries and a plurality of gates, and each of the areas is constituted of at least one of the boundaries and at least one of the gates. The area classification module defines a plurality of security levels and classifies each of the areas recognized by the area recognition module as one of the security levels. Accordingly, the system is able to automatically recognize the areas in the ground plane, set the security levels of the areas, and generate the corresponding detection areas and tripwires according to the security levels of the areas.

摘要翻译： 提供了一种用于检测多级入侵事件的系统和方法。 该系统包括区域识别模块和区域分类模块。 区域识别模块执行几何拓扑操作以识别具有多个边界和多个门的接地平面中的多个区域，并且每个区域由以下各项中的至少一个构成：边界和 大门。 区域分类模块定义多个安全级别，并将区域识别模块识别的区域中的每一个区分为安全级别之一。 因此，系统能够自动识别地面中的区域，设置区域的安全级别，并根据区域的安全级别生成相应的检测区域和Tripwire。

公开(公告)号：US20100239130A1

公开(公告)日：2010-09-23

申请号：US12563329

申请日：2009-09-21

申请人： Jian-Ren Chen ,  Leii H. Chang ,  Yi-Fei Luo

发明人： Jian-Ren Chen ,  Leii H. Chang ,  Yi-Fei Luo

IPC分类号： G06K9/00

CPC分类号： G06K9/00979 ,  G06K9/00288

摘要： A system and a method for performing rapid facial recognition are provided. The rapid facial recognition system includes an image capture device, a broadcasting feature computing unit and several response recognition computing units scattered on the network. Each of the broadcasting feature computing unit and the response recognition computing units includes a feature recognition module, wherein the broadcasting feature computing unit further includes a feature extraction module and an identification module. The image capture device captures a facial image, and the feature extraction module extracts features of the facial image to generate a set of feature data that is broadcasted to the response recognition computing units. The feature recognition modules, in accordance with the set of the feature data and their classes allocated, perform distributed facial recognition for generating recognition results as a response. The identification module identifies the recognition results to accomplish the recognition of an individual's identity.

摘要翻译： 提供一种执行快速面部识别的系统和方法。 快速面部识别系统包括分散在网络上的图像捕获装置，广播特征计算单元和若干响应识别计算单元。 广播特征计算单元和响应识别计算单元中的每一个包括特征识别模块，其中广播特征计算单元还包括特征提取模块和识别模块。 图像捕获装置捕获面部图像，并且特征提取模块提取面部图像的特征以生成广播到响应识别计算单元的一组特征数据。 特征识别模块根据特征数据集合及其分配的类别，执行分布式面部识别，以产生识别结果作为响应。 识别模块识别识别结果以完成个体身份的识别。

公开(公告)号：US20080129454A1

公开(公告)日：2008-06-05

申请号：US11727346

申请日：2007-03-26

申请人： Jian-Ren Chen ,  Yi-Fei Luo ,  Leii H. Chang ,  Cheng-I Kuo

发明人： Jian-Ren Chen ,  Yi-Fei Luo ,  Leii H. Chang ,  Cheng-I Kuo

IPC分类号： H04Q5/22

CPC分类号： G06K7/0008

摘要： A method and system for reading and identifying RFID tags of the invention is disclosed. The invention is capable of registering and storing information of a plurality of RFID tags attached to objects of the same group into a memory block of at least a specified RFID reader or RFID tag. The invention is also capable of enabling at least a specified RFID reader/tag in response to a first inquiry of an interrogator by transmitting each identification code of the plurality of RFID tags to the interrogator for acknowledgement. The method is capable of achieving the objective of reducing the overall communication time as the reader does not have to inquire one by one to the RFID tags to save the number of times of communication between the inquiry of the reader and the response of the RFID tags. In addition, the reading rate of the RFID system can be improved effectively since at least one of the RFID tags can function as a spokesman for those RFID tags hidden deeply inside a pile of the objects of the group.

摘要翻译： 公开了一种读取和识别本发明的RFID标签的方法和系统。 本发明能够将附加到同一组的对象的多个RFID标签的信息注册和存储到至少指定的RFID读取器或RFID标签的存储器块中。 本发明还能够通过将多个RFID标签的每个识别码发送到询问器来确认，响应于询问器的第一询问，能够使至少一个特定的RFID读取器/标签。 该方法能够实现减少整体通信时间的目的，因为读取器不必一一询问RFID标签，以节省读取器的查询和RFID标签的响应之间的通信次数 。 此外，RFID系统的读取速度可以有效地提高，因为RFID标签中的至少一个可以充当隐藏在该组对象内的那些RFID标签的发言人。

公开(公告)号：US08552862B2

公开(公告)日：2013-10-08

申请号：US12839425

申请日：2010-07-20

申请人： Jian-Ren Chen ,  Leii H. Chang ,  Ho-Hsin Lee ,  Yi-Fei Luo ,  Chii-Yah Yuan

发明人： Jian-Ren Chen ,  Leii H. Chang ,  Ho-Hsin Lee ,  Yi-Fei Luo ,  Chii-Yah Yuan

IPC分类号： G08B13/00

CPC分类号： H04N7/181 ,  G08B13/19602 ,  G08B13/19645

摘要： A system and a method for detecting multi-level intrusion events are provided. The system includes an area recognition module and an area classification module. The area recognition module performs a geometric topology operation to recognize a plurality of areas in a ground plane that has a plurality of boundaries and a plurality of gates, and each of the areas is constituted of at least one of the boundaries and at least one of the gates. The area classification module defines a plurality of security levels and classifies each of the areas recognized by the area recognition module as one of the security levels. Accordingly, the system is able to automatically recognize the areas in the ground plane, set the security levels of the areas, and generate the corresponding detection areas and tripwires according to the security levels of the areas.

摘要翻译： 提供了一种用于检测多级入侵事件的系统和方法。 该系统包括区域识别模块和区域分类模块。 区域识别模块执行几何拓扑操作以识别具有多个边界和多个门的接地平面中的多个区域，并且每个区域由以下各项中的至少一个构成：边界和 大门。 区域分类模块定义多个安全级别，并将区域识别模块识别的区域中的每一个区分为安全级别之一。 因此，系统能够自动识别地面中的区域，设置区域的安全级别，并根据区域的安全级别生成相应的检测区域和Tripwire。

公开(公告)号：US07768402B2

公开(公告)日：2010-08-03

申请号：US11727346

申请日：2007-03-26

申请人： Jian-Ren Chen ,  Yi-Fei Luo ,  Leii H. Chang ,  Cheng-I Kuo

发明人： Jian-Ren Chen ,  Yi-Fei Luo ,  Leii H. Chang ,  Cheng-I Kuo

IPC分类号： G08B13/14

CPC分类号： G06K7/0008

摘要： A method and system for reading and identifying RFID tags of the invention is disclosed. The invention is capable of registering and storing information of a plurality of RFID tags attached to objects of the same group into a memory block of at least a specified RFID reader or RFID tag. The invention is also capable of enabling at least a specified RFID reader/tag in response to a first inquiry of an interrogator by transmitting each identification code of the plurality of RFID tags to the interrogator for acknowledgement. The method is capable of achieving the objective of reducing the overall communication time as the reader does not have to inquire one by one to the RFID tags to save the number of times of communication between the inquiry of the reader and the response of the RFID tags. In addition, the reading rate of the RFID system can be improved effectively since at least one of the RFID tags can function as a spokesman for those RFID tags hidden deeply inside a pile of the objects of the group.

摘要翻译： 公开了一种读取和识别本发明的RFID标签的方法和系统。 本发明能够将附加到同一组的对象的多个RFID标签的信息注册和存储到至少指定的RFID读取器或RFID标签的存储器块中。 本发明还能够通过将多个RFID标签的每个识别码发送到询问器来确认，响应于询问器的第一询问，能够使至少一个特定的RFID读取器/标签。 该方法能够实现减少总体通信时间的目的，因为读取器不必一一询问RFID标签，以节省读取器的查询和RFID标签的响应之间的通信次数 。 此外，RFID系统的读取速度可以有效地提高，因为RFID标签中的至少一个可以充当隐藏在该组对象内的那些RFID标签的发言人。