-
公开(公告)号：US08452109B2
公开(公告)日：2013-05-28
申请号：US12655930
申请日：2010-01-11
申请人： Neil Alldrin , Kshitiz Garg , Andrew Neil Stein , Kristin Jean Dana , Bruce Allen Maxwell , Casey Arthur Smith , Youngrock Yoon , Besma Roui Abidi
发明人： Neil Alldrin , Kshitiz Garg , Andrew Neil Stein , Kristin Jean Dana , Bruce Allen Maxwell , Casey Arthur Smith , Youngrock Yoon , Besma Roui Abidi
IPC分类号： G06K9/62
CPC分类号： G06K9/4661 , G06T7/11 , G06T7/162 , G06T7/41 , G06T7/49 , G06T7/90 , G06T2200/24 , G06T2207/10024
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected pair of regions of the image file are of a same intrinsic characteristic, for example, a same texture, providing a classifier derived from a computer learning technique, computing a classification score for the selected pair of regions of the image file, as a function of the feature vector and the classifier and classifying the regions as being of the same intrinsic characteristic, as a function of the classification score.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：提供描绘图像的图像文件，在计算机存储器中组装图像文件的特征向量，所述特征向量包含关于所选择的一对 图像文件的区域具有相同的固有特性，例如相同的纹理，提供从计算机学习技术导出的分类器，根据特征的函数计算所选择的图像文件区域的分类分数 矢量和分类器，并将区域分类为具有相同固有特征的区域，作为分类分数的函数。
-
公开(公告)号：US20110170768A1
公开(公告)日：2011-07-14
申请号：US12655930
申请日：2010-01-11
申请人： Neil Alldrin , Kshitiz Garg , Andrew Neil Stein , Kristin Jean Dana , Bruce Allen Maxwell , Casey Arthur Smith , Youngrock Yoon , Besma Roui Abidi
发明人： Neil Alldrin , Kshitiz Garg , Andrew Neil Stein , Kristin Jean Dana , Bruce Allen Maxwell , Casey Arthur Smith , Youngrock Yoon , Besma Roui Abidi
IPC分类号： G06K9/62
CPC分类号： G06K9/4661 , G06T7/11 , G06T7/162 , G06T7/41 , G06T7/49 , G06T7/90 , G06T2200/24 , G06T2207/10024
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected pair of regions of the image file are of a same intrinsic characteristic, for example, a same texture, providing a classifier derived from a computer learning technique, computing a classification score for the selected pair of regions of the image file, as a function of the feature vector and the classifier and classifying the regions as being of the same intrinsic characteristic, as a function of the classification score.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：提供描绘图像的图像文件，在计算机存储器中组装图像文件的特征向量，所述特征向量包含关于所选择的一对 图像文件的区域具有相同的固有特性，例如相同的纹理，提供从计算机学习技术导出的分类器，根据特征的函数计算所选择的图像文件区域的分类分数 矢量和分类器，并将区域分类为具有相同固有特征的区域，作为分类分数的函数。
-
公开(公告)号：US08483480B2
公开(公告)日：2013-07-09
申请号：US12653846
申请日：2009-12-18
CPC分类号： G06K9/4661 , G06K9/4652 , G06T5/002 , G06T5/008 , G06T2207/20192
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, generating an illumination image from the image; and factoring the illumination image to generate a diffuse illumination image and a harsh shadow illumination image.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：在计算机存储器中提供描绘图像的图像文件，从图像生成照明图像; 并且将照明图像分解以产生漫射照明图像和恶劣阴影照明图像。
-
公开(公告)号：US20110150358A1
公开(公告)日：2011-06-23
申请号：US12653846
申请日：2009-12-18
IPC分类号： G06K9/40
CPC分类号： G06K9/4661 , G06K9/4652 , G06T5/002 , G06T5/008 , G06T2207/20192
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, generating an illumination image from the image; and factoring the illumination image to generate a diffuse illumination image and a harsh shadow illumination image.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：在计算机存储器中提供描绘图像的图像文件，从图像生成照明图像; 并且将照明图像分解以产生漫射照明图像和恶劣阴影照明图像。
-
公开(公告)号：US09760799B2
公开(公告)日：2017-09-12
申请号：US12661052
申请日：2010-03-10
申请人： Andrew Neil Stein , Neil Alldrin , Kshitiz Garg
发明人： Andrew Neil Stein , Neil Alldrin , Kshitiz Garg
CPC分类号： G06K9/6209 , G06K9/00221 , G06K9/4661
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, identifying shadow edges in the image, computing gradient information for the image and modifying the gradient information relative to the shadow edges for improved performance of computer functionality in an image processing operation.
-
公开(公告)号：US20100278448A1
公开(公告)日：2010-11-04
申请号：US12387258
申请日：2009-04-30
申请人： Richard Mark Friedhoff , Casey Arthur Smith , Bruce Allen Maxwell , Neil Alldrin , Steven Joseph Bushell , Timothy King Rodgers, JR.
发明人： Richard Mark Friedhoff , Casey Arthur Smith , Bruce Allen Maxwell , Neil Alldrin , Steven Joseph Bushell , Timothy King Rodgers, JR.
CPC分类号： G06T5/007 , G06T5/50 , G06T7/187 , G06T2207/20012
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsic images according to a set of preselected operations and merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：提供描绘图像的图像文件，在计算机存储器中，对图像文件执行图像分离操作，以生成对应于图像的一组固有图像，修改 根据一组预选操作来选择一组固有图像中的一个，并且相对于该固有图像集合合并一组固有图像中的修改后的一组，以提供经修改的输出图像。
-
公开(公告)号：US08478029B2
公开(公告)日：2013-07-02
申请号：US12454926
申请日：2009-05-26
CPC分类号： G06T7/90 , G06T7/11 , G06T2207/10024 , G06T2207/20016 , G06T2207/20104
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, forming a set of selectively varied representations of the image file and performing an image segregation operation on at least one preselected representation of the image of the image file, to generate intrinsic images corresponding to the image. According to a feature of the exemplary embodiment of the present invention, the selectively varied representations comprise multi-resolution representations such as a scale-spaced pyramid of representations. In a further feature of the exemplary embodiment of the present invention, the intrinsic images comprise a material image and an illumination image.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：在计算机存储器中提供描绘图像的图像文件，形成一组选择性变化的图像文件表示，并对至少一个预选的图像分离操作进行 表示图像文件的图像，以产生对应于图像的固有图像。 根据本发明的示例性实施例的特征，选择性地变化的表示包括多分辨率表示，诸如按比例间隔的表示的金字塔。 在本发明的示例性实施例的另一特征中，固有图像包括材料图像和照明图像。
-
公开(公告)号：US20110222742A1
公开(公告)日：2011-09-15
申请号：US12661052
申请日：2010-03-10
申请人： Andrew Neil Stein , Neil Alldrin , Kshitiz Garg
发明人： Andrew Neil Stein , Neil Alldrin , Kshitiz Garg
IPC分类号： G06K9/00
CPC分类号： G06K9/6209 , G06K9/00221 , G06K9/4661
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, identifying shadow edges in the image, computing gradient information for the image and modifying the gradient information relative to the shadow edges for improved performance of computer functionality in an image processing operation.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：提供描绘图像的图像文件，在计算机存储器中识别图像中的阴影边缘，计算图像的梯度信息并相对于阴影修改梯度信息 边缘，用于改善图像处理操作中计算机功能的性能。
-
公开(公告)号：US20100303348A1
公开(公告)日：2010-12-02
申请号：US12454926
申请日：2009-05-26
CPC分类号： G06T7/90 , G06T7/11 , G06T2207/10024 , G06T2207/20016 , G06T2207/20104
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, forming a set of selectively varied representations of the image file and performing an image segregation operation on at least one preselected representation of the image of the image file, to generate intrinsic images corresponding to the image. According to a feature of the exemplary embodiment of the present invention, the selectively varied representations comprise multi-resolution representations such as a scale-spaced pyramid of representations. In a further feature of the exemplary embodiment of the present invention, the intrinsic images comprise a material image and an illumination image.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：在计算机存储器中提供描绘图像的图像文件，形成一组选择性变化的图像文件表示，并对至少一个预选的图像分离操作进行 表示图像文件的图像，以产生对应于图像的固有图像。 根据本发明的示例性实施例的特征，选择性地变化的表示包括多分辨率表示，诸如按比例间隔的表示的金字塔。 在本发明的示例性实施例的另一特征中，固有图像包括材料图像和照明图像。
-
公开(公告)号：US08391601B2
公开(公告)日：2013-03-05
申请号：US12387258
申请日：2009-04-30
申请人： Richard Mark Friedhoff , Casey Arthur Smith , Bruce Allen Maxwell , Neil Alldrin , Steven Joseph Bushell , Timothy King Rodgers, Jr.
发明人： Richard Mark Friedhoff , Casey Arthur Smith , Bruce Allen Maxwell , Neil Alldrin , Steven Joseph Bushell , Timothy King Rodgers, Jr.
CPC分类号： G06T5/007 , G06T5/50 , G06T7/187 , G06T2207/20012
摘要： In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsic images according to a set of preselected operations and merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.
摘要翻译： 在本发明的第一示例性实施例中，提供了一种用于处理图像的自动计算机化方法。 根据本发明的特征，该方法包括以下步骤：提供描绘图像的图像文件，在计算机存储器中，对图像文件执行图像分离操作，以生成对应于图像的一组固有图像，修改 根据一组预选操作来选择一组固有图像中的一个，并且相对于该固有图像集合合并一组固有图像中的修改后的一组，以提供经修改的输出图像。
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.026 秒)
