专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11164037B2 Object instance ambiguity resolution 有权
公开(公告)号：US11164037B2
公开(公告)日：2021-11-02
申请号：US16051689
申请日：2018-08-01
申请人： International Business Machines Corporation
发明人： Mattias Marder , Yochay Tzur
IPC分类号： G06K9/62 , G06K9/00 , G06T17/00 , G06T7/70 , G06F16/583 , G06F16/58
摘要： A system and method for resolving an ambiguity between similar objects in an image is disclosed. A three dimensional representation of a room is generated, and objects in the room are identified from an image of the room are identified. A determination is made that at least two objects are visually similar, and a position of the two objects is ambiguous. At least one question based on the determined ambiguity is programmatically generated based on information known about the room, and is phrased such that the ambiguity can be resolved by an answer to the question. Based on the answer received one of the objects is selected. At least one property of the selected object is modified based upon the selection of one of the at least two objects.

2. 发明授权

US10395143B2 Systems and methods for identifying a target object in an image 有权
公开(公告)号：US10395143B2
公开(公告)日：2019-08-27
申请号：US16199270
申请日：2018-11-26
申请人： International Business Machines Corporation
发明人： Sivan Harary , Leonid Karlinsky , Mattias Marder , Joseph Shtok , Asaf Tzadok
IPC分类号： G06F16/51 , G06F16/58 , G06F16/583 , G06K9/46 , G06K9/62 , G06N20/00 , G06N5/04
摘要： There is provided a method of identifying objects in an image, comprising: extracting query descriptors from the image, comparing each query descriptor with training descriptors for identifying matching training descriptors, each training descriptor is associated with a reference object identifier and with relative location data (distance and direction from a center point of a reference object indicated by the reference object identifier), computing object-regions of the digital image by clustering the query descriptors having common center points defined by the matching training descriptors, each object-region approximately bounding one target object and associated with a center point and a scale relative to a reference object size, wherein the object-regions are computed independently of the identifier of the reference object associated with the object-regions, wherein members of each cluster point toward a common center point, and classifying the target object of each object-region according to the reference object identifier of the cluster.

3. 发明申请

US20190108420A1 Systems and methods for identifying a target object in an image 审中-公开
公开(公告)号：US20190108420A1
公开(公告)日：2019-04-11
申请号：US16199270
申请日：2018-11-26
申请人： International Business Machines Corporation
发明人： Sivan Harary , Leonid Karlinsky , Mattias Marder , Joseph Shtok , Asaf Tzadok
IPC分类号： G06K9/62 , G06N5/04 , G06N99/00 , G06F17/30 , G06K9/46
CPC分类号： G06K9/6267 , G06F16/51 , G06F16/5838 , G06F16/5866 , G06K9/00624 , G06K9/00691 , G06K9/4604 , G06K9/4628 , G06K9/6274 , G06K9/6276 , G06K9/6296 , G06K2209/25 , G06N3/0454 , G06N3/08 , G06N5/046 , G06N7/005 , G06N20/00
摘要： There is provided a method of identifying objects in an image, comprising: extracting query descriptors from the image, comparing each query descriptor with training descriptors for identifying matching training descriptors, each training descriptor is associated with a reference object identifier and with relative location data (distance and direction from a center point of a reference object indicated by the reference object identifier), computing object-regions of the digital image by clustering the query descriptors having common center points defined by the matching training descriptors, each object-region approximately bounding one target object and associated with a center point and a scale relative to a reference object size, wherein the object-regions are computed independently of the identifier of the reference object associated with the object-regions, wherein members of each cluster point toward a common center point, and classifying the target object of each object-region according to the reference object identifier of the cluster.

4. 发明申请

US20170323149A1 ROTATION INVARIANT OBJECT DETECTION 审中-公开
公开(公告)号：US20170323149A1
公开(公告)日：2017-11-09
申请号：US15146905
申请日：2016-05-05
申请人： International Business Machines Corporation
发明人： Sivan Harary , Mattias Marder
IPC分类号： G06K9/00 , G06K9/62 , G06T3/00
CPC分类号： G06K9/4671 , G06K9/6211 , G06K9/66 , G06K2009/6213 , G06K2209/29 , G06T7/579 , G06T7/74
摘要： A method, including receiving a two-dimensional (2D) image of a three-dimensional (3D) object recorded at a first angle of rotation of the object, and identifying, in the 2D image, a set of image descriptors, each of the image descriptors including an image keypoint and one or more image features. The set of image descriptors are compared against sets of template descriptors for respective previously captured 2D images, each of the template descriptors comprising a template keypoint and one or more template features. Using a threshold, a given set of template descriptors matching the set of image descriptors are identified, the given set of template descriptors corresponding to a given previously captured 2D image of the 3D object recorded at a second angle of rotation of the object. Any of the image descriptors not in the given set of the template descriptors are added to the given set of template descriptors.

5. 发明授权

US09773472B2 Text extraction from graphical user interface content 有权
公开(公告)号：US09773472B2
公开(公告)日：2017-09-26
申请号：US15226928
申请日：2016-08-03
申请人： International Business Machines Corporation
发明人： Amir Geva , Mattias Marder
IPC分类号： H04N1/40 , G09G5/02 , G06K9/00 , G06K9/34
CPC分类号： G09G5/02 , G06K9/00456 , G06K9/342 , G06K2209/03 , H04N1/40012 , H04N1/40062
摘要： Systems and methods for extracting text from images rendered on a display screen, the method comprising capturing a color image rendered on a display screen; and transforming the color image to binary color image, preserving text-like graphic components and filtering out non-text-like graphical components. The transforming comprises scanning one or more areas of the color image; and detecting continuous bi-tonal regions in the scanned one or more areas, wherein the continuous bi-tonal regions have large variances.

6. 发明授权

US09536144B2 Automatic image classification 有权
标题翻译：自动图像分类
公开(公告)号：US09536144B2
公开(公告)日：2017-01-03
申请号：US14582216
申请日：2014-12-24
申请人： International Business Machines Corporation
发明人： Sharon Alpert , Mattias Marder
IPC分类号： G06K9/36 , G06K9/00 , G06K9/62
CPC分类号： G06K9/0055 , G06K9/4676 , G06K9/6228 , G06K9/6276 , G06K9/628 , G06K2009/4666 , G06K2209/25
摘要： A method, system and product for image classification. The method comprising obtaining a set of encoding functions and signature values which corresponds to a set of class images, wherein each pair of an encoding function and a signature value corresponds to a class image of the set of class images, wherein the signature value is a value produced by applying the encoding function on the class image; obtaining an image to be classified to a class associated with a class image of the set of class images; with respect to each class image of the set of class images: determining a transformation from the image to the class image; and applying the encoding function using the transformation on the image to produce a value; and automatically determining a class to which the image is classified based on the values and the signature values.
摘要翻译：一种用于图像分类的方法，系统和产品。该方法包括获得对应于一组类图像的一组编码函数和签名值，其中每对编码功能和签名值对应于该类图像集合的类图像，其中该签名值为通过对类图像应用编码函数产生的值; 获得要分类到与所述一组类图像的类图像相关联的类别的图像; 关于该类图像集合的每个类图像：确定从图像到类图像的变换; 以及使用所述图像上的变换来应用编码函数以产生一个值; 并且基于所述值和所述签名值自动确定所述图像被分类的类。

7. 发明申请

US20150070392A1 AERIAL VIDEO ANNOTATION 有权
公开(公告)号：US20150070392A1
公开(公告)日：2015-03-12
申请号：US14020911
申请日：2013-09-09
申请人： International Business Machines Corporation
发明人： Ophir Azulai , Udi Barzelay , Mattias Marder , Oded Margalit , Dror Porat
IPC分类号： G06T7/00 , G06T17/05
CPC分类号： G06T17/05 , G06T19/00 , G06T2219/004
摘要： A method comprising using at least one hardware processor for: receiving an aerially-captured video and metadata associated with the video; receiving deviation data indicative of an amount of inaccuracy in the metadata; and overlaying, on the video, a geographic annotation descriptive of an object of interest having known geographic coordinates, wherein the geographic annotation is of a size and a shape representative of the amount of inaccuracy.
摘要翻译：一种方法，包括使用至少一个硬件处理器，用于：接收空中捕获的视频和与所述视频相关联的元数据; 接收表示所述元数据中的不准确度的偏差数据; 以及在所述视频上覆盖描述具有已知地理坐标的感兴趣对象的地理注释，其中所述地理注释具有代表不准确度量的大小和形状。

8. 发明授权

US10902264B2 Automatic generation of secondary class annotations 有权
公开(公告)号：US10902264B2
公开(公告)日：2021-01-26
申请号：US16199190
申请日：2018-11-25
申请人： International Business Machines Corporation
发明人： Mattias Marder
IPC分类号： G06K9/00 , G06N7/00 , G06K9/32 , G06K9/62
摘要： A method, an apparatus and a program for automatic generation of secondary class annotations. The method comprises obtaining a plurality of images of an environment, each of which comprising objects in the environment. Some of the objects are annotated, while other objects are not. The method comprises aligning the plurality of images to a common coordinates system and computing a plurality of weighted images by adding weights to regions in the plurality of images that are associated with annotated objects to reduce significance of such regions. The method further comprises generating, based on the plurality of weighted images, a background model of the environment by determining for each region in the common coordinates system a statistical metric representing a visual feature of a background of the environment. The background model is then utilized to identify the non-annotated objects and adding an annotation for each identified object.

9. 发明授权

US10832096B2 Representative-based metric learning for classification and few-shot object detection 有权
公开(公告)号：US10832096B2
公开(公告)日：2020-11-10
申请号：US16240927
申请日：2019-01-07
申请人： International Business Machines Corporation
发明人： Leonid Karlinsky , Eliyahu Schwartz , Joseph Shtok , Mattias Marder , Sivan Harary
IPC分类号： G06K9/00 , G06K9/62 , G06K9/32 , G06N3/04
摘要： A method can include learning a common embedding space and a set of parameters for each one of a plurality of sets of mixture models, wherein one mixture model is associated with one class of objects within a set of object categories. The method can also include adding new mixture models to the set of mixture models to support novel categories based on a set of example embedding vectors computed for each one of the novel categories. Additionally, the method includes detecting in images a plurality of boxes with associated labels and corresponding confidence scores, wherein the boxes correspond to image regions comprising objects of both known categories and the novel categories. Furthermore, the method includes, given a query image, executing an instruction based on the common embedding space and the set of mixture models, the instruction comprising identifying objects from both categories in the query image.

10. 发明申请

US20200175332A1 OUT-OF-SAMPLE GENERATING FEW-SHOT CLASSIFICATION NETWORKS 审中-公开
公开(公告)号：US20200175332A1
公开(公告)日：2020-06-04
申请号：US16206528
申请日：2018-11-30
申请人： International Business Machines Corporation
发明人： Leonid Karlinsky , Mattias Marder , Eliyahu Schwartz , Joseph Shtok , Sivan Harary
IPC分类号： G06K9/62
摘要： Embodiments of the present disclosure include training a model using a plurality of pairs of feature vectors related to a first class. Embodiments include providing a sample feature vector related to a second class as an input to the model. Embodiments include receiving at least one synthesized feature vector as an output from the model. Embodiments include training a classifier to recognize the second class using a training data set comprising the sample feature vector related to the second class and the at least one synthesized feature vector. Embodiments include providing a query feature vector as an input to the classifier. Embodiments include receiving output from the classifier that identifies the query feature vector as being related to the second class, wherein the output is used to perform an action.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式