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. 发明申请

WO2018117937A1 FINGERPRINT SENSING SYSTEM CONFIGURED TO DETERMINE IF A FINGER CONTACTS A FINGERPRINT SENSOR 审中-公开
公开(公告)号：WO2018117937A1
公开(公告)日：2018-06-28
申请号：PCT/SE2017/051220
申请日：2017-12-05
申请人： FINGERPRINT CARDS AB
发明人： HANSEN, Morten , WITH PEDERSEN, Morten
IPC分类号： G06K9/00
CPC分类号： G06K9/00899 , G06F21/32 , G06K9/00013 , G06K9/00087 , G06K9/00114 , G06K9/036 , G06K9/44 , G06K9/4604 , G06K9/4647 , G06K9/80
摘要： The invention relates to a method performed by a fingerprint sensing system (101) of determining if a finger contacts a fingerprint sensor (102) of the system, and a fingerprint sensing system (101) performing method. In a first aspect of the invention, a method performed by a fingerprint sensing system (101) is provided for determining if a finger contacts a fingerprint sensor (102) of the fingerprint sensing system (101). The method comprises capturing (S101) an image of an object contacting the fingerprint sensor (102), determining (S102) an intensity for a plurality of pixels of the captured image, estimating (S103) local curvatures of pixel intensity variation in the captured image, and determining (S104) from the estimated local curvatures if local pixel intensity variation is dominated by a single direction, in which case the object on the sensor (102) is considered to constitute a finger.

2. 发明申请

WO2017135697A1 A METHOD FOR CORRECTING DRIFT IN A DEVICE AND THE DEVICE 审中-公开
标题翻译：一种校正装置和装置中的漂移的方法
公开(公告)号：WO2017135697A1
公开(公告)日：2017-08-10
申请号：PCT/KR2017/001131
申请日：2017-02-02
申请人： SAMSUNG ELECTRONICS CO., LTD.
发明人： PERI, Christopher A.
IPC分类号： G02B27/00 , G06F3/01 , G02B27/02
CPC分类号： G06T7/73 , G06K9/00335 , G06K9/00671 , G06K9/036 , G06K9/6215 , G06T7/246
摘要： A method to correct for drift in an electronic device is described. The method comprises determining a first center pose of the electronic device; tracking, using a sensor in conjunction with computer vision operating on a processor, at least one key point within a scene when the first center pose is within a tolerance with respect to a reported center pose; determining a derived center poser based upon the first center pose and the at least one key point; disabling the sensor for a predetermined time; determining, after the predetermined time, whether a second center pose is within the tolerance with respect to the derived center pose; tracking, using the sensor, the at least one key point when the second center pose is within the tolerance with respect to the derived center pose; and adjusting the second center pose when there is a difference between the second center pose and the derived center pose.
摘要翻译：描述了校正电子设备中的漂移的方法。该方法包括确定电子设备的第一中心姿态; 使用传感器结合在处理器上操作的计算机视觉来跟踪当第一中心姿态相对于所报告的中心姿势处于容差内时场景内的至少一个关键点; 基于所述第一中心姿态和所述至少一个关键点确定派生的中心姿态; 使传感器停用预定时间; 在预定时间之后，确定第二中心姿态是否在相对于所导出的中心姿态的容差内; 当所述第二中心姿态相对于所述导出的中心姿态在所述容限内时，使用所述传感器跟踪所述至少一个关键点; 以及当第二中心姿态与派生的中心姿态之间存在差异时调整第二中心姿态。

3. 发明申请

WO2017123641A1 CHECK IMAGE CORRECTION MACROS 审中-公开
标题翻译：检查图像校正宏
公开(公告)号：WO2017123641A1
公开(公告)日：2017-07-20
申请号：PCT/US2017/013029
申请日：2017-01-11
申请人： DIGITAL CHECK CORPORATION
发明人： MALONEY, Rian , WEBER, Scott
IPC分类号： G06Q40/02 , G06Q40/00 , G06Q20/40
CPC分类号： G06K9/40 , G06K9/036 , G06Q20/0425 , G06T5/002 , G06T5/009 , G06T2207/20208 , G06T2207/30176
摘要： The present disclosure involves systems, software, and computer-implemented methods for applying correction macros to a clearing payment instrument image. An example method includes identifying a correction macro including one or more image processing actions to apply to a first clearing payment instrument image; associating the correction macro with a first attribute of the first clearing payment instrument image; and determining that the correction macro is to be applied to a second clearing payment instrument including a second attribute based on the second attribute matching the first attribute associated with the correction macro.
摘要翻译：本公开涉及用于将校正宏应用于结算支付工具图像的系统，软件和计算机实现的方法。示例方法包括：识别包括要应用于第一结算支付工具图像的一个或多个图像处理动作的修正宏; 将修正宏与第一结算支付工具图像的第一属性相关联; 以及基于与修正宏相关联的第一属性匹配的第二属性，确定修正宏将被应用于包括第二属性的第二结算支付工具。

4. 发明申请

WO2017053998A1 TECHNIQUES TO DETERMINE DISTINCTIVENESS OF A BIOMETRIC INPUT IN A BIOMETRIC SYSTEM 审中-公开
标题翻译：确定生物量系统中生物量输入的分离度的技术
公开(公告)号：WO2017053998A1
公开(公告)日：2017-03-30
申请号：PCT/US2016/053835
申请日：2016-09-26
申请人： INTEL CORPORATION
发明人： ANDERSON, Glen J. , DURHAM, Lenitra M.
IPC分类号： G06F21/32 , G06F21/45 , G06K9/00
CPC分类号： G06F21/32 , G06K9/00892 , G06K9/036 , G06N99/005
摘要： Various embodiments are generally directed to an apparatus, method and other techniques to receive a biometric input of a first input type, determine a distinctiveness value for the biometric input based on a comparison of an attributes score for the biometric input with an average of attributes scores for biometric inputs of the first input type from the plurality of biometric inputs, and determine an input type to use to perform an action based on the distinctiveness value.
摘要翻译：各种实施例通常涉及用于接收第一输入类型的生物特征输入的装置，方法和其它技术，基于生物特征输入的属性得分与属性得分的平均值的比较来确定生物特征输入的特征值用于来自所述多个生物测定输入的所述第一输入类型的生物特征输入，并且基于所述特征值确定用于执行动作的输入类型。

5. 发明申请

WO2017034784A1 DEFOCUS ESTIMATION FROM SINGLE IMAGE BASED ON LAPLACIAN OF GAUSSIAN APPROXIMATION 审中-公开
标题翻译：基于高斯大学拉普拉斯的单一图像的偏差估计
公开(公告)号：WO2017034784A1
公开(公告)日：2017-03-02
申请号：PCT/US2016/045841
申请日：2016-08-05
申请人： SONY CORPORATION , LI, Pingshan
发明人： LI, Pingshan , WEI, Jianing
IPC分类号： G06K9/36 , G06K9/40 , G06T5/00
CPC分类号： G06K9/6215 , G06K9/036 , G06T5/00 , G06T5/003 , G06T5/50 , G06T2207/30168 , H04N5/23212
摘要： A defocus estimation algorithm is described herein. The defocus estimation algorithm utilizes a single image. A Laplacian of Gaussian approximation is determined by computing a difference of Gaussian. Defocus blur is able to be estimated by computing a blur difference between two images using the difference of Gaussian.
摘要翻译：这里描述散焦估计算法。散焦估计算法利用单个图像。高斯近似的拉普拉斯算子通过计算高斯差来确定。散焦模糊能够通过使用高斯差计算两个图像之间的模糊差异来估计。

6. 发明申请

WO2017020045A1 SYSTEM AND METHODS FOR MALARIAL RETINOPATHY SCREENING 审中-公开
标题翻译：疟疾病毒筛查系统与方法
公开(公告)号：WO2017020045A1
公开(公告)日：2017-02-02
申请号：PCT/US2016/045051
申请日：2016-08-01
申请人： VISIONQUEST BIOMEDICAL LLC
发明人： JOSHI, Vinayak , SOLIZ, Peter , BARRIGA, Simon, E. , ZAMORA, Gilberto , AGURTO RIOS, Carla, P.
IPC分类号： A61B3/12 , A61B3/14 , A61B3/15 , G06K9/22 , G06K9/32
CPC分类号： A61B3/12 , A61B3/14 , A61B3/15 , G06K9/0061 , G06K9/036 , G06T7/0012 , G06T2207/10024 , G06T2207/10048 , G06T2207/30041 , G06T2207/30168
摘要： Systems and methods of detecting malarial retinopathy using color retinal fundus images by minimally trained persons, which includes a retinal camera for obtaining images of a fundus of a subject's eye, in combination with mathematical methods to assign real time image quality classification to the images, and mathematical methods to assign real time detection of malarial retinopathy in the images, for clinical interpretation by machine-coded and/or human-based methods. The classified images will be further processed if the classified images are of sufficient image quality for clinical interpretation by machine-coded and/or human-based methods. Such systems and methods can thus automatically determine whether a retinal image presents a case of malarial retinopathy which is indicative of cerebral malaria disease. The system integrates color features, textural features, morphological features, and statistical features. A partial least square (PLS) classifier is trained to distinguish retinal images with malarial retinopathy from images with no malarial retinopathy.
摘要翻译：结合用于将实时图像质量分类分配给图像的数学方法，通过最低训练人员使用彩色视网膜眼底图像检测疟疾视网膜病变的系统和方法，其包括用于获得受试者眼睛的眼底的图像的视网膜照相机，以及在图像中分配疟疾视网膜病变的实时检测的数学方法，通过机器编码和/或基于人的方法进行临床解释。如果通过机器编码和/或基于人的方法对分类图像具有足够的图像质量进行临床解释，则分类图像将被进一步处理。因此，这样的系统和方法可以自动确定视网膜图像是否呈现指示脑疟疾的疟疾视网膜病变的病例。该系统集成了色彩特征，纹理特征，形态特征和统计特征。训练了偏最小二乘（PLS）分类器，以将视网膜图像与疟疾视网膜病变与不伴有疟疾视网膜病变的图像区分开来。

7. 发明申请

WO2017015390A1 DEEP MULTI-TASK LEARNING FRAMEWORK FOR FACE DETECTION, LANDMARK LOCALIZATION, POSE ESTIMATION, AND GENDER RECOGNITION 审中-公开
标题翻译：深度多用途学习框架，用于面部检测，地名定位，估计和性别识别
公开(公告)号：WO2017015390A1
公开(公告)日：2017-01-26
申请号：PCT/US2016/043172
申请日：2016-07-20
申请人： UNIVERSITY OF MARYLAND, COLLEGE PARK
发明人： RANJAN, Rajeev , PATEL, Vishal M. , CHELLAPPA, Ramalingam , CASTILLO, Carlos D.
IPC分类号： G06K9/00 , G06K9/46 , G06K9/66 , G06K9/68
CPC分类号： G06K9/00281 , G06K9/00248 , G06K9/036 , G06K9/4628
摘要： Various image processing may benefit from the application deep convolutional neural networks. For example, a deep multi-task learning framework may assist face detection, for example when combined with landmark localization, pose estimation, and gender recognition. An apparatus can include a first module of at least three modules configured to generate class independent region proposals to provide a region. The apparatus can also include a second module of the at least three modules configured to classify the region as face or non-face using a multi-task analysis. The apparatus can further include a third module configured to perform post- processing on the classified region.
摘要翻译：各种图像处理可能受益于应用深度卷积神经网络。例如，深层多任务学习框架可以协助人脸检测，例如与地标定位，姿态估计和性别识别相结合。一种装置可以包括至少三个模块的第一模块，所述模块被配置为产生分类独立区域提议以提供区域。该装置还可以包括至少三个模块的第二模块，其被配置为使用多任务分析将区域分类为面部或非面部。该装置还可以包括被配置为对分类区域执行后处理的第三模块。

8. 发明申请

WO2017015076A1 METHOD OF PLACING AN ANTENNA OF A RADIO ACCESS NETWORK (RAN) ASSET IN A WIRELESS COMMUNICATION NETWORK 审中-公开
标题翻译：在无线通信网络中放置无线接入网（RAN）资产的天线的方法
公开(公告)号：WO2017015076A1
公开(公告)日：2017-01-26
申请号：PCT/US2016/042397
申请日：2016-07-15
申请人： CLEARSKY TECHNOLOGIES, INC.
发明人： RUBIO, Alberto, E.
IPC分类号： H04W16/18 , H04W24/08 , H04B17/27 , H04B17/309
CPC分类号： H04W16/18 , G06K9/00476 , G06K9/0063 , G06K9/036 , G06K9/4638 , H04L41/145 , H04W24/10
摘要： An antenna of a network asset may be placed at a location determined based on a signal quality analysis carried out using a clutter object data set characterizing the influences of real world objects present in an area on signal propagation. The clutter object data set may be generated based on a set of clutter object data files each of which corresponds to a respective type of real world object. Clutter object data files may be generated based on an image of the area and each includes data representing the positions of pixels having a spectral characteristic indicative of the corresponding object type. The object clutter data set may include information derived from the object data files according to a relative hierarchical order of object types.
摘要翻译：可以将网络资产的天线放置在基于使用表征存在于区域中的真实世界对象对信号传播的影响的杂波对象数据集进行的信号质量分析而确定的位置。可以基于一组杂波对象数据文件来生成杂波对象数据集，每个杂波对象数据文件对应于相应类型的真实世界对象。可以基于该区域的图像生成杂波对象数据文件，并且每个都包括表示具有指示相应对象类型的光谱特征的像素的位置的数据。对象杂波数据集可以包括根据对象类型的相对层级顺序从对象数据文件导出的信息。

9. 发明申请

WO2017002367A1 DISPARITY IMAGE GENERATION DEVICE, DISPARITY IMAGE GENERATION METHOD, DISPARITY IMAGE GENERATION PROGRAM, OBJECT RECOGNITION DEVICE, AND EQUIPMENT CONTROL SYSTEM 审中-公开
标题翻译：差异图像生成装置，不均匀图像生成方法，差异图像生成程序，对象识别装置和设备控制系统
公开(公告)号：WO2017002367A1
公开(公告)日：2017-01-05
申请号：PCT/JP2016/003129
申请日：2016-06-29
申请人： RICOH COMPANY, LTD. , TAKAHASHI, Sadao , SEKIGUCHI, Hiroyoshi
发明人： TAKAHASHI, Sadao , SEKIGUCHI, Hiroyoshi
IPC分类号： G06T1/00 , G01B11/00 , G01C3/06
CPC分类号： G01B11/00 , G01C3/06 , G01C11/06 , G06K9/00791 , G06K9/00805 , G06K9/03 , G06K9/036 , G06T7/593 , G06T2207/30252
摘要： A disparity image generation device includes a valid pixel determination unit configured to determine a valid pixel based on a feature value of each pixel in a captured image; and a validation unit configured to validate a disparity, which is not a valid disparity, near a valid disparity corresponding to the valid pixel in a disparity image corresponding to the captured image.
摘要翻译：视差图像生成装置包括：有效像素确定单元，被配置为基于拍摄图像中的每个像素的特征值来确定有效像素; 以及验证单元，被配置为在对应于所捕获的图像的视差图像中的有效像素对应的有效视差附近验证不是有效视差的视差。

10. 发明申请

WO2016197026A1 FULL REFERENCE IMAGE QUALITY ASSESSMENT BASED ON CONVOLUTIONAL NEURAL NETWORK 审中-公开
标题翻译：基于互联神经网络的完整参考图像质量评估
公开(公告)号：WO2016197026A1
公开(公告)日：2016-12-08
申请号：PCT/US2016/035868
申请日：2016-06-03
申请人： SONY CORPORATION , XU, Xun , YE, Peng
发明人： XU, Xun , YE, Peng
IPC分类号： G06K9/48 , G06K9/62 , G06K9/66 , G06K9/68 , G06T3/40 , G06T7/00
CPC分类号： G06T7/0002 , G06K9/036 , G06K9/46 , G06K9/4628 , G06K9/6215 , G06K9/6272 , G06K9/66 , G06N3/08 , G06T5/002 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30168
摘要： Embodiments generally relate to providing systems and methods for assessing image quality of a distorted image relative to a reference image. In one embodiment, the system comprises a convolutional neural network that accepts as an input the distorted image and the reference image, and provides as an output a metric of image quality. In another embodiment, the method comprises inputting the distorted image and the reference image to a convolutional neural network configured to process the distorted image and the reference image and provide as an output a metric of image quality.
摘要翻译：实施例通常涉及提供用于评估失真图像相对于参考图像的图像质量的系统和方法。在一个实施例中，该系统包括卷积神经网络，其接受失真图像和参考图像作为输入，并且提供图像质量的度量作为输出。在另一个实施例中，该方法包括将畸变图像和参考图像输入到被配置为处理失真图像和参考图像的卷积神经网络，并提供图像质量的度量作为输出。

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