IMAGE PROCESSING INCLUDING ADJOIN FEATURE BASED OBJECT DETECTION, AND/OR BILATERAL SYMMETRIC OBJECT SEGMENTATION
    1.
    发明申请
    IMAGE PROCESSING INCLUDING ADJOIN FEATURE BASED OBJECT DETECTION, AND/OR BILATERAL SYMMETRIC OBJECT SEGMENTATION 审中-公开
    包括基于特征的物体检测和/或双边对称对象分类的图像处理

    公开(公告)号:US20140369608A1

    公开(公告)日:2014-12-18

    申请号:US14124233

    申请日:2013-06-14

    IPC分类号: G06K9/46

    CPC分类号: G06K9/6211 G06K9/68

    摘要: Apparatuses, methods and storage medium associated with processing an image are disclosed herein. In embodiments, a method for processing one or more images may include generating a plurality of pairs of keypoint features for a pair of images. Each pair of keypoint features may include a keypoint feature from each image. Further, for each pair of keypoint features, corresponding adjoin features may be generated. Additionally, for each pair of keypoint features, whether the adjoin features are similar may be determined. Whether the pair of images have at least one similar object may also be determined, based at least in part on a result of the determination of similarity between the corresponding adjoin features. Other embodiments may be described and claimed.

    摘要翻译: 本文公开了与处理图像相关联的装置,方法和存储介质。 在实施例中,用于处理一个或多个图像的方法可以包括为一对图像生成多对关键点特征。 每对关键点特征可以包括来自每个图像的关键点特征。 此外,对于每对关键点特征,可以生成相应的邻接特征。 此外,对于每对关键点特征,可以确定邻接特征是否相似。 至少部分地基于相应邻接特征之间的相似性的确定结果,也可以确定该对图像是否具有至少一个相似对象。 可以描述和要求保护其他实施例。

    Method of facial landmark detection
    2.
    发明授权
    Method of facial landmark detection 有权
    面部地标检测方法

    公开(公告)号:US09471829B2

    公开(公告)日:2016-10-18

    申请号:US13997296

    申请日:2011-03-31

    IPC分类号: G06K9/00 G06K9/46 G06K9/62

    摘要: Detecting facial landmarks in a face detected in an image may be performed by first cropping a face rectangle region of the detected face in the image and generating an integral image based at least in part on the face rectangle region. Next, a cascade classifier may be executed for each facial landmark of the face rectangle region to produce one response image for each facial landmark based at least in part on the integral image. A plurality of Active Shape Model (ASM) initializations may be set up. ASM searching may be performed for each of the ASM initializations based at least in part on the response images, each ASM search resulting in a search result having a cost. Finally, a search result of the ASM searches having a lowest cost function may be selected, the selected search result indicating locations of the facial landmarks in the image.

    摘要翻译: 可以通过首先裁剪图像中检测到的面部的面部矩形区域并且至少部分地基于面部矩形区域来生成整体图像来检测在图像中检测到的面部中的面部界标。 接下来,可以对面部矩形区域的每个面部标记执行级联分类器,以至少部分地基于积分图像来为每个面部标记产生一个响应图像。 可以设置多个活动形状模型(ASM)初始化。 可以至少部分地基于响应图像来对每个ASM初始化执行ASM搜索,每个ASM搜索导致搜索结果具有成本。 最后,可以选择具有最低成本函数的ASM搜索的搜索结果,所选择的搜索结果指示图像中的面部地标的位置。

    Tracking and recognition of faces using selected region classification
    3.
    发明授权
    Tracking and recognition of faces using selected region classification 有权
    使用选择的区域分类来跟踪和识别面部

    公开(公告)号:US09489567B2

    公开(公告)日:2016-11-08

    申请号:US13996496

    申请日:2011-04-11

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00288 G06K9/00221

    摘要: Methods, apparatuses, and articles associated with facial tracking and recognition are disclosed. In embodiments, facial images may be detected in video or still images and tracked. After normalization of the facial images, feature data may be extracted from selected regions of the faces to compare to associated feature data in known faces. The selected regions may be determined using a boosting machine learning processes over a set of known images. After extraction, individual two-class comparisons may be performed between corresponding feature data from regions on the tested facial images and from the known facial image. The individual two-class classifications may then be combined to determine a similarity score for the tested face and the known face. If the similarity score exceeds a threshold, an identification of the known face may be output or otherwise used. Additionally, tracking with voting may be performed on faces detected in video. After a threshold of votes is reached, a given tracked face may be associated with a known face.

    摘要翻译: 公开了与面部跟踪和识别有关的方法,装置和文章。 在实施例中,可以在视频或静止图像中检测面部图像并进行跟踪。 在面部图像归一化之后,可以从面部的选定区域提取特征数据,以与已知面部中的相关特征数据进行比较。 可以使用一组已知图像上的升压机学习处理来确定所选择的区域。 提取后,可以在来自所测试的面部图像上的区域和来自已知面部图像的相应特征数据之间进行单独的两类比较。 然后可以组合个体两类分类以确定测试面部和已知面部的相似性得分。 如果相似性分数超过阈值,则可以输出或以其他方式使用已知面部的识别。 此外,可以对在视频中检测到的脸部进行投票跟踪。 在达成一个选票之后,一个给定的被追踪的面孔可能与一个已知的面孔相关联。

    TRACKING AND RECOGNITION OF FACES USING SELECTED REGION CLASSIFICATION
    4.
    发明申请
    TRACKING AND RECOGNITION OF FACES USING SELECTED REGION CLASSIFICATION 有权
    使用选定区域分类来跟踪和识别

    公开(公告)号:US20140241574A1

    公开(公告)日:2014-08-28

    申请号:US13996496

    申请日:2011-04-11

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00288 G06K9/00221

    摘要: Methods, apparatuses, and articles associated with facial tracking and recognition are disclosed. In embodiments, facial images may be detected in video or still images and tracked. After normalization of the facial images, feature data may be extracted from selected regions of the faces to compare to associated feature data in known faces. The selected regions may be determined using a boosting machine learning processes over a set of known images. After extraction, individual two-class comparisons may be performed between corresponding feature data from regions on the tested facial images and from the known facial image. The individual two-class classifications may then be combined to determine a similarity score for the tested face and the known face. If the similarity score exceeds a threshold, an identification of the known face may be output or otherwise used. Additionally, tracking with voting may be performed on faces detected in video. After a threshold of votes is reached, a given tracked face may be associated with a known face.

    摘要翻译: 公开了与面部跟踪和识别有关的方法,装置和文章。 在实施例中,可以在视频或静止图像中检测面部图像并进行跟踪。 在面部图像归一化之后,可以从面部的选定区域提取特征数据,以与已知面部中的相关特征数据进行比较。 可以使用一组已知图像上的升压机学习处理来确定所选择的区域。 提取后,可以在来自所测试的面部图像上的区域和来自已知面部图像的相应特征数据之间进行单独的两类比较。 然后可以组合个体两类分类以确定测试面部和已知面部的相似性得分。 如果相似性分数超过阈值,则可以输出或以其他方式使用已知面部的识别。 此外,可以对在视频中检测到的脸部进行投票跟踪。 在达成一个选票之后,一个给定的被追踪的面孔可能与一个已知的面孔相关联。

    METHOD OF FACIAL LANDMARK DETECTION
    6.
    发明申请
    METHOD OF FACIAL LANDMARK DETECTION 有权
    方法地名检测方法

    公开(公告)号:US20140050358A1

    公开(公告)日:2014-02-20

    申请号:US13997296

    申请日:2011-03-31

    IPC分类号: G06K9/00

    摘要: Detecting facial landmarks in a face detected in an image may be performed by first cropping a face rectangle region of the detected face in the image and generating an integral image based at least in part on the face rectangle region. Next, a cascade classifier may be executed for each facial landmark of the face rectangle region to produce one response image for each facial landmark based at least in part on the integral image. A plurality of Active Shape Model (ASM) initializations may be set up. ASM searching may be performed for each of the ASM initializations based at least in part on the response images, each ASM search resulting in a search result having a cost. Finally, a search result of the ASM searches having a lowest cost function may be selected, the selected search result indicating locations of the facial landmarks in the image.

    摘要翻译: 可以通过首先裁剪图像中检测到的面部的面部矩形区域并且至少部分地基于面部矩形区域来生成整体图像来检测在图像中检测到的面部中的面部界标。 接下来,可以对面部矩形区域的每个面部标记执行级联分类器,以至少部分地基于积分图像来为每个面部标记产生一个响应图像。 可以设置多个活动形状模型(ASM)初始化。 可以至少部分地基于响应图像来对每个ASM初始化执行ASM搜索,每个ASM搜索导致搜索结果具有成本。 最后,可以选择具有最低成本函数的ASM搜索的搜索结果,所选择的搜索结果指示图像中的面部地标的位置。

    FACE RECOGNITION CONTROL AND SOCIAL NETWORKING
    7.
    发明申请
    FACE RECOGNITION CONTROL AND SOCIAL NETWORKING 审中-公开
    面部识别控制和社会网络

    公开(公告)号:US20140026157A1

    公开(公告)日:2014-01-23

    申请号:US13996499

    申请日:2011-04-11

    IPC分类号: H04N21/4415 H04N21/442

    摘要: Methods, apparatuses, and articles associated with face recognition login, social network and video chat are disclosed herein. In various embodiments, an apparatus may include a networking interface, and a face recognition based controller configured to determine whether a user is watching a television, based on image frames of a video signal generated by a camera. The controller may be further configured to transmit a login request, via the network interface, to a server associated with a social network, on determination that the user is watching the television, to log the user into the social network, and enabling video chat. Other embodiments may be disclosed and/or claimed.

    摘要翻译: 本文公开了与面部识别登录,社交网络和视频聊天相关联的方法,装置和文章。 在各种实施例中,装置可以包括网络接口,以及基于面部识别的控制器,其被配置为基于由相机生成的视频信号的图像帧来确定用户正在观看电视。 控制器还可以被配置为:在确定用户正在观看电视的情况下,将登录请求经由网络接口​​发送到与社交网络相关联的服务器,将用户登录到社交网络中,以及启用视频聊天。 可以公开和/或要求保护其他实施例。

    OBJECT DETECTION USING MOTION ESTIMATION
    8.
    发明申请
    OBJECT DETECTION USING MOTION ESTIMATION 有权
    使用运动估计的目标检测

    公开(公告)号:US20140226865A1

    公开(公告)日:2014-08-14

    申请号:US13997092

    申请日:2011-12-30

    IPC分类号: H04N5/14 G06K9/62

    摘要: Systems and methods of detecting an object using motion estimation may include a processor and motion estimation and object detection logic coupled to the processor. The motion estimation and object detection logic may be configured to include logic to detect an object in a frame of a video based on motion estimation. The video may include a first frame and a second frame. The motion estimation may be performed on a region of the second frame using sum of absolute difference between the region of the second frame and a corresponding region of the first frame.

    摘要翻译: 使用运动估计来检测对象的系统和方法可以包括耦合到处理器的处理器和运动估计和对象检测逻辑。 运动估计和对象检测逻辑可以被配置为包括基于运动估计来检测视频帧中的对象的逻辑。 视频可以包括第一帧和第二帧。 可以使用第二帧的区域和第一帧的对应区域之间的绝对差的和来在第二帧的区域上执行运动估计。

    Object detection using motion estimation
    9.
    发明授权
    Object detection using motion estimation 有权
    使用运动估计的对象检测

    公开(公告)号:US09525803B2

    公开(公告)日:2016-12-20

    申请号:US13997092

    申请日:2011-12-30

    摘要: Systems and methods of detecting an object using motion estimation may include a processor and motion estimation and object detection logic coupled to the processor. The motion estimation and object detection logic may be configured to include logic to detect an object in a frame of a video based on motion estimation. The video may include a first frame and a second frame. The motion estimation may be performed on a region of the second frame using sum of absolute difference between the region of the second frame and a corresponding region of the first frame.

    摘要翻译: 使用运动估计来检测对象的系统和方法可以包括耦合到处理器的处理器和运动估计和对象检测逻辑。 运动估计和对象检测逻辑可以被配置为包括基于运动估计来检测视频帧中的对象的逻辑。 视频可以包括第一帧和第二帧。 可以使用第二帧的区域和第一帧的对应区域之间的绝对差的和来在第二帧的区域上执行运动估计。