-
11.发明授权公开(公告)号：US08705848B2
公开(公告)日：2014-04-22
申请号：US13761006
申请日：2013-02-06
Applicant: A9.com, Inc.
Inventor： Mark Andrew 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。
-
12.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。
-
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。
-
Patent Agency Ranking
15.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：US09892344B1
公开(公告)日：2018-02-13
申请号：US14954646
申请日：2015-11-30
Applicant: A9.com, Inc.
Inventor： Son Dinh Tran , Raghavan Manmatha
CPC classification number: G06K9/66 , G06K9/6256 , G06K9/6267 , G06N3/08
Abstract: Tasks such as object classification from image data can take advantage of a deep learning process using convolutional neural networks. These networks can include a convolutional layer followed by an activation layer, or activation unit, among other potential layers. Improved accuracy can be obtained by using a generalized linear unit (GLU) as an activation unit in such a network, where a GLU is linear for both positive and negative inputs, and is defined by a positive slope, a negative slope, and a bias. These parameters can be learned for each channel or a block of channels, and stacking those types of activation units can further improve accuracy.
-
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.
-
公开(公告)号：US20150213061A1
公开(公告)日：2015-07-30
申请号：US14605669
申请日：2015-01-26
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Sunil Ramesh , Max Delgadillo , Raghavan Manmatha
IPC: G06F17/30
CPC classification number: G06F17/30256 , G06F17/30247 , G06F17/30259 , G06F17/30542 , G06F17/30867 , G06K9/46 , G06K9/6203
Abstract: Systems and approaches for searching a content collection corresponding to query content are provided. In particular, false positive match rates between the query content and the content collection may be reduced with a minimum content region test and/or a minimum features per scale test. For example, by correlating content descriptors of a content piece in the content collection with query descriptors of the query content, the content piece can be determined to match the query content when a particular region of the content piece and/or a particular region of a query descriptor have a proportionate size meeting or exceeding a specified minimum. Alternatively, or in addition, the false positive match rate between query content and a content piece can be reduced by comparing content descriptors and query descriptors of features at a plurality of scales. A content piece can be determined to match the query content according to descriptor proportion quotas for the plurality of scales.
Abstract translation: 提供了用于搜索与查询内容相对应的内容集合的系统和方法。 特别地，可以通过最小内容区域测试和/或每个比例测试的最小特征来减少查询内容和内容收集之间的假阳性匹配率。 例如，通过将内容集合中的内容片段的内容描述符与查询内容的查询描述符相关联，可以确定内容片段与内容片段的特定区域和/或内容片段的特定区域 查询描述符的比例大小满足或超过规定的最小值。 或者或另外，通过比较多个尺度的特征的内容描述符和查询描述符，可以减少查询内容与内容片段之间的假正匹配率。 可以根据多个尺度的描述符比例配额来确定内容片段以匹配查询内容。
-
19.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。
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.022 seconds)
