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. 发明授权
    • Generating an erosion image utilizing parallel pixel processing
    • 使用并行像素处理产生侵蚀图像
    • US08150193B2
    • 2012-04-03
    • US12353073
    • 2009-01-13
    • Allison BajoManoj Mathew
    • Allison BajoManoj Mathew
    • G06K9/44G06K9/60
    • G06K9/342G06K9/00986G06T7/11G06T7/136G06T7/155G06T2207/20036
    • An erosion image is generated from an original digital image utilizing a processing image (b) and a target image (T), where each pixel in the target image is processed in parallel. The process entails, for each target pixel, i) determining coordinate values for the target pixel, ii) determining a surrounding pixel area for the target pixel, iii) and processing each pixel in the surrounding pixel area to determine whether or not to updated the value of the target pixel. In processing each surrounding pixel, a determination is made whether the pixel has a value of 1. If not, then the next surrounding pixel is processed. If so, then a determination is made which pixel element of a structuring element overlays the target pixel, and whether that SE pixel has a value of 1. If so, then the value of the target pixel is updated. If not, then the next pixel in the surrounding pixel area is processed. Once the target pixel has been updated a set number of times to a predetermined value (e.g., 2), the processing of the remaining surrounding pixels is terminated. After all target pixels have been processed, an output image is obtained by setting target pixels having a value of 2 to a binary value of 1, and setting the other pixels to a binary value of 0. The resultant output image is an erosion image that is then output.
    • 利用处理图像(b)和目标图像(T)从原始数字图像生成侵蚀图像,其中目标图像中的每个像素被并行处理。 对于每个目标像素,该过程需要i)确定目标像素的坐标值,ii)确定目标像素的周围像素区域,iii)并处理周围像素区域中的每个像素以确定是否更新 目标像素的值。 在处理每个周围像素时,确定像素是否具有值1.如果不是,则处理下一个周围像素。 如果是,则确定结构化元素的哪个像素元素覆盖目标像素,以及该SE像素是否具有值1.如果是,则更新目标像素的值。 如果没有,则处理周围像素区域中的下一个像素。 一旦目标像素被更新了一定次数到预定值(例如,2),则其余周围像素的处理被终止。 在所有目标像素被处理之后,通过将具有值2的目标像素设置为二进制值1并将其他像素设置为二进制值0来获得输出图像。所得到的输出图像是 然后输出。
    • 5. 发明申请
    • TASK ALLOCATION IN A DISTRIBUTED COMPUTING SYSTEM
    • 分布式计算系统中的任务分配
    • US20120166514A1
    • 2012-06-28
    • US12980100
    • 2010-12-28
    • Manoj Mathew
    • Manoj Mathew
    • G06F15/16
    • G06F9/5083G06F9/505
    • Work is distributed amongst a plurality of nodes. A first plurality of tasks is extracted, where the number of tasks is selected in correspondence to the number of nodes, and where sizes of the tasks are sized based on a job load metric. The first plurality of tasks is distributed. A determination is made whether a time difference between a response from a node that is first to complete its task and a response from a node that is last to complete its task exceeds a predefined threshold. In response to a determination that the time difference exceeds the predefined threshold, the job load metric is adjusted. A second plurality of tasks is extracted, where the number of tasks is selected in correspondence to the number of nodes, and wherein sizes of the tasks are sized based on the adjusted job load metric. The second plurality of tasks is distributed.
    • 工作分布在多个节点之间。 提取第一多个任务,其中根据节点的数量选择任务的数量,并且基于作业负载量度来确定任务的大小。 第一批多个任务被分配。 确定来自首先完成其任务的节点的响应与来自完成其任务的最后一个节点的响应之间的时间差是否超过预定阈值。 响应于确定时间差超过预定阈值,调整作业负载度量。 提取第二多个任务,其中根据节点数量选择任务的数量,并且其中任务的大小基于经调整的作业负载度量来确定大小。 第二组任务是分布式的。
    • 6. 发明申请
    • GENERATING A DILATION IMAGE UTILIZING PARALLEL PIXEL PROCESSING
    • 生成平行图像使用并行像素处理
    • US20100158404A1
    • 2010-06-24
    • US12341751
    • 2008-12-22
    • MANOJ MATHEWALLISON BAJO
    • MANOJ MATHEWALLISON BAJO
    • G06K9/44
    • G06T5/30G06T2207/10116
    • A dilation image is generated from an original digital image utilizing a processing image (b) and a target image (T), where each pixel in the target image is processed in parallel. The process entails, for each target pixel, i) determining coordinate values for the target pixel, ii) determining a surrounding pixel area for the target pixel, iii) and processing each pixel in the surrounding pixel area to determine whether or not to updated the value of the target pixel. In processing each surrounding pixel, a determination is made whether the pixel has a value of 1. If not, then the next surrounding pixel is processed. If so, then a determination is made which pixel element of the structuring element overlays the target pixel, and whether that pixel has a value of 1. If so, then the value of the target pixel is updated. If not, then the next pixel in the surrounding pixel area is processed. Once the target pixel has been updated one time, the processing of the remaining surrounding pixels is terminates. If processing of all surrounding pixels results in no update to the target pixel, then the target pixel is not updated. After all target pixels have been processed, the resultant image is output as the dilation image.
    • 使用处理图像(b)和目标图像(T)从原始数字图像生成扩张图像,其中目标图像中的每个像素被并行处理。 对于每个目标像素,该过程需要i)确定目标像素的坐标值,ii)确定目标像素的周围像素区域,iii)并处理周围像素区域中的每个像素以确定是否更新 目标像素的值。 在处理每个周围像素时,确定像素是否具有值1.如果不是,则处理下一个周围像素。 如果是,则确定结构元素的哪个像素元素覆盖目标像素,以及该像素是否具有值1.如果是,则更新目标像素的值。 如果没有,则处理周围像素区域中的下一个像素。 一旦目标像素被更新一次,则其余周围像素的处理终止。 如果对所有周围像素的处理导致不更新目标像素,则不更新目标像素。 在所有目标像素被处理之后,所得到的图像被输出为扩张图像。
    • 7. 发明申请
    • PARALLEL PROCESSING FOR GENERATING A THINNED IMAGE
    • 并行处理用于生成薄膜图像
    • US20100158390A1
    • 2010-06-24
    • US12342624
    • 2008-12-23
    • Manoj MathewKeiichi Sakai
    • Manoj MathewKeiichi Sakai
    • G06K9/56
    • G06K9/44G06K9/56G06T5/30
    • A thinned output image is generated from an input image. Values of pixels surrounding a pixel of interest in the input image are determined, and first and second neighboring pixel patterns surrounding the pixel of interest are established based on the values of the pixels surrounding the pixel of interest. The first neighboring pixel pattern may be compared to each of a set of purge patterns to determine whether to eliminate the pixel, and the second neighboring pixel pattern may be compared to each of a set of conservation patterns to determine whether to conserve the pixel. The comparisons to the purge and conservation patterns are performed for each pixel independently, and in parallel for all pixels of the input image.
    • 从输入图像生成细化的输出图像。 确定输入图像中感兴趣的像素周围的像素的值,并且基于感兴趣像素周围的像素的值来建立围绕感兴趣像素的第一和第二相邻像素图案。 可以将第一相邻像素图案与一组清除图案中的每一个进行比较以确定是否消除像素,并且可以将第二相邻像素图案与一组守恒模式中的每一个进行比较,以确定是否保存像素。 对于每个像素,对输入图像的所有像素独立地并行地执行与清除和保存模式的比较。
    • 8. 发明授权
    • Image labeling using parallel processing
    • 图像标签使用并行处理
    • US08600171B2
    • 2013-12-03
    • US12635588
    • 2009-12-10
    • Manoj Mathew
    • Manoj Mathew
    • G06K9/56
    • G06K9/4638G06K9/342G06K2209/05G06T7/11G06T7/187G06T2207/10116G06T2207/30061
    • Image data which includes a feature is labeled. The image data is comprised of pixel data in an N×M array. At least one pixel is designated and flagged. Asynchronous processes are executed, where each process corresponds to exactly one pixel. Each process sets a flag only for the owner pixel and only if a connected neighbor pixel in the pre-defined path is flagged. Each process inspects pixel data for all neighbor pixels of the owner pixel to determine if a neighbor pixel is a connected pixel and if the neighbor pixel is flagged, and continues until it sets the flag for the owner pixel or until all connected horizontal and vertical neighbor pixels have been inspected without encountering a connected neighbor pixel whose flag is set. The asynchronous processes are repeated until a pre-defined condition has been satisfied. All flagged pixels are labeled.
    • 包括特征的图像数据被标记。 图像数据由N×M阵列中的像素数据组成。 指定和标记至少一个像素。 执行异步处理,其中每个进程对应于正好一个像素。 每个进程只为所有者像素设置一个标志,只有标记了预定义路径中连接的邻居像素。 每个过程检查所有者像素的所有相邻像素的像素数据,以确定相邻像素是否是连接的像素,并且如果相邻像素被标记,并且继续直到其为所有者像素设置标志,或者直到所有连接的水平和垂直邻居 已经检查了像素,而不会遇到其标志被设置的连接的相邻像素。 重复异步处理,直到满足预定义的条件。 所有标记的像素都被标记。
    • 9. 发明授权
    • Transmission of medical image data
    • 传输医学图像数据
    • US08571280B2
    • 2013-10-29
    • US12710262
    • 2010-02-22
    • Manoj Mathew
    • Manoj Mathew
    • G06K9/00G06K9/34
    • G06F19/321G06F19/00G06F19/3418
    • Transmission of a medical image such as a DICOM-formatted image which is formatted into a plurality of data sets including a data set for the image data and a data set for embedded information which identifies the nature of the medical image. A region of interest in the medical image is identified automatically by using the embedded information. Image data for the region of interest is transmitted, and image data for a region other than the region of interest is transmitted. Transmission of the image data for the entirety of the region of interest is completed before transmission of the image data for the entirety of the region other than the region of interest.
    • 传输诸如DICOM格式的图像的医学图像,其被格式化为包括用于图像数据的数据集的多个数据集和用于识别医学图像的性质的嵌入信息的数据集。 通过使用嵌入信息自动识别医学图像中的感兴趣区域。 发送感兴趣区域的图像数据,并且发送除感兴趣区域之外的区域的图像数据。 在感兴趣区域之外的整个区域的图像数据发送之前,完成感兴趣区域整体的图像数据的传输。
    • 10. 发明申请
    • IMAGE LABELING USING PARALLEL PROCESSING
    • 使用并行处理的图像标签
    • US20110142303A1
    • 2011-06-16
    • US12635588
    • 2009-12-10
    • Manoj Mathew
    • Manoj Mathew
    • G06K9/00G06K9/34
    • G06K9/4638G06K9/342G06K2209/05G06T7/11G06T7/187G06T2207/10116G06T2207/30061
    • Image data which includes a feature is labeled. The image data is comprised of pixel data in an N×M array. At least one pixel is designated and flagged. Asynchronous processes are executed, where each process corresponds to exactly one pixel. Each process sets a flag only for the owner pixel and only if a connected neighbor pixel in the pre-defined path is flagged. Each process inspects pixel data for all neighbor pixels of the owner pixel to determine if a neighbor pixel is a connected pixel and if the neighbor pixel is flagged, and continues until it sets the flag for the owner pixel or until all connected horizontal and vertical neighbor pixels have been inspected without encountering a connected neighbor pixel whose flag is set. The asynchronous processes are repeated until a pre-defined condition has been satisfied. All flagged pixels are labeled.
    • 包括特征的图像数据被标记。 图像数据由N×M阵列中的像素数据组成。 指定和标记至少一个像素。 执行异步处理,其中每个进程对应于正好一个像素。 每个进程只为所有者像素设置一个标志,只有标记了预定义路径中连接的邻居像素。 每个过程检查所有者像素的所有相邻像素的像素数据,以确定相邻像素是否是连接的像素,并且如果相邻像素被标记,并且继续直到其为所有者像素设置标志,或者直到所有连接的水平和垂直邻居 已经检查了像素,而不会遇到其标志被设置的连接的相邻像素。 重复异步处理,直到满足预定义的条件。 所有标记的像素都被标记。