公开(公告)号：EP2053973A2

公开(公告)日：2009-05-06

申请号：EP07841322.6

申请日：2007-08-24

申请人： Restoration Robotics, Inc.

发明人： QURESHI, Shehrzad, A. ,  BODDULURI, Mohan

IPC分类号： A61B6/00

CPC分类号： G06K9/00 ,  A61B2017/00752 ,  A61F2/10 ,  G06K9/00127 ,  G06K9/36 ,  G06T7/0012 ,  G06T2207/20036 ,  G06T2207/30088 ,  G06T2207/30242

摘要： A system and method for counting follicular units using an automated system comprises acquiring an image of a body surface having skin and follicular units, filtering the image to remove skin components in the image, processing the resulted image to segment it, and filtering noise to eliminate all elements other than hair follicles of interest so that hair follicles in an area of interest can be counted. The system may comprise an image acquisition device and an image processor for performing the method. In another aspect, the system and method also classifies the follicular units based on the number of hairs in the follicular unit.

公开(公告)号：EP1667829A4

公开(公告)日：2008-12-10

申请号：EP04757388

申请日：2004-07-28

申请人： FLUIDIGM CORP

发明人： TAYLOR COLIN JON ,  SUN GANG ,  DUBE SIMANT

IPC分类号： G06K9/00 ,  A61B5/05 ,  A61B6/00 ,  B01L3/00 ,  B29C20060101 ,  C12Q1/68 ,  G06K9/20 ,  G06K9/36 ,  G06K9/46 ,  G06K9/52 ,  G06K9/62 ,  G06T7/00

CPC分类号： G06K9/36 ,  B01L3/5027 ,  G06K9/00 ,  G06K9/00127 ,  G06K9/00134 ,  G06K9/6232 ,  G06T7/0008 ,  G06T7/0012 ,  G06T7/254 ,  G06T7/33 ,  G06T2207/30004

摘要： A method for processing an image of a micro fluidic device. The method includes receiving a first image of a micro fluidic device. The first image corresponds to a first state. Additionally, the method includes receiving a second image of the micro fluidic device. The second image corresponds to a second state. Moreover, the method includes transforming the first image and the second image into a third coordinate space (520). Also, the method includes obtaining a third image based on at least information associated (540) with the transformed first image and the transformed second image, and processing the third image to obtain information (550) associated with the first state and the second state.

摘要翻译： 一种用于处理微流体装置的图像的方法。 该方法包括接收微流体装置的第一图像。 第一图像对应于第一状态。 另外，该方法包括接收微流体装置的第二图像。 第二图像对应于第二状态。 此外，该方法包括将第一图像和第二图像变换为第三坐标空间。 此外，该方法包括至少基于与变换的第一图像和变换的第二图像相关联的信息获得第三图像，并且处理第三图像以获得与第一状态和第二状态相关联的信息。

公开(公告)号：EP1769371A4

公开(公告)日：2007-08-15

申请号：EP05749682

申请日：2005-04-25

申请人： MOTOROLA INC

发明人： MOHAMED MAGDI A ,  XIAO WEIMIN

IPC分类号： G06F15/00 ,  G06K9/36 ,  G06K9/62

CPC分类号： G06K9/36 ,  G06K9/6288 ,  H03H17/0261 ,  H03H2017/0072 ,  H03H2222/02

摘要： A Q-Filter is a reconfigurable technique that performs a continuum of linear and nonlinear filtering operations. It is modeled by unique mathematical structure, utilizing a function called the Q-Measure, defined using a set of adjustable kernel parameters to enable efficient hardware and software implementations of a variety of useful, new and conventional, filtering operations. The Q-Measure is a novel is based on an extension of the well-known Sugeno Q-Measure.

摘要翻译： Q滤波器是一种可重构技术，可执行连续的线性和非线性滤波操作。 它采用独特的数学结构建模，利用称为Q-Measure的功能，使用一组可调节的内核参数进行定义，以实现各种有用的新型常规过滤操作的高效硬件和软件实现。 Q-Measure是一款基于知名Sugeno Q-Measure扩展的小说。

公开(公告)号：EP1769371A2

公开(公告)日：2007-04-04

申请号：EP05749682.0

申请日：2005-04-25

申请人： MOTOROLA, INC.

发明人： MOHAMED, Magdi A., ,  XIAO, Weimin,

IPC分类号： G06F15/00

CPC分类号： G06K9/36 ,  G06K9/6288 ,  H03H17/0261 ,  H03H2017/0072 ,  H03H2222/02

摘要： A Q-Filter is a reconfigurable technique that performs a continuum of linear and nonlinear filtering operations. It is modeled by unique mathematical structure, utilizing a function called the Q-Measure, defined using a set of adjustable kernel parameters to enable efficient hardware and software implementations of a variety of useful, new and conventional, filtering operations. The Q-Measure is a novel is based on an extension of the well-known Sugeno Q-Measure.

公开(公告)号：EP1428378A1

公开(公告)日：2004-06-16

申请号：EP02773294.0

申请日：2002-09-06

申请人： Intergraph Hardware Technologies Company

发明人： FLETCHER, Susan, Heath, Calvin ,  GRINDSTAFF, Gene, Arthur ,  MCKAY, Therman, Ward, III

IPC分类号： H04N5/232

CPC分类号： H04N5/247 ,  G06K9/36 ,  G06T5/50 ,  G06T7/33 ,  H04N5/23248 ,  H04N5/23267 ,  H04N7/181 ,  H04N9/646

摘要： A method for image stabilization of at least two digital images is disclosed. In such an embodiment, a first digital image having a plurality of pixels and at least a second image having a plurality of pixels are provided. Each pixel has an associated address for display and is representative of a color. Either a user of the system provides a color match range or the system provides a predetermined color matched range. A pixel is selected within the first digital image. Preferably the pixel is one that represents an item within the image that is either blurry due to movement of the item or appears jittery due to camera movement. Due to the vast number of available colors a pixel selected in a first image can be matched to a pixel in a second image within a range. The range allows for compensation due to lighting changes. Once the pixel in the first image is selected it can be compared to all pixels within the second image. Each pixel within the second image that is within the color match range is saved and the closest pixel color to the pixel from the first image is selected. The address of the pixels in the second image are then readdressed such that the address of the pixel located in the second image that has the closest color to the pixel in the first image now has the same display address as that of the pixel in the first image. The repositioned second digital image is then stored to memory.

摘要翻译： 公开了一种用于至少两个数字图像的图像稳定的方法。 在这样的实施例中，提供具有多个像素的第一数字图像和至少具有多个像素的第二图像。 每个像素具有用于显示的相关联的地址并且代表颜色。 系统的用户提供颜色匹配范围，或者系统提供预定的颜色匹配范围。 在第一数字图像内选择像素。 优选地，像素是表示图像中由于项目的移动而模糊的项目或由于相机移动而显示抖动的像素。 由于大量的可用颜色，第一图像中选择的像素可以与范围内的第二图像中的像素匹配。 该范围允许由于照明变化的补偿。 一旦选择了第一个图像中的像素，它可以与第二个图像中的所有像素进行比较。 在第二图像内的颜色匹配范围内的每个像素被保存，并且选择与第一图像的像素最接近的像素颜色。 然后，第二图像中的像素的地址被读取，使得位于第二图像中的与第一图像中的像素最接近的颜色的像素的地址现在具有与第一图像中的像素相同的显示地址 图片。 然后将重新定位的第二数字图像存储到存储器中。

公开(公告)号：EP1417635A2

公开(公告)日：2004-05-12

申请号：EP02750805.0

申请日：2002-06-25

申请人： Koenig & Bauer Aktiengesellschaft

发明人： SACHER, Jörn ,  WILLEKE, Harald, Heinrich

IPC分类号： G06K9/64 ,  G07D7/00

CPC分类号： G07D7/20 ,  G06K9/36 ,  G06K9/38 ,  G06T7/74

摘要： The invention relates to a method for qualitatively evaluating material with at least one identification characteristic whose position can vary within an expectation range designated by tolerance limits. The evaluation involves the use of at least one illuminating device, at least one photoelectric sensor and an evaluating device that interacts therewith. At least one background reference value and at least one mask reference are stored in the evaluating device, whereby the background reference value represents the characteristics of the printed image, particularly the gray scale value, in at least one portion of a surrounding area around the identification characteristic. In addition, the mask reference represents the geometrical contour of the identification characteristic and/or the relative arrangement of several identification characteristics among themselves. When inspecting the imprinted material, differential image data is formed, at least for the expectation range, from the actual image data and from the background reference value in the evaluating device. The actual position of the identification characteristic is subsequently derived in the evaluating device based on the comparison of the differential image data with the mask reference.

摘要翻译： 用于定性评估具有至少一个识别特征的材料的方法，其特征在于，其位置可以在由公差限度指定的期望范围内变化，包括使用至少一个照明装置，至少一个光电传感器和评估装置。 至少一个背景参考值和至少一个掩模参考存储在评估装置中。 背景参考表示围绕识别特征的至少一个部分中的打印图像的特性，特别是灰度值。 掩模参考表示识别特征的几何轮廓。 在印刷材料的检查期间，至少从预期范围，从实际图像数据和评估装置中的背景参考值发现差分图像数据。 随后在评估装置中导出识别特征的实际位置。

公开(公告)号：EP0944961A4

公开(公告)日：2000-05-24

申请号：EP97946587

申请日：1997-11-10

申请人： TERALOGIC INC

发明人： CHUI CHARLES K ,  YI RONGXIANG

IPC分类号： H03M7/30 ,  G06K9/36 ,  G06T9/00 ,  H04N7/26 ,  H03M7/00

CPC分类号： H04N19/61 ,  G06K9/36 ,  H04N19/13 ,  H04N19/619 ,  H04N19/63

摘要： A data encoder and method successively analyzes successively smaller blocks of a specified data array. Data blocks are analyzed in a predefined order, and corresponding entries identifying data blocks containing at least one non-zero value are stored in that same order in a list of blocks. Whenever a data block is processed, if the data block is entirely filled with zero data it is so identified in the output data (371) and no further processing of the subblock is required. Otherwise, if the size of the data block is greater than a predefined minimum block size (376) (e.g., 2 x 2), the block is divided into smaller data blocks and those smaller data blocks are put on the list of blocks for further processing. Finally, if the size of a data block that is being processed is the predefined minimum block size, values representing all the data items in that data block are written into the output data (396).

公开(公告)号：EP0551403A1

公开(公告)日：1993-07-21

申请号：EP91918813.0

申请日：1991-09-26

申请人： UNISYS CORPORATION ,  CGK Computer Gesellschaft Konstanz mbH

发明人： WUSTMANN, Gerhard, K.

IPC分类号： G06K ,  G06K9

CPC分类号： G06K9/36

摘要： Procédé de localisation et de reconnaissance automatique de données de quantité (10b) sur un document (10) par balayage du document pour localiser d'abord un symbole particulier, tel que le signe "$" (10a), ce signe localisé "$" étant utilisé pour déterminer la région du document (10b-1, 10b-2) contenant les données de quantité (10b) à reconnaître. Des éléments du symbole "$" et les caractères de quantité sont extraits d'une image de niveau de gris (Fig. 5) en utilisant des images binaires de valeur de départ et de masque (Fig. 7, 8 et 10, 11) de seuils différents de manière que des pixels noirs trouvés dans les images de valeur de départ des seuils les plus élevés se propagent dans l'image de masque de seuil inférieur pour former des composants reliés (Fig. 8, cc-1 et cc-2).

公开(公告)号：EP0327069A3

公开(公告)日：1992-08-26

申请号：EP89101744.4

申请日：1989-02-01

申请人： TOYODA KOKI KABUSHIKI KAISHA

发明人： Sugita, Kazuhiko ,  Hotta, Shigeo ,  Matsuda, Osamu ,  Yamakawa, Yoichi

IPC分类号： G06K9/80

CPC分类号： G06K9/6203 ,  B25J9/1697 ,  G06K9/36

摘要： A method and a system for recognizing the location of a cylindrical shaft is provided for use in positioning an end effector of an industrial robot which handles said shaft. In the method and system, a multilevel gray image of the cylindrical shaft which is generated by a charge coupled device (CCD) image sensor is first differentiated, and the absolute values of picture elements constituting the differentiated gray image are then binarized on the basis of a threshold value so as to extract an accentuated pattern image which is inherent to the shape of the cylindrical shaft. The accentuated pattern image thus extracted is then collated with a reference accentuated pattern image (template) so as to generate a normal curve signal which has its peak point at a position where the axis of said cylindrical shaft is located. The normal curve data is then binarized on the basis of another predetermined threshold value to generate a single strip image. The center of the single strip image is calculated to determine the location of the cylindrical shaft.

公开(公告)号：EP0052400A1

公开(公告)日：1982-05-26

申请号：EP81201231.8

申请日：1981-10-30

申请人： Staat der Nederlanden (Staatsbedrijf der Posterijen, Telegrafie en Telefonie)

发明人： van Bilzem, Jan Frederick ,  van Staveren, Johannes

IPC分类号： G06K9/60 ,  G06K9/03

CPC分类号： G06K9/60 ,  G06K9/03 ,  G06K9/20 ,  G06K9/32 ,  G06K9/34 ,  G06K9/36 ,  G06K9/44

摘要： Handwritten and typewritten characters read in one and the same process.
In the first step, four interleaved images of the character are recorded in a memory (3). Then a preprocessor (4) determines the sort of characters either handwritten or typewritten, on the basis of their respective dimensions. Typewritten characters are enlarged so that they will be better readable owing to an enhanced scanning and stored in a buffer (10), the handwritten characters being first segmented by a geometric separator (9) before their storage in the buffer (10), next a circuit (5) derives the features irrespective of the sort of characters, after which the classification (in 11) takes place by means of learning means (12, 13) dependent on the sort of characters. A results combiner (20) resolves multiple recognitions by a feedback action to the buffer (10).
An editing device (14) arranges the recognition result in the right format and a final comparator (15) compares the output of the character-reading device to the output of a manual key-entry device.

摘要翻译： 手写和打字字符在同一个过程中读取。 在第一步骤中，字符的四个交错图像被记录在存储器（3）中。 然后，预处理器（4）基于它们各自的尺寸确定手写或打字的字符的种类。 打字字符被放大，使得它们将由于增强的扫描而被更好地读取并存储在缓冲器（10）中，手写字符首先在几何分离器（9）存储在缓冲器（10）之前被分割，接下来 电路（5）导出特征，而不管字符的种类，之后分类（11）通过依赖于字符种类的学习手段（12,13）进行。 结果组合器（20）通过对缓冲器（10）的反馈动作来解析多个识别。 编辑装置（14）将识别结果排列成正确的格式，最后的比较器（15）将字符读取装置的输出与手动键入装置的输出进行比较。