-
公开(公告)号：US20150206334A1
公开(公告)日：2015-07-23
申请号：US14673460
申请日：2015-03-30
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Dmitriy Shirchenko
CPC classification number: G06T11/60 , G06T7/60 , G06T7/68 , G06T7/73 , G06T7/90 , G06T2207/10024 , G06T2207/20221 , G09G5/377
Abstract: A method, system and computer program product for virtually placing an object on an image of a human appendage is provided. First, image boundaries are detected in the image of the appendage and converted into a set of line segments. A pair of line segments is evaluated according to a function that combines subscores of the pair of line segments to produce a score. The subscores of the line segments are computed based on various properties such as orientation difference, extent, proximity to the center of the image, bilateral symmetry, and the number of skin-colored pixels. A pair of line segments with the highest score is chosen as the appendage boundaries and is used to determine the position, orientation, and extent of the object. The image of the object is then transformed according to the determined parameters and combined with the image of the appendage to produce the desired result.
Abstract translation: 提供了一种用于将物体虚拟地放置在人类附属物的图像上的方法，系统和计算机程序产品。 首先，在附件的图像中检测图像边界并将其转换成一组线段。 根据组合一对线段的分数以产生分数的函数来评估一对线段。 线段的分数是基于各种属性来计算的，例如取向差异，程度，图像中心的接近度，双边对称性和皮肤色素数量。 选择具有最高分数的一对线段作为附加边界，并用于确定对象的位置，方向和范围。 然后根据确定的参数对对象的图像进行变换，并与附件的图像组合以产生期望的结果。
-
公开(公告)号：US08977072B1
公开(公告)日：2015-03-10
申请号：US13713776
申请日：2012-12-13
Applicant: A9.com, Inc.
Inventor： Raghavan Manmatha , Mark A. Ruzon
CPC classification number: G06K9/344 , G06K9/18 , G06K9/325 , G06K9/342 , G06K9/346 , G06K9/38 , G06K9/40 , G06K9/62 , G06K9/6288 , G06K9/748 , G06K2209/01
Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.
Abstract translation: 本发明的各种实施例涉及用于检测和识别由相机和扫描仪捕获的图像中的文本的方法，系统和计算机程序产品。 首先，应用一系列图像处理技术来检测图像中的文本区域。 随后，检测到的文本区域通过不同的处理阶段，减少模糊和可变照明的负面影响。 这导致创建多个相同文本区域的图像。 这些多个版本中的一些被发送到字符识别系统。 然后，将发送到字符识别系统的图像的每个版本的结果文本合并为单个结果，其中单个结果是检测到的文本。
-
公开(公告)号：US09530069B2
公开(公告)日：2016-12-27
申请号：US14613279
申请日：2015-02-03
Applicant: A9.com, Inc.
Inventor： Raghavan Manmatha , Mark A. Ruzon
CPC classification number: G06K9/344 , G06K9/18 , G06K9/325 , G06K9/342 , G06K9/346 , G06K9/38 , G06K9/40 , G06K9/62 , G06K9/6288 , G06K9/748 , G06K2209/01
Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.
-
4.发明申请公开(公告)号：US20150161480A1
公开(公告)日：2015-06-11
申请号：US14623367
申请日：2015-02-16
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Raghavan Manmatha , Donald Tanguay
IPC: G06K9/62
CPC classification number: G06K9/4671 , G06K9/4609 , G06K9/6212 , G06K9/6232 , G06T9/00
Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.
Abstract translation: 提供了一种用于编码图像的方法，系统和计算机程序产品。 需要表示的图像以高斯金字塔的形式表示，高斯金字塔是图像的尺度空间表示，并且包括几个金字塔图像。 识别金字塔图像中的特征点，并选择指定数量的特征点。 通过使用一组取向计算算法获得所选特征点的取向。 基于特征点的取向和金字塔图像的采样因子，在金字塔图像的特征点周围提取补丁。 通过用额外的像素填充金字塔图像来提取金字塔图像中的边界补丁。 定义提取的补丁的特征向量。 这些特征向量被归一化，使得特征向量中的分量小于阈值。
-
5.发明授权公开(公告)号：US09530076B2
公开(公告)日：2016-12-27
申请号：US14623367
申请日：2015-02-16
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Raghavan Manmatha , Donald Tanguay
CPC classification number: G06K9/4671 , G06K9/4609 , G06K9/6212 , G06K9/6232 , G06T9/00
Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.
Abstract translation: 提供了一种用于编码图像的方法，系统和计算机程序产品。 需要表示的图像以高斯金字塔的形式表示，高斯金字塔是图像的尺度空间表示，并且包括几个金字塔图像。 识别金字塔图像中的特征点，并选择指定数量的特征点。 通过使用一组取向计算算法获得所选特征点的取向。 基于特征点的取向和金字塔图像的采样因子，在金字塔图像的特征点周围提取补丁。 通过用额外的像素填充金字塔图像来提取金字塔图像中的边界补丁。 定义提取的补丁的特征向量。 这些特征向量被归一化，使得特征向量中的分量小于阈值。
-
Patent Agency Ranking
公开(公告)号：US20150154464A1
公开(公告)日：2015-06-04
申请号：US14613279
申请日：2015-02-03
Applicant: A9.com, Inc.
Inventor： Raghavan Manmatha , Mark A. Ruzon
CPC classification number: G06K9/344 , G06K9/18 , G06K9/325 , G06K9/342 , G06K9/346 , G06K9/38 , G06K9/40 , G06K9/62 , G06K9/6288 , G06K9/748 , G06K2209/01
Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.
Abstract translation: 本发明的各种实施例涉及用于检测和识别由相机和扫描仪捕获的图像中的文本的方法，系统和计算机程序产品。 首先，应用一系列图像处理技术来检测图像中的文本区域。 随后，检测到的文本区域通过不同的处理阶段，减少模糊和可变照明的负面影响。 这导致创建多个相同文本区域的图像。 这些多个版本中的一些被发送到字符识别系统。 然后，将发送到字符识别系统的图像的每个版本的结果文本合并为单个结果，其中单个结果是检测到的文本。
-
公开(公告)号：US20140226913A1
公开(公告)日：2014-08-14
申请号：US14259002
申请日：2014-04-22
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Raghavan Manmatha , Donald Tanguay
CPC classification number: G06K9/4671 , G06K9/4609 , G06K9/6212 , G06K9/6232 , G06T9/00
Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.
Abstract translation: 提供了一种用于编码图像的方法，系统和计算机程序产品。 需要表示的图像以高斯金字塔的形式表示，高斯金字塔是图像的尺度空间表示，并且包括几个金字塔图像。 识别金字塔图像中的特征点，并选择指定数量的特征点。 通过使用一组取向计算算法获得所选特征点的取向。 基于特征点的取向和金字塔图像的采样因子，在金字塔图像的特征点周围提取补丁。 通过用额外的像素填充金字塔图像来提取金字塔图像中的边界补丁。 定义提取的补丁的特征向量。 这些特征向量被归一化，使得特征向量中的分量小于阈值。
-
8.发明申请公开(公告)号：US20140086503A1
公开(公告)日：2014-03-27
申请号：US13761006
申请日：2013-02-06
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Raghavan Manmatha , Donald Tanguay
IPC: G06T9/00
CPC classification number: G06K9/4671 , G06K9/4609 , G06K9/6212 , G06K9/6232 , G06T9/00
Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.
Abstract translation: 提供了一种用于编码图像的方法，系统和计算机程序产品。 需要表示的图像以高斯金字塔的形式表示，高斯金字塔是图像的尺度空间表示，并且包括几个金字塔图像。 识别金字塔图像中的特征点，并选择指定数量的特征点。 通过使用一组取向计算算法获得所选特征点的取向。 基于特征点的取向和金字塔图像的采样因子，在金字塔图像的特征点周围提取补丁。 通过用额外的像素填充金字塔图像来提取金字塔图像中的边界补丁。 定义提取的补丁的特征向量。 这些特征向量被归一化，使得特征向量中的分量小于阈值。
-
公开(公告)号：US20170103282A1
公开(公告)日：2017-04-13
申请号：US15387314
申请日：2016-12-21
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Raghavan Manmatha , Donald Ranguay
CPC classification number: G06K9/4671 , G06K9/4609 , G06K9/6212 , G06K9/6232 , G06T9/00
Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.
-
公开(公告)号：US09542765B2
公开(公告)日：2017-01-10
申请号：US14673460
申请日：2015-03-30
Applicant: A9.com, Inc.
Inventor： Mark A. Ruzon , Dmitriy Shirchenko
CPC classification number: G06T11/60 , G06T7/60 , G06T7/68 , G06T7/73 , G06T7/90 , G06T2207/10024 , G06T2207/20221 , G09G5/377
Abstract: A method, system and computer program product for virtually placing an object on an image of a human appendage is provided. First, image boundaries are detected in the image of the appendage and converted into a set of line segments. A pair of line segments is evaluated according to a function that combines subscores of the pair of line segments to produce a score. The subscores of the line segments are computed based on various properties such as orientation difference, extent, proximity to the center of the image, bilateral symmetry, and the number of skin-colored pixels. A pair of line segments with the highest score is chosen as the appendage boundaries and is used to determine the position, orientation, and extent of the object. The image of the object is then transformed according to the determined parameters and combined with the image of the appendage to produce the desired result.
Abstract translation: 提供了一种用于将物体虚拟地放置在人类附属物的图像上的方法，系统和计算机程序产品。 首先，在附件的图像中检测图像边界并将其转换成一组线段。 根据组合一对线段的分数以产生分数的函数来评估一对线段。 线段的分数是基于各种属性来计算的，例如取向差异，程度，图像中心的接近度，双边对称性和皮肤色素数量。 选择具有最高分数的一对线段作为附加边界，并用于确定对象的位置，方向和范围。 然后根据确定的参数对对象的图像进行变换，并与附件的图像组合以产生期望的结果。
-
-
-
-
-
-
-
-
-
Search Results
15
records
(took 0.017 seconds)
