Image-based lighting simulation for objects
    1.
    发明授权
    Image-based lighting simulation for objects 有权
    基于图像的对象照明仿真

    公开(公告)号:US08803880B2

    公开(公告)日:2014-08-12

    申请号:US12545420

    申请日:2009-08-21

    IPC分类号: G06T15/50 G09G5/02 G09G5/00

    CPC分类号: G06T15/506

    摘要: This disclosure relates to simulating the light-reflective condition of an object when situated in a given environment. A spatial irradiance mapping of the environment may be obtained, from which a series of directional incidence light sources are determined. The reflective qualities of the object may be modeled as a bi-directional reflection distribution function to be applied to directional incidence light sources. The spatial irradiance mapping and/or bi-directional reflection distribution function may be obtained according to image-based techniques.

    摘要翻译: 本公开涉及模拟位于给定环境中的物体的光反射状态。 可以获得环境的空间辐照度映射,从中确定一系列定向入射光源。 物体的反射特性可以被建模为应用于定向入射光源的双向反射分布函数。 可以根据基于图像的技术获得空间辐照度映射和/或双向反射分布函数。

    Concave surface modeling in image-based visual hull
    2.
    发明授权
    Concave surface modeling in image-based visual hull 有权
    基于图像的视觉船体的凹面建模

    公开(公告)号:US08526713B2

    公开(公告)日:2013-09-03

    申请号:US12995751

    申请日:2009-12-07

    IPC分类号: G06K9/00

    CPC分类号: G06T7/564 G06T15/205

    摘要: Apparatus and methods disclosed herein provide for a set of reference images obtained from a camera and a reference image obtained from a viewpoint to capture an entire concave region of an object; a silhouette processing module for obtaining a silhouette image of the concave region of the object; and a virtual-image synthesis module connected to the silhouette processing module for synthesizing a virtual inside-out image of the concave region from the computed silhouette images and for generating a visual hull of the object having the concave region.

    摘要翻译: 本文公开的装置和方法提供从照相机获取的一组参考图像和从视点获得的用于捕获物体的整个凹区域的参考图像; 用于获得对象的凹区域的剪影图像的剪影处理模块; 以及虚拟图像合成模块,其连接到所述轮廓处理模块,用于从所计算的轮廓图像合成所述凹区域的虚拟内向外图像,并且用于生成具有所述凹区域的所述对象的视觉船体。

    Text vectorization using OCR and stroke structure modeling
    3.
    发明授权
    Text vectorization using OCR and stroke structure modeling 失效
    使用OCR和笔画结构建模的文本向量化

    公开(公告)号:US08244038B2

    公开(公告)日:2012-08-14

    申请号:US12332913

    申请日:2008-12-11

    IPC分类号: G06K9/18

    CPC分类号: G06K9/481 G06K2209/01

    摘要: Systems and methods are described that facilitate dominant point detection for text in a scanned document. The dominant points are classified as “major” (e.g., structural) and “minor” (e.g., serif). A set of rules or parameters for each character is determined off-line. During the text vectorization, OCR is performed and the rules (parameters) associated with the recognized character are selected. Both major and minor dominant points are detected as a maximization process with the parameter set. For minor dominant points, additional processes are optionally employed.

    摘要翻译: 描述了促进扫描文档中的文本的主要点检测的系统和方法。 优势点被归类为“主要”(例如,结构)和“次要”(例如,衬线)。 离线确定每个字符的一组规则或参数。 在文本向量化期间,执行OCR并选择与识别的字符相关联的规则(参数)。 主要和次要主要点被检测为具有参数集的最大化过程。 对于较小的优势点,可以采用额外的过程。

    BETWEEN-SEGMENT DISCONTINUITY REDUCTION FOR TEXT VECTORIZATION USING DOMINANT POINT CLASSIFICATION
    4.
    发明申请
    BETWEEN-SEGMENT DISCONTINUITY REDUCTION FOR TEXT VECTORIZATION USING DOMINANT POINT CLASSIFICATION 失效
    使用主要点分类进行文本验证的分段不连续性减少

    公开(公告)号:US20110007334A1

    公开(公告)日:2011-01-13

    申请号:US12498387

    申请日:2009-07-07

    IPC分类号: G06K15/02

    摘要: What is disclosed is a novel system and method for text vectorization for bitmap images with reduced artificial discontinuities. Dominant points are identified in a bitmap character image. An initial curve is fitted to edge points of the character image in a vicinity of a selected dominant point. A set of boundary parameters in a vicinity of the selected dominant point are estimated based upon the initial curve. The selected dominant point is then classified as one of a sharp dominant point and a smooth dominant point based upon the boundary parameters or alternatively upon predefined classifications produced by an optical character recognition process. Curves are fitted between the selected dominant point and adjacent dominant points. The fitted curves maintain the estimated boundary parameters in the vicinity of smooth dominant points. A vectorized representation of the text character image based upon the fitted curves is produced as output.

    摘要翻译: 公开的是用于具有减少的人造不连续性的位图图像的文本向量化的新颖系统和方法。 主要点在位图字符图像中被识别。 初始曲线拟合到所选择的优势点附近的字符图像的边缘点。 基于初始曲线估计所选优势点附近的一组边界参数。 然后,基于边界参数或者通过光学字符识别处理产生的预定义分类,选择的主点被分类为锐利主要点和平滑主要点之一。 曲线拟合在选定的优势点和相邻优势点之间。 拟合曲线保持平滑优势点附近的估计边界参数。 作为输出,产生基于拟合曲线的文本字符图像的向量化表示。

    Connectivity similarity based graph learning for interactive multi-label image segmentation
    5.
    发明授权
    Connectivity similarity based graph learning for interactive multi-label image segmentation 有权
    用于交互式多标签图像分割的基于连通性的图形学习

    公开(公告)号:US08842915B2

    公开(公告)日:2014-09-23

    申请号:US13260109

    申请日:2009-04-22

    IPC分类号: G06K9/34

    摘要: A system and method of connectivity-based image processing to identify and extract objects in image data is described. Variations on the method may include iterative local smoothing operations and various algorithmic solutions to improve real-time processing. Variations may also include object extraction processes based on user-provided information about an object in an image.

    摘要翻译: 描述了用于识别和提取图像数据中的对象的基于连接的图像处理的系统和方法。 该方法的变化可以包括迭代局部平滑操作和各种算法解决方案以改进实时处理。 变化还可以包括基于用户提供的关于图像中的对象的信息的对象提取过程。

    CONCAVE SURFACE MODELING IN IMAGE-BASED VISUAL HULL
    6.
    发明申请
    CONCAVE SURFACE MODELING IN IMAGE-BASED VISUAL HULL 有权
    基于图像的视觉海鸥的表面建模

    公开(公告)号:US20110262031A1

    公开(公告)日:2011-10-27

    申请号:US12995751

    申请日:2009-12-07

    IPC分类号: G06K9/36 G06K9/00

    CPC分类号: G06T7/564 G06T15/205

    摘要: Apparatus and methods disclosed herein provide for a set of reference images obtained from a camera and a reference image obtained from a viewpoint to capture an entire concave region of an object; a silhouette processing module for obtaining a silhouette image of the concave region of the object; and a virtual-image synthesis module connected to the silhouette processing module for synthesizing a virtual inside-out image of the concave region from the computed silhouette images and for generating a visual hull of the object having the concave region.

    摘要翻译: 本文公开的装置和方法提供从照相机获取的一组参考图像和从视点获得的用于捕获物体的整个凹区域的参考图像; 用于获得对象的凹区域的剪影图像的剪影处理模块; 以及虚拟图像合成模块,其连接到所述轮廓处理模块,用于从所计算的轮廓图像合成所述凹区域的虚拟内向外图像,并且用于生成具有所述凹区域的所述对象的视觉船体。

    IMAGE-BASED LIGHTING SIMULATION FOR OBJECTS
    7.
    发明申请
    IMAGE-BASED LIGHTING SIMULATION FOR OBJECTS 有权
    基于图像的对象照明模拟

    公开(公告)号:US20110043522A1

    公开(公告)日:2011-02-24

    申请号:US12545420

    申请日:2009-08-21

    IPC分类号: G06T15/50

    CPC分类号: G06T15/506

    摘要: This disclosure relates to simulating the light-reflective condition of an object when situated in a given environment. A spatial irradiance mapping of the environment may be obtained, from which a series of directional incidence light sources are determined. The reflective qualities of the object may be modeled as a bi-directional reflection distribution function to be applied to directional incidence light sources. The spatial irradiance mapping and/or bi-directional reflection distribution function may be obtained according to image-based techniques.

    摘要翻译: 本公开涉及模拟位于给定环境中的物体的光反射状态。 可以获得环境的空间辐照度映射,从中确定一系列定向入射光源。 物体的反射特性可以被建模为应用于定向入射光源的双向反射分布函数。 可以根据基于图像的技术获得空间辐照度映射和/或双向反射分布函数。

    Between-segment discontinuity reduction for text vectorization using dominant point classification
    8.
    发明授权
    Between-segment discontinuity reduction for text vectorization using dominant point classification 失效
    使用优点分类的文本向量化的段间不连续性减少

    公开(公告)号:US08441684B2

    公开(公告)日:2013-05-14

    申请号:US12498387

    申请日:2009-07-07

    IPC分类号: H04N1/387 G06K15/00 G06K9/34

    摘要: What is disclosed is a novel system and method for text vectorization for bitmap images with reduced artificial discontinuities. Dominant points are identified in a bitmap character image. An initial curve is fitted to edge points of the character image in a vicinity of a selected dominant point. A set of boundary parameters in a vicinity of the selected dominant point are estimated based upon the initial curve. The selected dominant point is then classified as one of a sharp dominant point and a smooth dominant point based upon the boundary parameters or alternatively upon predefined classifications produced by an optical character recognition process. Curves are fitted between the selected dominant point and adjacent dominant points. The fitted curves maintain the estimated boundary parameters in the vicinity of smooth dominant points. A vectorized representation of the text character image based upon the fitted curves is produced as output.

    摘要翻译: 公开的是用于具有减少的人造不连续性的位图图像的文本向量化的新颖系统和方法。 主要点在位图字符图像中被识别。 初始曲线拟合到所选择的优势点附近的字符图像的边缘点。 基于初始曲线估计所选优势点附近的一组边界参数。 然后,基于边界参数或者通过光学字符识别处理产生的预定义分类,选择的主点被分类为锐利主要点和平滑主要点之一。 曲线拟合在选定的优势点和相邻优势点之间。 拟合曲线保持平滑优势点附近的估计边界参数。 作为输出,产生基于拟合曲线的文本字符图像的向量化表示。

    CONNECTIVITY SIMILARITY BASED GRAPH LEARNING FOR INTERACTIVE MULTI-LABEL IMAGE SEGMENTATION
    9.
    发明申请
    CONNECTIVITY SIMILARITY BASED GRAPH LEARNING FOR INTERACTIVE MULTI-LABEL IMAGE SEGMENTATION 有权
    基于连通性的图形学习交互式多标签图像分割

    公开(公告)号:US20120027300A1

    公开(公告)日:2012-02-02

    申请号:US13260109

    申请日:2009-04-22

    IPC分类号: G06K9/34

    摘要: A system and method of connectivity-based image processing to identify and extract objects in image data. Variations on the method may include iterative local smoothing operations and various algorithmic solutions to improve real-time processing. Variations may also include object extraction processes based on user-provided information about an object in an image.

    摘要翻译: 基于连接的图像处理的系统和方法,用于识别和提取图像数据中的对象。 该方法的变化可以包括迭代局部平滑操作和各种算法解决方案以改进实时处理。 变化还可以包括基于用户提供的关于图像中的对象的信息的对象提取过程。

    TEXT VECTORIZATION USING OCR AND STROKE STRUCTURE MODELING
    10.
    发明申请
    TEXT VECTORIZATION USING OCR AND STROKE STRUCTURE MODELING 失效
    使用OCR和STROKE结构建模的文本验证

    公开(公告)号:US20100150445A1

    公开(公告)日:2010-06-17

    申请号:US12332913

    申请日:2008-12-11

    IPC分类号: G06K9/18

    CPC分类号: G06K9/481 G06K2209/01

    摘要: Systems and methods are described that facilitate dominant point detection for text in a scanned document. The dominant points are classified as “major” (e.g., structural) and “minor” (e.g., serif). A set of rules or parameters for each character is determined off-line. During the text vectorization, OCR is performed and the rules (parameters) associated with the recognized character are selected. Both major and minor dominant points are detected as a maximization process with the parameter set. For minor dominant points, additional processes are optionally employed.

    摘要翻译: 描述了促进扫描文档中的文本的主要点检测的系统和方法。 优势点被归类为“主要”(例如,结构)和“次要”(例如,衬线)。 离线确定每个字符的一组规则或参数。 在文本向量化期间,执行OCR并选择与识别的字符相关联的规则(参数)。 主要和次要主要点被检测为具有参数集的最大化过程。 对于较小的优势点,可以采用额外的过程。