会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 4. 发明专利
    • Maze pattern analyzing method and its device
    • MAZE图案分析方法及其设备
    • JP2006073011A
    • 2006-03-16
    • JP2005255046
    • 2005-09-02
    • Microsoft Corpマイクロソフト コーポレーション
    • WANG JIANCHEN LIYONGWANG QIANGMA XIAOXUDANG YINGNONG
    • G06T7/60G06F3/042
    • G06F3/0321G06F3/03545G06T7/80H04N1/32208H04N2201/3269
    • PROBLEM TO BE SOLVED: To provide a process and a device for analyzing a maze pattern image for extracting bits encoded into a maze pattern. SOLUTION: Grid lines of the maze pattern are determined, and the directions of effective pixels of a bar are estimated and grouped into clusters. A line is estimated for the effective pixels of the selected clusters. The grid lines of the other clusters are determined. The estimated lines are trimmed according to the inclination distribution analysis and grouped according to the distance analysis, and mostly fitting lines are selected from each group. An affine parameter is determined from the mostly fitting lines. A type of corner lacking in the maze pattern is determined and a right orientation of the maze pattern is obtained. Gray level values of the related maze patterns are processed and bits are extracted from the maze pattern image. COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:提供一种用于分析迷宫图案图像以提取编码成迷宫图案的比特的处理和装置。

      解决方案:确定迷宫图案的网格线,并且估计条的有效像素的方向并将其分组成簇。 针对所选择的聚类的有效像素估计一行。 确定其他簇的网格线。 估计线根据倾斜分布分析进行修剪,并根据距离分析进行分组,并从每组中选择大多数拟合线。 从大多数拟合线确定仿射参数。 确定迷宫图案中缺少的一种角落,并获得迷宫图案的正确方向。 处理相关迷宫图案的灰度值,并从迷宫图案图像中提取比特。 版权所有(C)2006,JPO&NCIPI

    • 5. 发明专利
    • Local positioning using fast image match
    • 使用快速图像匹配的本地定位
    • JP2005327246A
    • 2005-11-24
    • JP2005002847
    • 2005-01-07
    • Microsoft Corpマイクロソフト コーポレーション
    • WANG JIANCHEN LIYONGWANG QIANGMA XIAOXUDANG YINGNONG
    • G06K9/20G06F3/00G06F3/03G06F3/033G06F17/30G06K9/00G06K9/22G06K9/24G06K9/30G06K9/34G06K9/50G06K9/62G06T1/00G06T7/00G06T7/60
    • G06F3/0321G06F3/03545G06K9/222G06K9/24G06T7/74
    • PROBLEM TO BE SOLVED: To provide an efficient technology for deciding a document part matching a captured image. SOLUTION: When a user creates a stroke in a document by means of a pen, an image of the document is captured by a camera mounted on the pen. Positions of some images are decided by analyzing a pattern on the document captured by the image, while positions of other images are decided by segmenting a sequence of the images into groups corresponding to the shape of the stroke. Then, using information about an already located image inside the segment, a position of an unlocated image is decided in the segment. Using rotation and a scale of the unlocated image, an unlocated image is warped. Then, pixel-by-pixel comparison is carried out between the warped unlocated image and a document search area. When the warped unlocated image is matched successfully, a transformation parameter of the image is refined further. COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:提供用于确定与拍摄图像匹配的文档部分的有效技术。

      解决方案:当用户通过笔创建文档中的笔触时,文档的图像将由安装在笔上的相机捕获。 通过分析由图像拍摄的文档上的图案来决定一些图像的位置,而通过将图像的序列分割成与笔划的形状相对应的组来确定其他图像的位置。 然后,使用关于片段内已经定位的图像的信息,在片段中确定未定位图像的位置。 使用旋转和未定位图像的刻度,未定位的图像会变形。 然后,在翘曲的未定位图像和文档搜索区域之间进行逐像素比较。 当翘曲的未定位图像成功匹配时,图像的变换参数进一步提高。 版权所有(C)2006,JPO&NCIPI

    • 6. 发明专利
    • Camera-pen-tip mapping and calibration
    • 相机笔尖绘图和校准
    • JP2005202953A
    • 2005-07-28
    • JP2005001435
    • 2005-01-06
    • Microsoft Corpマイクロソフト コーポレーション
    • WANG JIANCHEN LIYONGMA XIAOXUDANG YINGNONG
    • G06F3/041G06F3/00G06F3/03G06F3/033G06K19/06
    • G06F3/03545G06F3/0321
    • PROBLEM TO BE SOLVED: To provide camera-pen-tip mapping and calibration. SOLUTION: X-y positions of a digital pen's tip may be determined by using a calibration parameter to map the x-y positions of the respective centers of images captured by the pen's camera. The calibration parameter may be generated by iteratively calculating estimates of the calibration parameter. Calibration input data may be produced by a user placing the pen tip in a fixed location on a surface, which may be a positionally encoded medium, such as paper, and then rotating the pen and/or moving the opposite end of the pen in various directions to capture multiple images for use in generating the calibration parameter. A user may perform such a calibration procedure without the need for complicated calibration equipment typically used in connection with conventional calibration techniques. COPYRIGHT: (C)2005,JPO&NCIPI
    • 要解决的问题:提供相机笔尖映射和校准。

      解决方案:数字笔尖的X-Y位置可以通过使用校准参数来确定由笔的相机拍摄的各个图像中心的x-y位置来确定。 可以通过迭代地计算校准参数的估计来生成校准参数。 校准输入数据可以由用户将笔尖放置在表面上的固定位置(其可以是位置编码的介质,例如纸)然后旋转笔和/或使笔的相对端移动到各种 捕获多个图像以用于生成校准参数的方向。 用户可以执行这样的校准过程,而不需要通常结合常规校准技术使用的复杂校准设备。 版权所有(C)2005,JPO&NCIPI

    • 8. 发明专利
    • Stroke localization by m-array decoding and fast image matching
    • 通过M阵列解码和快速图像匹配进行局部化
    • JP2005235185A
    • 2005-09-02
    • JP2005009688
    • 2005-01-17
    • Microsoft Corpマイクロソフト コーポレーション
    • WANG JIANCHEN LIYONGMA XIAOXUDANG YINGNONG
    • G06T1/00B60Q1/14G06F3/03G06F3/033G06F3/042
    • G06F3/03545G06F3/0321
    • PROBLEM TO BE SOLVED: To provide a system and a method that determine a path of a pen tip as the pen tip is moved across a document. SOLUTION: The document is watermarked with a maze pattern from which encoded position information is determined. A sequence of images is captured by a camera that is located in a pen. The path of the pen tip is determined by decoding the associated maze pattern and by matching the captured images with document images. If the position coordinates of any frame that is associated with a stroke cannot be determined from m-array decoding, the frames are transformed and then matched with an area of a document image. Once the position coordinates of at least one frame is determined, the position coordinates of other frames can be determined by matching the frames in a neighboring area. COPYRIGHT: (C)2005,JPO&NCIPI
    • 要解决的问题:提供一种当笔尖移动穿过文件时确定笔尖的路径的系统和方法。 解决方案:文档用迷宫图案加水印,从而确定编码位置信息。 图像序列由位于笔中的相机捕获。 笔尖的路径通过解码相关联的迷宫图案并通过将拍摄的图像与文档图像相匹配来确定。 如果不能从m阵列解码中确定与笔划相关联的任何帧的位置坐标,则将帧变换,然后与文档图像的区域匹配。 一旦确定了至少一帧的位置坐标,则可以通过匹配相邻区域中的帧来确定其他帧的位置坐标。 版权所有(C)2005,JPO&NCIPI
    • 10. 发明专利
    • Global localization by fast image matching
    • 通过快速图像匹配进行全球定位
    • JP2005235178A
    • 2005-09-02
    • JP2005002846
    • 2005-01-07
    • Microsoft Corpマイクロソフト コーポレーション
    • WANG JIANCHEN LIYONGWANG QIANGMA XIAOXUDANG YINGNONG
    • G06T7/00G06F3/03G06F3/033G06K19/06
    • G06F3/03545G06F3/0321
    • PROBLEM TO BE SOLVED: To provide an efficient technique for determining a portion of a document, corresponding to a captured image. SOLUTION: Areas of a document, in which the pattern is at least partially obscured, are identified. A reference pixel in the image is selected, and the offset between the pixel and the pattern is determined. A pixel-by-pixel comparison is then made of the image with the document, such that the reference pixel is compared only with the locations in the document that are both within the identified areas and have the determined offset from the pattern. The comparison with the highest correspondence between the image pixels and the electronic document then identifies the position of the reference pixel relative to the electronic document. COPYRIGHT: (C)2005,JPO&NCIPI
    • 要解决的问题:提供一种用于确定与拍摄图像相对应的文档的一部分的有效技术。

      解决方案:识别出图案至少部分模糊的文档区域。 选择图像中的参考像素,并且确定像素和图案之间的偏移。 然后,使用文档对图像进行逐像素比较,使得仅将参考像素与文档中位于所识别的区域内的位置进行比较,并且具有从图案确定的偏移。 与图像像素和电子文档之间的最高对应关系的比较然后识别参考像素相对于电子文档的位置。 版权所有(C)2005,JPO&NCIPI