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

US09189841B2 Method of checking the appearance of the surface of a tyre 有权
标题翻译：检查轮胎表面外观的方法
公开(公告)号：US09189841B2
公开(公告)日：2015-11-17
申请号：US14348156
申请日：2012-09-27
申请人： Guillaume Noyel , Dominique Jeulin , Estelle Parra-Denis , Michel Bilodeau
发明人： Guillaume Noyel , Dominique Jeulin , Estelle Parra-Denis , Michel Bilodeau
IPC分类号： G06T7/00
CPC分类号： G06T7/0004 , G06K9/6234 , G06K9/6247 , G06K9/6269 , G06K2209/19 , G06T7/001 , G06T2207/20021 , G06T7/004 , G06T7/0048
摘要： A tire appearance detection method includes: capturing an original grey-level image of an inner surface of a tire, and transforming the original image into an orthonormal space with an x-axis (OX) representing a circumferential direction and with a y-axis (OY) representing a radial direction; applying a series of filters to the original image, to obtain a multivariate image; splitting the multivariate image according to a predefined tiling in axial and circumferential directions, to obtain multivariate sub-images of the inner surface of the tire; transforming each of the multivariate sub-images into one-dimensional vectors using selected descriptors, to obtain a simplified multivariate image of the inner surface of the tire; transforming the simplified multivariate image into a common reduced factorial space; and locating sub-images of the inner surface of the tire containing an anomaly using a classifier suitable for identifying an area of the common reduced factorial space containing an anomaly.
摘要翻译：轮胎外观检测方法包括：捕获轮胎的内表面的原始灰度图像，并且将原始图像转换成具有代表圆周方向的x轴（OX）和具有y轴的正交空间（OX） OY）表示径向; 对原始图像应用一系列滤波器，获得多变量图像; 根据轴向和圆周方向上的预定平铺分割多变量图像，以获得轮胎内表面的多变量子图像; 使用所选择的描述符将每个多变量子图像变换为一维向量，以获得轮胎内表面的简化多变量图像; 将简化的多变量图像转换为共同的缩减因子空间; 以及使用适合于识别包含异常的公共缩减阶乘空间的区域的分类器来定位包含异常的轮胎的内表面的子图像。

2. 发明申请

US20150206311A1 METHOD OF OBJECT ORIENTATION DETECTION 有权
标题翻译：对象方位检测方法
公开(公告)号：US20150206311A1
公开(公告)日：2015-07-23
申请号：US14601095
申请日：2015-01-20
申请人： Apical Ltd.
发明人： Ilya ROMANENKO
IPC分类号： G06T7/00 , G06K9/62
CPC分类号： G06T7/0048 , G06K9/00248 , G06K9/4614 , G06K9/6276 , G06T7/77 , G06T2207/20081 , G06T2207/30201
摘要： A method of determining an orientation of an object within an image. The method determines the responses of at least two classifiers in at least one region of the image corresponding to the object. The classifiers have been trained to identify a given object in different specific orientations. The orientation of the object is determined as an average of the specific orientations, weighted by the responses of their respective classifiers.
摘要翻译：确定图像内的对象的取向的方法。该方法确定在与对象相对应的图像的至少一个区域中的至少两个分类器的响应。已经对分类器进行了训练，以便以不同的特定方向识别给定的对象。对象的方向被确定为由它们各自的分类器的响应加权的特定取向的平均值。

3. 发明申请

US20140086484A1 IMAGE PROCESS WITH SPATIAL PERIODICITY MEASURE 有权
标题翻译：具有空间周期性度量的图像过程
公开(公告)号：US20140086484A1
公开(公告)日：2014-03-27
申请号：US14036054
申请日：2013-09-25
申请人： Snell Limited
发明人： Michael James Knee
IPC分类号： G06K9/62
CPC分类号： G06T7/0048 , G06K9/6212 , G06T5/40 , G06T7/42 , G06T7/44 , G06T2207/10004 , H04N19/00 , H04N19/521 , H04N19/85
摘要： An image manipulation process is controlled by a spatial periodicity measure formed for an image or an image block by measuring the sparseness of the two-dimensional spatial frequency spectrum of the image on a scale of zero to unity in which a two-dimensional spatial frequency spectrum having all equal values has a sparseness of zero and in which a two-dimensional spatial frequency spectrum having only one non-zero value has a sparseness of unity. Sparseness may be measured by allocating values of the spectrum to frequency bins and counting the number of bins that contain non-zero values; comparing values of the spectrum with a threshold and counting the number of values that exceed the threshold; or forming a function of the mean-square value and the mean value of the spectrum values.
摘要翻译：通过对图像或图像块形成的空间周期性度量来控制图像处理过程，通过以二维空间频谱测量图像的二维空间频谱的稀疏度具有所有相等值的稀疏度为零，并且其中仅具有一个非零值的二维空间频谱具有一致的稀疏度。可以通过将频谱的值分配给频率仓并计数包含非零值的仓的数量来测量稀疏度; 将频谱的值与阈值进行比较，并对超过阈值的数值进行计数; 或形成均方值和频谱值的平均值的函数。

4. 发明授权

US6125198A Method of matching stereo images and method of measuring disparity between these items 有权
标题翻译：匹配立体图像的方法和测量这些项目之间的差异的方法
公开(公告)号：US6125198A
公开(公告)日：2000-09-26
申请号：US196329
申请日：1998-11-19
申请人： Katsumasa Onda
发明人： Katsumasa Onda
IPC分类号： H04N13/02 , G01C11/06 , G06T7/00 , H04N13/00 , G06K9/00
CPC分类号： G06T7/0075 , G01C11/06 , G06K9/20 , G06K9/32 , G06T7/0044 , G06T7/0048 , G06K2209/40 , G06T2207/10012 , H04N13/0239 , H04N2013/0081
摘要： In the image pickup phase (A), right and left images are taken in through two image-pickup devices (S101, S102). Then, in the next feature extraction phase (B), right and left images are respectively subjected to feature extraction (S103, S104). Thereafter, in the succeeding matching phase (C), the extracted features of right and left images are compared to check how they match with each other (step S105). More specifically, in the matching phase (C), a one-dimensional window is set, this one-dimensional window is shifted along the left image in accordance with a predetermined scanning rule so as to successively set overlapped one-dimensional windows, and a matching operation is performed by comparing the image features within one window and corresponding image features on the right image. Subsequently, in the disparity determination phase (D), the left image is dissected or divided into plural blocks each having a predetermined size, a histogram in each block is created from disparities obtained by the matching operation based on one-dimensional windows involving pixels of a concerned block, and a specific disparity just corresponding to the peak of thus obtained histogram is identified as a valid disparity representing the concerned block (S106).
摘要翻译：在图像拾取阶段（A）中，通过两个图像拾取装置拍摄右图像和左图像（S101，S102）。然后，在下一特征提取阶段（B）中，右图像和左图像分别进行特征提取（S103，S104）。此后，在后续的匹配阶段（C）中，将所提取的右图像和左图像的特征进行比较，以检查它们如何彼此匹配（步骤S105）。更具体地，在匹配阶段（C）中，设置一维窗口，该一维窗口根据预定的扫描规则沿着左图像移位，以便连续地设置重叠的一维窗口，并且通过比较一个窗口内的图像特征和右图像上的相应图像特征来执行匹配操作。随后，在视差确定阶段（D）中，将左图像解剖或分成具有预定大小的多个块，每个块中的直方图是通过基于通过匹配操作获得的差异创建的，相关块，并且与由此获得的直方图的峰值相对应的特定差异被识别为表示相关块的有效视差（S106）。

5. 发明授权

US4951201A Method of automatically determining imaged body posture in medical image display 失效
标题翻译：在医学图像显示中自动确定成像体姿势的方法
公开(公告)号：US4951201A
公开(公告)日：1990-08-21
申请号：US183809
申请日：1988-04-20
申请人： Hideya Takeo , Nobuyuki Tanaka , Nobuyoshi Nakajima
发明人： Hideya Takeo , Nobuyuki Tanaka , Nobuyoshi Nakajima
IPC分类号： G06T7/00
CPC分类号： G06T7/0048 , G06T7/0044 , G06T2207/30004 , Y10S250/909
摘要： A distribution of an image signal read from a stimulable phosphor sheet and bearing a transmitted radiation image of a human body is determined along a horizontal direction across the image. Signal values of the distribution along the direction are accumulated, and the rate of change of the accumulated values is determined to find the imaged posture of the image. Alternatively, the separation or the average value of the distribution is determined, or the pattern of the distribution is compared with a plurality of reference signal distribution patterns. The derivative of second order of a function approximated by the distribution pattern may be checked for its sign, or the distribution pattern may be checked to determine whether it is of a one-valley form or a two-valley form.
摘要翻译：沿着图像的水平方向确定从可刺激的磷光体片读取并承载人体的透射辐射图像的图像信号的分布。累积沿着方向的分布的信号值，并且确定累积值的变化率以找到图像的成像姿势。或者，确定分布的分离或平均值，或将分布的图案与多个参考信号分布模式进行比较。可以检查由分布模式近似的函数的二阶导数的符号，或者可以检查分布模式以确定它是单谷形还是双谷形。

6. 发明授权

US09330469B2 Systems and methods for boil detection 有权
标题翻译：锅炉检测系统和方法
公开(公告)号：US09330469B2
公开(公告)日：2016-05-03
申请号：US14247381
申请日：2014-04-08
申请人： General Electric Company
发明人： Li Guan
IPC分类号： G06K9/00 , G06T7/00 , G06T7/20
CPC分类号： G06T7/0048 , F24C7/083 , G06T7/277 , G06T2207/10016 , G06T2207/20081 , G06T2207/30128
摘要： Systems and methods for boil detection are provided. One example system includes a vision sensor positioned to collect imagery depicting the cooktop and one or more processors implementing instructions to perform operations. The operations include obtaining a first frame of imagery and a second frame of imagery from the vision sensor. The first frame of imagery and the second frame of imagery respectively depict the cooktop. The operations include identifying a plurality of motion vectors based on the first and second frames of imagery. The operations include generating a histogram describing a characteristic of the plurality of motion vectors. The operations include calculating a dissimilarity score. The dissimilarity score describes a difference between the histogram and a pre-learned histogram. The pre-learned histogram describes the characteristic for imagery depicting boiling liquid. The operations include determining whether a boiling event is occurring at the cooktop based at least in part on the dissimilarity score.
摘要翻译：提供了用于沸点检测的系统和方法。一个示例性系统包括视觉传感器，其被定位成收集描绘炉灶的图像和实现指令以执行操作的一个或多个处理器。操作包括从视觉传感器获得第一帧图像和第二帧图像。第一帧图像和第二帧图像分别描绘了炉灶。这些操作包括基于第一和第二帧图像识别多个运动矢量。这些操作包括生成描述多个运动矢量的特征的直方图。操作包括计算不相似性得分。不相似性分数描述直方图与预先学习的直方图之间的差异。预先学习的直方图描述了描绘沸腾液体的图像的特征。这些操作包括至少部分地基于不相似性得分确定在炉灶面上是否发生沸腾事件。

7. 发明授权

US09324152B2 Image processing of images that include marker images 有权
标题翻译：包括标记图像的图像的图像处理
公开(公告)号：US09324152B2
公开(公告)日：2016-04-26
申请号：US14851313
申请日：2015-09-11
申请人： Varian Medical Systems, Inc.
发明人： Hassan Mostafavi , Andrew Jeung
IPC分类号： G06K9/00 , G06T7/00 , G06T7/40 , G06T5/40 , A61B5/05
CPC分类号： G06T7/0048 , A61B6/52 , A61N5/1049 , G06T5/40 , G06T7/0012 , G06T7/194 , G06T7/44 , G06T7/77 , G06T7/90 , G06T2207/10116 , G06T2207/20021 , G06T2207/30061 , G06T2207/30096 , G06T2207/30204
摘要： A method, includes: obtaining an image, the image having marker images and a background image; identifying presence of an object in the background image using a processor; and providing a signal for stopping a procedure if the presence of the object is identified. An image processing apparatus, includes: a processor configured for: obtaining an image, the image having marker images and a background image; identifying presence of an object in the background image; and providing a signal for stopping a procedure if the presence of the object is identified. A computer product having a non-transitory medium storing instructions, an execution of which causes an image processing method to be performed, the method includes: obtaining an image, the image having marker images and a background image; identifying presence of an object in the background image; and providing a signal for stopping a procedure if the presence of the object is identified.
摘要翻译：一种方法，包括：获得图像，所述图像具有标记图像和背景图像; 使用处理器识别背景图像中的对象的存在; 以及如果识别出对象的存在，则提供用于停止过程的信号。一种图像处理装置，包括：处理器，被配置为：获得图像，所述图像具有标记图像和背景图像; 识别对象在背景图像中的存在; 以及如果识别出对象的存在，则提供用于停止过程的信号。一种计算机产品，具有存储指令的非暂时介质，其执行使得执行图像处理方法，所述方法包括：获得图像，所述图像具有标记图像和背景图像; 识别对象在背景图像中的存在; 以及如果识别出对象的存在，则提供用于停止过程的信号。

8. 发明授权

US08867802B2 Automatic organ localization 有权
标题翻译：自动器官定位
公开(公告)号：US08867802B2
公开(公告)日：2014-10-21
申请号：US13090108
申请日：2011-04-19
申请人： Antonio Criminisi , Jamie Daniel Joseph Shotton , Duncan Paul Robertson , Sayan D. Pathak , Steven James White , Khan Mohammed Siddiqui
发明人： Antonio Criminisi , Jamie Daniel Joseph Shotton , Duncan Paul Robertson , Sayan D. Pathak , Steven James White , Khan Mohammed Siddiqui
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06T7/0048 , G06K2209/051 , G06T7/77 , G06T2207/10072 , G06T2207/20076 , G06T2207/20081 , G06T2207/30004
摘要： Automatic organ localization is described. In an example, an organ in a medical image is localized using one or more trained regression trees. Each image element of the medical image is applied to the trained regression trees to compute probability distributions that relate to a distance from each image element to the organ. At least a subset of the probability distributions are selected and aggregated to calculate a localization estimate for the organ. In another example, the regression trees are trained using training images having a predefined organ location. At each node of the tree, test parameters are generated that determine which subsequent node each training image element is passed to. This is repeated until each image element reaches a leaf node of the tree. A probability distribution is generated and stored at each leaf node, based on the distance from the leaf node's image elements to the organ.
摘要翻译：描述自动器官定位。在一个示例中，使用一个或多个经过训练的回归树将医学图像中的器官定位。将医学图像的每个图像元素应用于经过训练的回归树，以计算与从每个图像元素到器官的距离相关的概率分布。选择和聚合概率分布的至少一个子集以计算器官的定位估计。在另一示例中，使用具有预定义的器官位置的训练图像来训练回归树。在树的每个节点，生成测试参数，确定每个训练图像元素传递到哪个后续节点。这是重复的，直到每个图像元素到达树的叶节点。基于从叶节点的图像元素到器官的距离，在每个叶节点处生成并存储概率分布。

9. 发明申请

US20140270365A1 IMAGE PROCESSING OF IMAGES THAT INCLUDE MARKER IMAGES 有权
标题翻译：包含标记图像的图像的图像处理
公开(公告)号：US20140270365A1
公开(公告)日：2014-09-18
申请号：US14040599
申请日：2013-09-27
申请人： Varian Medical Systems, Inc.
发明人： Hassan Mostafavi , Andrew Jeung
IPC分类号： A61N5/10 , A61B6/00 , G06T7/20
CPC分类号： G06T7/0048 , A61B6/52 , A61N5/1049 , G06T5/40 , G06T7/0012 , G06T7/194 , G06T7/44 , G06T7/77 , G06T7/90 , G06T2207/10116 , G06T2207/20021 , G06T2207/30061 , G06T2207/30096 , G06T2207/30204
摘要： An image processing method, includes: obtaining an image, the image having marker images and a background image; identifying presence of an object in the background image using a processor; and providing a signal for stopping a procedure if the presence of the object is identified. An image processing apparatus, includes: a processor configured for: obtaining an image, the image having marker images and a background image; identifying presence of an object in the background image; and providing a signal for stopping a procedure if the presence of the object is identified. A computer product having a non-transitory medium storing a set of instructions, an execution of which causes an image processing method to be performed, the method includes: obtaining an image, the image having marker images and a background image; identifying presence of an object in the background image; and providing a signal for stopping a procedure if the presence of the object is identified.
摘要翻译：一种图像处理方法，包括：获得图像，具有标记图像的图像和背景图像; 使用处理器识别背景图像中的对象的存在; 以及如果识别出对象的存在，则提供用于停止过程的信号。一种图像处理装置，包括：处理器，被配置为：获得图像，所述图像具有标记图像和背景图像; 识别对象在背景图像中的存在; 以及如果识别出对象的存在，则提供用于停止过程的信号。一种具有存储一组指令的非暂时介质的计算机产品，其执行使得执行图像处理方法，所述方法包括：获得图像，所述图像具有标记图像和背景图像; 识别对象在背景图像中的存在; 以及如果识别出对象的存在，则提供用于停止过程的信号。

10. 发明授权

US5418892A Subspace-based line detection 失效
标题翻译：基于子空间的线检测
公开(公告)号：US5418892A
公开(公告)日：1995-05-23
申请号：US3255
申请日：1993-01-12
申请人： Hamid K. Aghajan , Thomas Kailath
发明人： Hamid K. Aghajan , Thomas Kailath
IPC分类号： G01S3/74 , G06K9/46 , G06T5/00 , G06T7/00 , G06F15/00
CPC分类号： G06T7/0083 , G06K9/4633 , G06T7/0048 , G01S3/74 , G06T2207/20061 , G06T2207/30148 , G06T2207/30256
摘要： A new signal processing method solves the problem of fitting multiple lines in a two-dimensional image. The Subspace-Based Line Detection (SLIDE) algorithm formulates the multi-line fitting problem in a special parameter estimation framework such that a signal structure similar to the sensor array processing signal representation is obtained. Any spectral estimation method can then be exploited to obtain estimates of the line parameters. In particular, subspace-based algorithms of sensor array processing (e.g., the ESPRIT technique) can be used to produce closed-form and high resolution estimates for line parameters. The signal representation employed in this formulation can be generalized to handle both problems of line fitting (in which a set of binary-valued discrete pixels is given) and of straight edge detection (in which one starts with a grey-scale image).
摘要翻译：新的信号处理方法解决了在二维图像中拟合多条线的问题。基于子空间线检测（SLIDE）算法在特殊参数估计框架中形成多线拟合问题，从而获得与传感器阵列处理信号表示相似的信号结构。然后可以利用任何频谱估计方法来获得线路参数的估计。特别地，传感器阵列处理的基于子空间的算法（例如，ESPRIT技术）可以用于产生线性参数的闭合形式和高分辨率估计。在该公式中使用的信号表示可以被推广以处理线拟合（其中给出一组二进制值离散像素）和直边检测（其中以灰度图像开始）的两个问题。

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