公开(公告)号：US08699828B2

公开(公告)日：2014-04-15

申请号：US14041693

申请日：2013-09-30

Applicant: A9.com, Inc.

Inventor： Mark Andrew Ruzon ,  Donald Tanguay

IPC: G06K9/60

CPC classification number: G06K9/6211 ,  G06F17/30247 ,  G06T7/33

Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.

Abstract translation: 提供了一种用于匹配图像的方法，系统和计算机程序产品。 要匹配的图像由特征点和与特征点相关联的特征向量和取向表示。 首先，通过使用特征向量来确定推定的对应关系。 选择推定对应的子集，确定子集的拓扑等价性。 推定对应的拓扑等效子集用于建立运动估计模型。 对推定的对应和相应的运动估计变换进行取向一致性测试，以避免不可行的变换。 对满足定向一致性测试的匹配进行覆盖测试。 不覆盖其中一个图像的重要部分的候选匹配被拒绝。 在满足所有测试要求的多个图像的情况下，按照减少匹配的顺序提供最终匹配图像。

公开(公告)号：US08825612B1

公开(公告)日：2014-09-02

申请号：US13781550

申请日：2013-02-28

Applicant: A9.com, Inc.

Inventor： Mark Andrew Ruzon ,  Keshav Menon ,  Gurumurthy D. Ramkumar ,  Donald Tanguay ,  Supratik Bhattacharyya ,  Gautam Bhargava

IPC: G06F17/00 ,  G06F17/30

CPC classification number: G06F17/30017 ,  G06F17/30247 ,  G06F17/30277

Abstract: The present invention relates to a method, system, and a computer program product for delivering content to a communication device, in response to an image sent by the communication device. The received image is matched with a plurality of images, and, when a match is found for the received image, content corresponding to the image is delivered to the communication device. The plurality of images is stored in an image database, and the corresponding content is stored in a content repository. The present invention enables a content provider to automatically update the image database and the content repository without any human intervention.

Abstract translation: 本发明涉及一种用于响应于由通信设备发送的图像将内容传送到通信设备的方法，系统和计算机程序产品。 所接收的图像与多个图像匹配，并且当对于接收到的图像找到匹配时，与图像相对应的内容被传送到通信装置。 多个图像被存储在图像数据库中，并且相应的内容被存储在内容存储库中。 本发明使得内容提供商能够在没有任何人为干预的情况下自动更新图像数据库和内容存储库。

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

IPC: G06K9/00 ,  G06K9/40 ,  G06K9/36

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：US08548279B1

公开(公告)日：2013-10-01

申请号：US13773451

申请日：2013-02-21

Applicant: A9.com, Inc.

Inventor： Mark Andrew Ruzon ,  Donald Tanguay

IPC: G06K9/60

CPC classification number: G06K9/6211 ,  G06F17/30247 ,  G06T7/33

Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.

Abstract translation: 提供了一种用于匹配图像的方法，系统和计算机程序产品。 要匹配的图像由特征点和与特征点相关联的特征向量和取向表示。 首先，通过使用特征向量来确定推定的对应关系。 选择推定对应的子集，确定子集的拓扑等价性。 推定对应的拓扑等效子集用于建立运动估计模型。 对推定的对应和相应的运动估计变换进行取向一致性测试，以避免不可行的变换。 对满足定向一致性测试的匹配进行覆盖测试。 不覆盖其中一个图像的重要部分的候选匹配被拒绝。 在满足所有测试要求的多个图像的情况下，按照减少匹配的顺序提供最终匹配图像。