Segmenting human hairs and faces
    1.
    发明授权
    Segmenting human hairs and faces 失效
    分割人的头发和面孔

    公开(公告)号:US08638993B2

    公开(公告)日:2014-01-28

    申请号:US13066112

    申请日:2011-04-05

    IPC分类号: G06K9/00

    摘要: Systems for segmenting human hairs and faces in color images are disclosed, with methods and processes for making and using the same. The image may be cropped around the face area and roughly centered. Optionally, the illumination environment of the input image may be determined. If the image is taken under dark environment or the contrast between the face and hair regions and background is low, an extra image enhancement may be applied. Sub-processes for identifying the pose angle and chin contours may be performed. A preliminary mask for the face by using multiple cues, such as skin color, pose angle, face shape and contour information can be represented. An initial hair mask by using the abovementioned multiple cues plus texture and hair shape information may be created. The preliminary face and hair masks are globally refined using multiple techniques.

    摘要翻译: 公开了用于分割彩色图像中的人发和脸部的系统,其具有用于制造和使用它们的方法和过程。 图像可能会在脸部区域周围裁剪,并且大致居中。 可选地,可以确定输入图像的照明环境。 如果在黑暗环境下拍摄图像,或者脸部和头发区域与背景之间的对比度较低,则可能会应用额外的图像增强。 可以执行用于识别姿态角度和下巴轮廓的子过程。 可以表示通过使用多种线索(如肤色,姿态角度,脸部形状和轮廓信息)的面部的初步面具。 可以创建通过使用上述多重线索加上纹理和头发形状信息的初始头发面罩。 初步的面部和头发面罩使用多种技术进行全球精炼。

    Systems and methods for segmenting human hairs and faces in color images
    2.
    发明申请
    Systems and methods for segmenting human hairs and faces in color images 失效
    用于将人的头发和脸部分割成彩色图像的系统和方法

    公开(公告)号:US20110299776A1

    公开(公告)日:2011-12-08

    申请号:US13066112

    申请日:2011-04-05

    IPC分类号: G06K9/34

    摘要: Systems for segmenting human hairs and faces in color images are disclosed, with methods and processes for making and using the same. The image may be cropped around the face area and roughly centered. Optionally, the illumination environment of the input image may be determined. If the image is taken under dark environment or the contrast between the face and hair regions and background is low, an extra image enhancement may be applied. Sub-processes for identifying the pose angle and chin contours may be performed. A preliminary mask for the face by using multiple cues, such as skin color, pose angle, face shape and contour information can be represented. An initial hair mask by using the abovementioned multiple cues plus texture and hair shape information may be created. The preliminary face and hair masks are globally refined using multiple techniques.

    摘要翻译: 公开了用于分割彩色图像中的人发和脸部的系统,其具有用于制造和使用它们的方法和过程。 图像可能会在脸部区域周围裁剪,并且大致居中。 可选地,可以确定输入图像的照明环境。 如果在黑暗环境下拍摄图像,或者脸部和头发区域与背景之间的对比度较低,则可能会应用额外的图像增强。 可以执行用于识别姿态角度和下巴轮廓的子过程。 可以表示通过使用多种线索(如肤色,姿态角度,脸部形状和轮廓信息)的面部的初步面具。 可以创建通过使用上述多重线索加上纹理和头发形状信息的初始头发面罩。 初步的面部和头发面罩使用多种技术进行全球精炼。

    Segmenting Human Hairs and Faces
    3.
    发明申请
    Segmenting Human Hairs and Faces 审中-公开
    分割人力和面孔

    公开(公告)号:US20140119642A1

    公开(公告)日:2014-05-01

    申请号:US14137771

    申请日:2013-12-20

    IPC分类号: G06K9/00 G06K9/46

    摘要: Systems for segmenting human hairs and faces in color images are disclosed, with methods and processes for making and using the same. The image may be cropped around the face area and roughly centered. Optionally, the illumination environment of the input image may be determined. If the image is taken under dark environment or the contrast between the face and hair regions and background is low, an extra image enhancement may be applied. Sub-processes for identifying the pose angle and chin contours may be performed. A preliminary mask for the face by using multiple cues, such as skin color, pose angle, face shape and contour information can be represented. An initial hair mask by using the abovementioned multiple cues plus texture and hair shape information may be created. The preliminary face and hair masks are globally refined using multiple techniques.

    摘要翻译: 公开了用于分割彩色图像中的人发和脸部的系统,其具有用于制造和使用它们的方法和过程。 图像可能会在脸部区域周围裁剪,并且大致居中。 可选地,可以确定输入图像的照明环境。 如果在黑暗环境下拍摄图像,或者脸部和头发区域与背景之间的对比度较低,则可能会应用额外的图像增强。 可以执行用于识别姿态角度和下巴轮廓的子过程。 可以表示通过使用多种线索(如肤色,姿态角度,脸部形状和轮廓信息)的面部的初步面具。 可以创建通过使用上述多重线索加上纹理和头发形状信息的初始头发面罩。 初步的面部和头发面罩使用多种技术进行全球精炼。

    Manifold learning and matting
    4.
    发明授权
    Manifold learning and matting 有权
    歧管学习和消光

    公开(公告)号:US09311567B2

    公开(公告)日:2016-04-12

    申请号:US13068460

    申请日:2011-05-10

    IPC分类号: G06K9/62 G06T7/00

    摘要: Systems for manifold learning for matting are disclosed, with methods and processes for making and using the same. The embodiments disclosed herein provide a closed form solution for solving the matting problem by a manifold learning technique, Local Linear Embedding. The transition from foreground to background is characterized by color and texture variations, which should be captured in the alpha map. This intuition implies that neighborhood relationship in the feature space should be preserved in the alpha map. By applying Local Linear Embedding using the disclosed embodiments, the local image variations can be preserved in the embedded manifold, which is the resulting alpha map. Without any strong assumption, such as color line model, the disclosed embodiments can be easily extended to incorporate other features beyond RGB color features, such as gradient and texture information.

    摘要翻译: 公开了用于消光的流体学习系统,其具有用于制造和使用其的方法和过程。 本文公开的实施例提供了一种用于通过歧管学习技术局部线性嵌入来解决消光问题的闭合形式解决方案。 从前景到背景的转换的特点是颜色和纹理变化,应该在alpha图中捕获。 这种直觉意味着特征空间中的邻域关系应该保留在alpha图中。 通过使用所公开的实施例应用局部线性嵌入,局部图像变化可以保留在嵌入式多维数据集中,这是所得到的α图。 没有任何强烈的假设,例如颜色线模型,所公开的实施例可以容易地扩展以包含超出RGB颜色特征(诸如梯度和纹理信息)的其他特征。

    Systems and methods for manifold learning for matting
    5.
    发明申请
    Systems and methods for manifold learning for matting 有权
    用于消光的歧管学习的系统和方法

    公开(公告)号:US20110274344A1

    公开(公告)日:2011-11-10

    申请号:US13068460

    申请日:2011-05-10

    IPC分类号: G06K9/62

    摘要: Systems for manifold learning for matting are disclosed, with methods and processes for making and using the same. The embodiments disclosed herein provide a closed form solution for solving the matting problem by a manifold learning technique, Local Linear Embedding. The transition from foreground to background is characterized by color and texture variations, which should be captured in the alpha map. This intuition implies that neighborhood relationship in the feature space should be preserved in the alpha map. By applying Local Linear Embedding using the disclosed embodiments, the local image variations can be preserved in the embedded manifold, which is the resulting alpha map. Without any strong assumption, such as color line model, the disclosed embodiments can be easily extended to incorporate other features beyond RGB color features, such as gradient and texture information.

    摘要翻译: 公开了用于消光的流体学习系统,其具有用于制造和使用其的方法和过程。 本文公开的实施例提供了一种用于通过歧管学习技术局部线性嵌入来解决消光问题的闭合形式解决方案。 从前景到背景的转换的特点是颜色和纹理变化,应该在alpha图中捕获。 这种直觉意味着特征空间中的邻域关系应该保留在alpha图中。 通过使用所公开的实施例应用局部线性嵌入,局部图像变化可以保留在嵌入式多维数据集中,这是所得到的α图。 没有任何强烈的假设,例如颜色线模型,所公开的实施例可以容易地扩展以包含超出RGB颜色特征(诸如梯度和纹理信息)的其他特征。

    Refinement of segmentation markup
    6.
    发明授权
    Refinement of segmentation markup 失效
    细分标记的细化

    公开(公告)号:US08670615B2

    公开(公告)日:2014-03-11

    申请号:US12924705

    申请日:2010-09-30

    IPC分类号: G06K9/34

    CPC分类号: G06T7/11 G06T7/194

    摘要: Systems for refinement of a segmentation of an image using spray-paint markup are disclosed, with methods and processes for making and using the same. Spray-paint markup allows for easy markup of errors in a segmentation. The markup's data may be correlated or harmonized with the representation of the segmentation, such that it may be applied to the segmentation. The markup's data is utilized to refine the segmentation errors. To assist in the refinement process, the resolutions may be scaled down so as to exert less computation burden during the process.

    摘要翻译: 公开了使用喷漆标记来改进图像分割的系统,其具有用于制造和使用图像的方法和过程。 喷漆标记允许在分割中容易地标记错误。 标记的数据可以与分割的表示相关或协调,使得它可以应用于分割。 标记的数据用于细化分段错误。 为了协助细化过程,可以缩小分辨率,以便在该过程中减少计算负担。

    COMPUTER IMPLEMENTED TECHNIQUE FOR ANALYZING IMAGES
    10.
    发明申请
    COMPUTER IMPLEMENTED TECHNIQUE FOR ANALYZING IMAGES 有权
    用于分析图像的计算机实现技术

    公开(公告)号:US20080199075A1

    公开(公告)日:2008-08-21

    申请号:US11841355

    申请日:2007-08-20

    IPC分类号: G06K9/34

    CPC分类号: G06K9/6276 G06K9/6251

    摘要: An input image is received, represented by a matrix D having a first number of dimensions. Each of the first number of dimensions may represent or correspond to a portion of the image. A metric objective may be identified. A dimensional reduction on the matrix D may then be performed that optimize the metric objective, so that a matrix d of a second number of dimensions is identified to represent the input image, where the second number of dimensions is less than the first number of dimensions.

    摘要翻译: 接收由具有第一数量维数的矩阵D表示的输入图像。 第一数量的维度中的每一个可以表示或对应于图像的一部分。 可以确定度量目标。 然后可以执行矩阵D上的尺寸减小,其优化度量目标,使得识别第二数量维度的矩阵d以表示输入图像,其中第二数量的维度小于第一数量的维度 。