中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

54 records (took 0.019 seconds)

    Optimal gradient pursuit for image alignment
    12.
    发明授权
    Optimal gradient pursuit for image alignment 有权
    图像对齐的最佳梯度追踪

    公开(公告)号：US08478077B2

    公开(公告)日：2013-07-02

    申请号：US13052097

    申请日：2011-03-20

    Applicant: Xiaoming Liu ,  Frederick Wilson Wheeler ,  Peter Henry Tu ,  Jilin Tu

    Inventor： Xiaoming Liu ,  Frederick Wilson Wheeler ,  Peter Henry Tu ,  Jilin Tu

    IPC: G06K9/32 ,  G06K9/62 ,  G06K9/66 ,  G06K9/36 ,  G06K9/48

    CPC classification number: G06K9/3241 ,  G06K9/00228

    Abstract: A method for image alignment is disclosed. In one embodiment, the method includes acquiring a facial image of a person and using a discriminative face alignment model to fit a generic facial mesh to the facial image to facilitate locating of facial features. The discriminative face alignment model may include a generative shape model component and a discriminative appearance model component. Further, the discriminative appearance model component may have been trained to estimate a score function that minimizes the angle between a gradient direction and a vector pointing toward a ground-truth shape parameter. Additional methods, systems, and articles of manufacture are also disclosed.

    Abstract translation: 公开了一种用于图像对准的方法。 在一个实施例中，该方法包括获取人的面部图像并使用区别性面部对准模型来将面部图像拟合为面部图像，以便于面部特征的定位。 鉴别面部对齐模型可以包括生成形状模型组件和鉴别外观模型组件。 此外，鉴别外观模型组件可能已经被训练以估计最小化梯度方向和指向地面真实形状参数的向量之间的角度的得分函数。 还公开了附加的方法，系统和制品。

    OPTIMAL SUBSPACES FOR FACE RECOGNITION
    13.
    发明申请
    OPTIMAL SUBSPACES FOR FACE RECOGNITION 有权
    面向认可的最佳选择

    公开(公告)号：US20110013845A1

    公开(公告)日：2011-01-20

    申请号：US12627039

    申请日：2009-11-30

    Applicant: Jilin Tu ,  Frederick Wilson Wheeler ,  Peter Henry Tu ,  Xiaoming Liu ,  Yan Tong

    Inventor： Jilin Tu ,  Frederick Wilson Wheeler ,  Peter Henry Tu ,  Xiaoming Liu ,  Yan Tong

    IPC: G06K9/68

    CPC classification number: G06K9/6234 ,  G06K9/00288 ,  G06K9/6215

    Abstract: A technique for optimizing object recognition is disclosed. The technique includes receiving at least one image of an object and at least one reference image. The technique further includes identifying at least one performance metric corresponding to an object recognition task. The identified performance metric is optimized to generate the corresponding optimized performance metric by determining an optimal subspace based on a determined objective function corresponding to the object recognition task and a difference between the received image and the corresponding reference image. Subsequently, the technique includes comparing the received image with the reference image based on the optimized performance metric for performing the object recognition task.

    Abstract translation: 公开了一种用于优化对象识别的技术。 该技术包括接收对象和至少一个参考图像的至少一个图像。 该技术还包括识别对应于对象识别任务的至少一个性能量度。 通过基于与对象识别任务相对应的确定的目标函数和接收到的图像与对应的参考图像之间的差异来确定最佳子空间来优化识别的性能度量以产生相应的优化性能度量。 随后，该技术包括基于用于执行对象识别任务的优化性能度量来比较接收到的图像与参考图像。

    SYSTEM AND METHOD FOR AUTOMATIC LANDMARK LABELING WITH MINIMAL SUPERVISION
    14.
    发明申请
    SYSTEM AND METHOD FOR AUTOMATIC LANDMARK LABELING WITH MINIMAL SUPERVISION 有权
    自动地标标签系统与方法与最小监控

    公开(公告)号：US20100246980A1

    公开(公告)日：2010-09-30

    申请号：US12533066

    申请日：2009-07-31

    Applicant: Yan Tong ,  Xiaoming Liu ,  Jilin Tu ,  Peter Henry Tu ,  Frederick Wilson Wheeler

    Inventor： Yan Tong ,  Xiaoming Liu ,  Jilin Tu ,  Peter Henry Tu ,  Frederick Wilson Wheeler

    IPC: G06K9/62 ,  G06K9/00

    CPC classification number: G06K9/66 ,  G06K9/00228 ,  G06T7/33 ,  G06T7/35 ,  G06T2207/20121 ,  G06T2207/30201

    Abstract: A system and method for estimating a set of landmarks for a large image ensemble employs only a small number of manually labeled images from the ensemble and avoids labor-intensive and error-prone object detection, tracking and alignment learning task limitations associated with manual image labeling techniques. A semi-supervised least squares congealing approach is employed to minimize an objective function defined on both labeled and unlabeled images. A shape model is learned on-line to constrain the landmark configuration. A partitioning strategy allows coarse-to-fine landmark estimation.

    Abstract translation: 用于估计大图像集合的一组地标的系统和方法仅使用来自集合的少量手动标记的图像，并且避免与手动图像标签相关联的劳动密集型和易出错的对象检测，跟踪和对准学习任务限制 技术 采用半监督的最小二乘法凝结方法来最小化在标记和未标记图像上定义的目标函数。 形状模型在线学习以约束地标配置。 分区策略允许粗略到精细的地标估计。

    Assesssing biometric sample quality using wavelets and a boosted classifier
    15.
    发明申请
    Assesssing biometric sample quality using wavelets and a boosted classifier 有权
    使用小波和增强分类器评估生物特征样本质量

    公开(公告)号：US20100111376A1

    公开(公告)日：2010-05-06

    申请号：US12457959

    申请日：2009-06-26

    Applicant: Weizhong Yan ,  Frederick W. Wheeler ,  Peter H. Tu ,  Xiaoming Liu

    Inventor： Weizhong Yan ,  Frederick W. Wheeler ,  Peter H. Tu ,  Xiaoming Liu

    IPC: G06K9/00

    CPC classification number: G07C9/00158 ,  G06K9/00268 ,  G06K9/036 ,  G06K9/6255

    Abstract: A biometric sample training device, a biometric sample quality assessment device, a biometric fusion recognition device, an integrated biometric fusion recognition system and example processes in which each may be used are described. Wavelets and a boosted classifier are used to assess the quality of biometric samples, such as facial images. The described biometric sample quality assessment approach provides accurate and reliable quality assessment values that are robust to various degradation factors, e.g., such as pose, illumination, and lighting in facial image biometric samples. The quality assessment values allow biometric samples of different sample types to be combined to support complex recognition techniques used by, for example, biometric fusion devices, resulting in improved accuracy and robustness in both biometric authentication and biometric recognition.

    Abstract translation: 描述了生物特征样本训练装置，生物特征样本质量评估装置，生物测定融合识别装置，集成生物测定融合识别系统以及其中可以使用每一种的实例过程。 小波和增强分类器用于评估生物特征样本的质量，如面部图像。 所描述的生物特征样本质量评估方法提供对各种降解因素（例如面部图像生物特征样本中的姿态，照明和照明）可靠的质量评估值。 质量评估值允许组合不同样本类型的生物特征样本，以支持例如生物测定融合装置使用的复杂识别技术，从而提高生物特征认证和生物识别识别两者的精度和鲁棒性。

    Method of combining images of multiple resolutions to produce an enhanced active appearance model
    16.
    发明申请
    Method of combining images of multiple resolutions to produce an enhanced active appearance model 有权
    组合多个分辨率图像以产生增强的活动外观模型的方法

    公开(公告)号：US20070292049A1

    公开(公告)日：2007-12-20

    申请号：US11650213

    申请日：2007-01-05

    Applicant: Xiaoming Liu ,  Frederick Wheeler ,  Peter Tu

    Inventor： Xiaoming Liu ,  Frederick Wheeler ,  Peter Tu

    IPC: G06K9/32

    CPC classification number: G06K9/621 ,  G06K9/00281

    Abstract: A method of producing an enhanced Active Appearance Model (AAM) by combining images of multiple resolutions is described herein. The method generally includes processing a plurality of images each having image landmarks and each image having an original resolution level. The images are down-sampled into multiple scales of reduced resolution levels. The AAM is trained for each image at each reduced resolution level, thereby creating a multi-resolution AAM. An enhancement technique is then used to refine the image landmarks for training the AAM at the original resolution level. The landmarks for training the AAM at each level of reduced resolution is obtained by scaling the landmarks used at the original resolution level by a ratio in accordance with the multiple scales.

    Abstract translation: 本文描述了通过组合多个分辨率的图像来生成增强的活动外观模型（AAM）的方法。 该方法通常包括处理多个具有图像界标的图像，并且每个图像具有原始分辨率级别。 图像被下采样成分辨率降低的多个尺度。 在每个降低的分辨率级别对每个图像训练AAM，从而创建多分辨率AAM。 然后使用增强技术来改善用于以原始分辨率级别训练AAM的图像界标。 通过将原始分辨率级别使用的地标按照多个尺度的比例进行缩放，可以获得在每个降低分辨率级别下对AAM进行训练的地标。

    Image concealing via efficient feature selection
    18.
    发明授权
    Image concealing via efficient feature selection 有权
    图像隐藏通过高效的特征选择

    公开(公告)号：US08774513B2

    公开(公告)日：2014-07-08

    申请号：US13346479

    申请日：2012-01-09

    Applicant: Xiaoming Liu ,  Peter Henry Tu ,  Ya Xue

    Inventor： Xiaoming Liu ,  Peter Henry Tu ,  Ya Xue

    IPC: G06K9/34 ,  H04N9/07

    CPC classification number: G06K9/6206 ,  G06K9/00281 ,  G06K9/6224 ,  G06K9/623 ,  G06K9/6263

    Abstract: A novel technique for unsupervised feature selection is disclosed. The disclosed methods include automatically selecting a subset of a feature of an image. Additionally, the selection of the subset of features may be incorporated with a congealing algorithm, such as a least-square-based congealing algorithm. By selecting a subset of the feature representation of an image, redundant and/or irrelevant features may be reduced or removed, and the efficiency and accuracy of least-square-based congealing may be improved.

    Abstract translation: 公开了一种用于无监督特征选择的新技术。 所公开的方法包括自动选择图像的特征的子集。 另外，可以使用诸如基于最小二乘法的凝结算法的凝结算法来结合特征子集的选择。 通过选择图像的特征表示的子集，可以减少或去除冗余和/或不相关的特征，并且可以提高基于最小二乘法的凝结的效率和精度。

    Methods involving face model fitting
    19.
    发明授权
    Methods involving face model fitting 有权
    涉及面部模型拟合的方法

    公开(公告)号：US08224037B2

    公开(公告)日：2012-07-17

    申请号：US12100620

    申请日：2008-04-10

    Applicant: Xiaoming Liu ,  Peter Henry Tu ,  Frederick Wilson Wheeler

    Inventor： Xiaoming Liu ,  Peter Henry Tu ,  Frederick Wilson Wheeler

    IPC: G06K9/00

    CPC classification number: G06K9/00288 ,  G06K9/00261 ,  G06K9/621

    Abstract: A method for face model fitting comprising, receiving a first observed image, receiving a second observed image, and fitting an active appearance model of a third image to the second observed image and the first observed image with an algorithm that includes a first function of a mean-square-error between a warped image of the second observed image and a synthesis of the active appearance model and a second function of a mean-square-error between the warped image of the second observed image and an appearance data of the first observed image.

    Abstract translation: 一种用于面部模型拟合的方法，包括：接收第一观察图像，接收第二观察图像，以及使用包括第一观察图像的第一函数的第二观察图像和第一观察图像拟合第三图像的活动外观模型 第二观察图像的翘曲图像与活动外观模型的合成之间的均方误差以及第二观察图像的翘曲图像与第一观察图像的外观数据之间的均方误差的第二函数 图片。

Patent Agency Ranking