DEVICE AND METHOD FOR DESIGNING USING SYMBOLIZED IMAGE, AND DEVICE AND METHOD FOR ANALYZING DESIGN TARGET TO WHICH SYMBOLIZED IMAGE IS APPLIED
    31.
    发明申请
    DEVICE AND METHOD FOR DESIGNING USING SYMBOLIZED IMAGE, AND DEVICE AND METHOD FOR ANALYZING DESIGN TARGET TO WHICH SYMBOLIZED IMAGE IS APPLIED 审中-公开
    用于使用符号图像设计的设备和方法,以及用于分析设计目标以分配符号图像的设备和方法

    公开(公告)号:US20160148341A1

    公开(公告)日:2016-05-26

    申请号:US14903655

    申请日:2014-07-09

    申请人: Jung ha Ryu

    发明人: Jung ha Ryu

    IPC分类号: G06T3/00

    摘要: A first method for mapping out a design by using a symbolized image and a second method for analyzing an object of design to which a symbolized image is applied is provided. The first method includes the steps of: mapping out an object of design to display the symbolized image including a symbolic sign created at a position in the symbolized image corresponding to a blank space of a character image; and outputting an image of the object of design. Further, the second method includes the steps of: receiving information on an appearance of the object of design implemented by using a symbolized image including a symbolic sign created at a position in the symbolized image corresponding to a blank space of the character image; extracting the symbolized image implemented on the object of design; and (c) displaying the extracted symbolized image.

    摘要翻译: 提供了通过使用符号化图像来绘制设计的第一方法和用于分析应用符号化图像的设计对象的第二方法。 第一种方法包括以下步骤:映射设计对象以显示符号化图像,其包括在与字符图像的空白空间相对应的符号图像中的位置处创建的符号符号; 并输出设计对象的图像。 此外,第二方法包括以下步骤:接收通过使用包括在与字符图像的空白空间相对应的符号图像中的位置处创建的符号符号的符号化图像来实现的设计的外观的信息; 提取在设计对象上实现的符号化图像; 和(c)显示所提取的符号图像。

    METHOD AND TERMINAL DEVICE FOR RETARGETING IMAGES
    34.
    发明申请
    METHOD AND TERMINAL DEVICE FOR RETARGETING IMAGES 有权
    用于缩回图像的方法和终端装置

    公开(公告)号:US20150371367A1

    公开(公告)日:2015-12-24

    申请号:US14666311

    申请日:2015-03-24

    申请人: Xiaomi Inc.

    IPC分类号: G06T3/40 G06T7/00

    CPC分类号: G06T3/0012 G06K9/4671

    摘要: The present disclosure relates to a method and a terminal device for image retargeting, and belongs to the computer technical field. The method includes: establishing a saliency model for an original image; calculating a saliency value of each pixel point in the original image based on the saliency model; and retargeting a target image according to the saliency value of each pixel point, original resolution of the original image and target resolution of the target image. Thus, the present disclosure may solve the problem of complicated analysis process and huge calculation amount caused by analyzing image contents of the original image to obtain important pixel points. Consequently, technical effects of reducing calculation amount may be achieved.

    摘要翻译: 本公开涉及一种用于图像重定向的方法和终端装置,属于计算机技术领域。 该方法包括:为原始图像建立显着性模型; 基于显着性模型计算原始图像中每个像素点的显着值; 并根据每个像素点的显着值,原始图像的原始分辨率和目标图像的目标分辨率重新定位目标图像。 因此,本公开可以解决复杂的分析处理和通过分析原始图像的图像内容而导致的巨大计算量以获得重要的像素点的问题。 因此,可以实现减少计算量的技术效果。

    System and method for content aware hybrid cropping and seam carving of images
    37.
    发明授权
    System and method for content aware hybrid cropping and seam carving of images 有权
    用于内容识别混合裁剪和图像缝合雕刻的系统和方法

    公开(公告)号:US08963960B2

    公开(公告)日:2015-02-24

    申请号:US12469486

    申请日:2009-05-20

    申请人: Anant Gilra

    发明人: Anant Gilra

    摘要: A system and method for performing content aware cropping/expansion may be applied to resize an image or to resize a selected object therein. An image object may be selected using an approximate bounding box of the object. The system may receive input indicating a lowest priority edge or corner of the image or object to be resized (e.g., using a drag operation). Respective energy values for some pixels of the image and/or of the object to be resized may be weighted based on their distance from the lowest priority edge/corner and/or on a cropping or expansion graph, and relative costs may be determined for seams of the image dependent on the energy values. Low cost seams may be removed or replicated in different portions of the image and/or the object to modify the image. The selected object may be resized using interpolated scaling and patched over the modified image.

    摘要翻译: 可以应用用于执行内容感知裁剪/扩展的系统和方法来调整图像的大小或调整其中所选择的对象的大小。 可以使用对象的近似边界框来选择图像对象。 系统可以接收指示要调整大小的图像或对象的最低优先级边缘或角落的输入(例如,使用拖动操作)。 可以基于其与最低优先级边缘/角落和/或裁剪或扩展图上的距离对图像和/或要调整大小的某些像素的相应能量值进行加权,并且可以确定接缝的相对成本 的图像取决于能量值。 可以在图像和/或对象的不同部分中移除或复制低成本接缝以修改图像。 可以使用内插缩放来调整所选择的对象,并在修改的图像上进行修补。

    INTELLIGENT MAP COMBINATION FOR VENUES ENABLING INDOOR POSITIONING
    38.
    发明申请
    INTELLIGENT MAP COMBINATION FOR VENUES ENABLING INDOOR POSITIONING 有权
    智能地图组合实现室内定位

    公开(公告)号:US20150019121A1

    公开(公告)日:2015-01-15

    申请号:US13938124

    申请日:2013-07-09

    IPC分类号: G06T3/00 H04W4/02 G01C21/00

    摘要: Methods and devices are described for merging maps. In one potential embodiment a method may comprise receiving an indication of at least one plurality of geographically proximate points, where each of the at least one plurality of geographically proximate points are determined by at least one access point in communication with one or more mobile devices. A first and second map may then be received, where the first map and the second map each cover a first area such that the first area is in both the first map and the second map. The first map and the second map may then be merged by matching a mapping of a first portion of an indication of the at least one plurality of geographically proximate points on the first map and a second portion of an indication of an at least one plurality of geographically proximate points on the second map.

    摘要翻译: 描述了用于合并地图的方法和设备。 在一个潜在的实施例中,方法可以包括接收至少一个多个地理上邻近的点的指示,其中所述至少一个多个地理上邻近的点中的每一个由与一个或多个移动设备通信的至少一个接入点确定。 然后可以接收第一和第二地图,其中第一地图和第二地图各自覆盖第一区域,使得第一区域在第一地图和第二地图中。 然后可以通过匹配第一地图上的至少多个地理上靠近的点的指示的第一部分的映射和至少一个多个位置上的指示的第二部分的映射来合并第一地图和第二地图 地理位置上第二个地图上的邻近点。

    HIERARCHICAL CLASSIFICATION IN CREDIT CARD DATA EXTRACTION
    39.
    发明申请
    HIERARCHICAL CLASSIFICATION IN CREDIT CARD DATA EXTRACTION 有权
    信用卡数据提取中的分层分类

    公开(公告)号:US20150003748A1

    公开(公告)日:2015-01-01

    申请号:US14059071

    申请日:2013-10-21

    申请人: GOOGLE INC.

    IPC分类号: G06K9/00

    摘要: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

    摘要翻译: 这里的实施例提供了计算机实现的技术,用于允许用户计算设备使用光学字符识别(“OCR”)提取金融卡信息。 可以通过对图像数据应用各种分类器和其他变换来提高金融卡信息的提取。 例如,在应用OCR算法之前,对图像应用线性分类器以确定数字位置允许用户计算设备使用较少的处理能力来提取准确的卡数据。 OCR应用程序可以训练分类器来使用卡的磨损模式来改善OCR算法性能。 OCR应用可以应用线性分类器,然后应用非线性分类器来提高OCR算法的性能和准确性。 OCR应用程序使用典型的信用卡和借记卡使用的已知数字模式来提高OCR算法的准确性。

    EXTRACTING CARD DATA WITH WEAR PATTERNS
    40.
    发明申请
    EXTRACTING CARD DATA WITH WEAR PATTERNS 有权
    提取卡片数据与磨损模式

    公开(公告)号:US20150003667A1

    公开(公告)日:2015-01-01

    申请号:US14091093

    申请日:2013-11-26

    申请人: GOOGLE INC.

    摘要: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

    摘要翻译: 这里的实施例提供了计算机实现的技术,用于允许用户计算设备使用光学字符识别(“OCR”)提取金融卡信息。 可以通过对图像数据应用各种分类器和其他变换来提高金融卡信息的提取。 例如,在应用OCR算法之前,对图像应用线性分类器以确定数字位置允许用户计算设备使用较少的处理能力来提取准确的卡数据。 OCR应用程序可以训练分类器来使用卡的磨损模式来改善OCR算法性能。 OCR应用程序可以应用线性分类器,然后应用非线性分类器来提高OCR算法的性能和准确性。 OCR应用程序使用典型的信用卡和借记卡使用的已知数字模式来提高OCR算法的准确性。