公开(公告)号：US20180357512A1

公开(公告)日：2018-12-13

申请号：US16026015

申请日：2018-07-02

Applicant: Ping Zhang

Inventor： Ping Zhang ,  Kuldeep Kumar

IPC: G06K9/62

CPC classification number: G06K9/6229 ,  G06K9/6292 ,  G06K2209/05

Abstract: A method and system for classifying tissue suspected of being abnormal as being malignant or benign. The method includes generating a set of selection features, performing statistical applications to generate additional selection features, generating a feature vector for the abnormal tissue, feeding the feature vector into a neural network, and obtaining a result from the neural network as to whether the abnormal tissue is malignant or benign. The method and system may be used for determining the presence of cancers such as breast cancer.

公开(公告)号：US20180322369A1

公开(公告)日：2018-11-08

申请号：US15973184

申请日：2018-05-07

Applicant: GoPro, Inc.

Inventor： Balineedu Chowdary Adsumilli ,  Ryan Lustig

IPC: G06K9/62 ,  G06N99/00 ,  G06N3/12 ,  G06K9/00

CPC classification number: G06K9/6262 ,  G06K9/00228 ,  G06K9/00744 ,  G06K9/6227 ,  G06K9/6229 ,  G06K9/6256 ,  G06N3/126 ,  G06N7/005 ,  G06N20/00

Abstract: An algorithm for performing an image or video processing task is generated that may be used to combine a plurality of different independent solutions to the image or video processing task in an optimized manner. A plurality of base algorithms may be applied to a training set of images or video and a first generation of different combining algorithms may be applied to combine the respective solutions from each of the respective base algorithms into respective combined solutions. The respective combined solutions may be evaluated to generate respective fitness scores representing measures of how well the plurality of different combining algorithms each perform the image or video processing task. The algorithms may be iteratively updated to generate an optimized combining algorithm that may be applied to an input image or video.

公开(公告)号：US09818048B2

公开(公告)日：2017-11-14

申请号：US14967876

申请日：2015-12-14

Applicant: eBay Inc.

Inventor： M. Hadi Kiapour ,  Wei Di ,  Vignesh Jagadeesh ,  Robinson Piramuthu

IPC: G06K9/00 ,  G06K9/62 ,  G06Q30/00 ,  G06K9/32 ,  G06K9/68 ,  G06K9/46

CPC classification number: G06K9/6276 ,  G06K9/00979 ,  G06K9/3216 ,  G06K9/3241 ,  G06K9/4628 ,  G06K9/6229 ,  G06K9/6256 ,  G06K9/6857 ,  G06Q30/00

Abstract: An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

公开(公告)号：US20170323442A1

公开(公告)日：2017-11-09

申请号：US15654769

申请日：2017-07-20

Applicant: Siemens Healthcare GmbH

Inventor： Michael SUEHLING

IPC: G06T7/00 ,  A61B6/00 ,  G06F19/00 ,  G06N3/00 ,  G06K9/62 ,  A61B6/03

CPC classification number: G06T7/0012 ,  A61B6/032 ,  A61B6/566 ,  G06F19/321 ,  G06F19/3418 ,  G06K9/6229 ,  G06N3/006 ,  G06N5/022 ,  G06N5/046 ,  G06N20/00 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10132 ,  G16H50/50

Abstract: A method for supporting a reporting physician in the evaluation of an image data set of a patient recorded with an image recording system. In an embodiment, the image data set is automatically processed by at least one preprocessing algorithm for display to the reporting physician. In an embodiment, the at least one preprocessing algorithm and/or at least one preprocessing parameter parameterizing the at least one preprocessing algorithm are automatically selected by a selection algorithm of artificial intelligence as a function of at least one item of recording information describing the recording and/or the recording area of the image data set and/or of at least one item of additional information concerning a previous examination of the patient.

公开(公告)号：US08694447B2

公开(公告)日：2014-04-08

申请号：US12954145

申请日：2010-11-24

Applicant: Yoshiyuki Kobayashi

Inventor： Yoshiyuki Kobayashi

IPC: G06F15/18

CPC classification number: G06T5/002 ,  G06K9/6229 ,  G06T2207/20081 ,  G10H2210/036

Abstract: An information processing apparatus is disclosed. The apparatus may include a processing method preparation unit for generating a first processing method. The apparatus may include an evaluator generation unit for generating an evaluator based on a genetic algorithm, using one or more input data sets, each of which may include data and a corresponding evaluation value. The apparatus may include an evaluation unit for calculating, using the evaluator, a first evaluation value using first output data obtained by processing the data using the first processing method. The apparatus may include a processing method update unit for generating a second processing method such that a second evaluation value calculated by the evaluator, using second output data obtained by processing the data using the second processing method, is higher than the first evaluation value. The apparatus may include an output unit that outputs the second output data and the second processing method.

Abstract translation: 公开了一种信息处理装置。 该装置可以包括用于产生第一处理方法的处理方法准备单元。 该装置可以包括评估器生成单元，用于使用一个或多个输入数据集，基于遗传算法生成评估者，每个输入数据集可以包括数据和对应的评估值。 该装置可以包括评估单元，用于使用使用第一处理方法处理数据而获得的第一输​​出数据来使用评估器计算第一评估值。 该装置可以包括处理方法更新单元，用于生成第二处理方法，使得使用第二处理方法处理数据而获得的使用第二输出数据的由评估者计算的第二评估值高于第一评估值。 该装置可以包括输出第二输出数据和第二处理方法的输出单元。

公开(公告)号：US20130311410A1

公开(公告)日：2013-11-21

申请号：US13923999

申请日：2013-06-21

Applicant: Sony Corporation

Inventor： Yoshiyuki KOBAYASHI

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06F17/30256 ,  G06F17/30743 ,  G06K9/6229

Abstract: An information processing apparatus for generating a similarity determination algorithm determining a similarity between a pair of data. The apparatus includes: a feature-quantity-extraction expression list generation mechanism generating a feature quantity-extraction expression list including a plurality of feature-quantity-extraction expressions including a plurality of operators by updating the feature-quantity extraction expression list of a preceding generation; a calculation mechanism inputting first and second data given as teacher data into each of the feature-quantity-extraction expressions in the feature-quantity-extraction expression list to calculate a feature quantity corresponding to each of the first and the second data; an evaluation-value calculation mechanism calculating the evaluation value of each of the feature-quantity-extraction expressions using the calculated feature quantities and a similarity between the first and the second data; and a similarity-calculation expression estimation mechanism estimating a similarity calculation expression for calculating a similarity between the first and the second data.

Abstract translation: 一种用于生成确定一对数据之间的相似度的相似度确定算法的信息处理装置。 该装置包括：特征量提取表达式列表生成机构，通过更新前一代的特征量提取表达列表，生成包括多个特征量提取表达式的特征量提取表达式列表，该特征量提取表达式包括多个运算符 ; 输入作为教师数据给出的第一和第二数据的计算机构，输入到特征量提取表达式列表中的每个特征量提取表达式，以计算与第一和第二数据中的每一个对应的特征量; 评估值计算机构，使用计算出的特征量和第一和第二数据之间的相似度来计算每个特征量提取表达式的评估值; 以及估计用于计算第一和第二数据之间的相似度的相似度计算表达式的相似度计算表达式估计机构。

公开(公告)号：US08195591B1

公开(公告)日：2012-06-05

申请号：US12788229

申请日：2010-05-26

Applicant: Yuri Owechko

Inventor： Yuri Owechko

IPC: G06F17/00 ,  G06N5/00

CPC classification number: G06K9/00369 ,  G06K9/6229 ,  G06K9/6292

Abstract: Described is a signal processing system. The system comprises a signal processing module having signal processing parameters and being configured to receive a plurality of signals. The signal processing module uses the signal processing parameters to output a processed signal, as either a fused signal or a plurality of separate signals. A classification module is included to recognize information encoded in the processed signal to classify the information encoded in the process signal, with the classification having a confidence level. An optimization module is configured, in a feedback loop, to utilize the information encoded in the processed signal to adjust the signal processing parameters to optimize the confidence level of the classification, thereby optimizing an output of the signal processing module.

Abstract translation: 描述了一种信号处理系统。 该系统包括具有信号处理参数并被配置为接收多个信号的信号处理模块。 信号处理模块使用信号处理参数来输出经处理的信号，作为融合信号或多个单独的信号。 包括分类模块以识别经处理的信号中编码的信息，以对分类具有置信水平的过程信号中编码的信息进行分类。 在反馈环路中，优化模块被配置为利用经处理的信号中编码的信息来调整信号处理参数以优化分类的置信水平，从而优化信号处理模块的输出。

公开(公告)号：US08190539B2

公开(公告)日：2012-05-29

申请号：US12137071

申请日：2008-06-11

Applicant: Aaron Keith Baughman

Inventor： Aaron Keith Baughman

IPC: G06F15/18 ,  G06N3/00 ,  G06N3/12

CPC classification number: G06N3/126 ,  G06K9/00268 ,  G06K9/6229

Abstract: An evolutionary feature selection system and method that determines a feature space for a dataset. A system is disclosed that includes: a system for generating a plurality of chromosomes; an agglomerative K-means clustering system for clustering data into clusters, wherein each of the cluster spaces is associated with a different one of the chromosomes; a linear discriminant analysis system for scoring each of the cluster spaces; and an evolutionary mating system that genetically mutates and mates at least two of the chromosomes associated with the highest scoring cluster spaces, and generates a final chromosome. The final chromosome can thereafter be used to define a feature space in a matching system that attempts to match inputted biometric data with entries in a biometric dataset.

Abstract translation: 进化特征选择系统和方法，用于确定数据集的特征空间。 公开了一种系统，其包括：用于产生多个染色体的系统; 用于将数据聚类成簇的聚集K均值聚类系统，其中每个簇空间与不同的一个染色体相关联; 用于对每个聚类空间进行评分的线性判别分析系统; 和进化交配系统，遗传突变和交配与最高得分簇空间相关联的至少两个染色体，并产生最终染色体。 最后的染色体此后可用于在匹配系统中定义试图将输入的生物特征数据与生物特征数据集中的条目相匹配的特征空间。

公开(公告)号：US20110243450A1

公开(公告)日：2011-10-06

申请号：US12752960

申请日：2010-04-01

Applicant: Ce Liu

Inventor： Ce Liu

IPC: G06K9/46

CPC classification number: G06K9/6229 ,  G06K9/00577 ,  G06K9/4671 ,  G06K9/6297

Abstract: A method of operating a computer system to perform material recognition based on multiple features extracted from an image is described. A combination of low-level features extracted directly from the image and multiple novel mid-level features extracted from transformed versions of the image are selected and used to assign a material category to a single image. The novel mid-level features include non-reflectance based features such as the micro-texture features micro jet and micro-SIFT and the shape feature curvature, and reflectance-based features including edge slice and edge ribbon. An augmented Latent Dirichlet Allocation (LDA) model is provided as an exemplary Bayesian framework for selecting a subset of features useful for material recognition of objects in an image.

Abstract translation: 描述了基于从图像提取的多个特征来操作计算机系统以执行材料识别的方法。 选择直接从图像中提取的低级特征和从图像的变换版本提取的多个新颖的中级特征的组合，并用于将材料类别分配给单个图像。 新颖的中级特征包括基于非反射率的特征，例如微观纹理特征微射流和微SIFT以及形状特征曲率，以及基于反射率的特征，包括边缘切片和边缘带。 提供增强的潜在狄利克雷分配（LDA）模型作为示例性贝叶斯框架，用于选择对于图像中的对象的材料识别有用的特征的子集。

公开(公告)号：US20100318300A1

公开(公告)日：2010-12-16

申请号：US12782414

申请日：2010-05-18

Applicant: Manfred Hiebl

Inventor： Manfred Hiebl

IPC: G06F19/00

CPC classification number: G06K9/626 ,  G01S7/412 ,  G01S13/726 ,  G06K9/6229

Abstract: A method for recognizing an object that has a plurality of expressions of abstract object characteristics, and is associated with an object characteristic class of a hierarchical system of object characteristic classes stored in a first memory. The method includes i) observing at least one location at which the object is presumed to be present, using a plurality of sensors in a sensor population, each of said sensors responding to at least one object characteristic and accordingly emitting a sensor signal; ii) checking whether each of the emitted sensor signals exceeds a specified threshold value for the sensor signals, and accepting sensor signals which exceed the threshold value; iii) pairing combinations of the sensor characteristics, for the accepted sensor signals obtained in ii) to form identification characteristic pairs; iv) comparing the population of identification characteristic pairs obtained in iii) to the object characteristic classes stored in the first memory; and v) identifying the object, based on the object characteristic class, whose object characteristic pairs are identical to the identification characteristic pairs obtained in iii).

Abstract translation: 一种用于识别具有抽象对象特征的多个表达的对象的方法，并且与存储在第一存储器中的对象特征类的分层系统的对象特征类相关联。 该方法包括：i）使用传感器群体中的多个传感器来观察至少一个假定存在对象的位置，每个所述传感器响应于至少一个对象特征并因此发射传感器信号; ii）检查每个发射的传感器信号是否超过传感器信号的指定阈值，并且接受超过阈值的传感器信号; iii）对于在ii）中获得的所接受的传感器信号，对传感器特性的组合进行配对以形成识别特征对; iv）将在iii）中获得的识别特征对的总体与存储在第一存储器中的对象特征类别进行比较; 以及v）基于对象特征等级来识别对象，其对象特征对与在iii）中获得的识别特征对相同。