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
    • 1. 发明授权
    • Method and apparatus for reducing image noise
    • 降低图像噪声的方法和装置
    • US09165346B2
    • 2015-10-20
    • US14262062
    • 2014-04-25
    • Fujitsu Limited
    • Xuan FuJiangli Ye
    • G06K9/00G06T5/40G06T5/20G06T5/00
    • G06T5/002G06T5/20G06T5/40
    • Embodiments of the present invention provide a method and an apparatus for reducing image noise. The method includes decomposing an original image into a luminance channel image and at least one chrominance channel image, and calculating a weighted average value of each pixel of the luminance channel image and the chrominance channel image by using luminance information, to correct each pixel of the luminance channel image and the chrominance channel image. By virtue of the embodiments of the present invention, it is possible to effectively avoid color dispersion at edges of images, to achieve easy implementation, and to effect low cost.
    • 本发明的实施例提供了一种降低图像噪声的方法和装置。 该方法包括将原始图像分解为亮度通道图像和至少一个色度通道图像,并且通过使用亮度信息来计算亮度通道图像和色度通道图像的每个像素的加权平均值,以校正每个像素 亮度通道图像和色度通道图像。 凭借本发明的实施例,可以有效地避免图像边缘的色散,实现易于实现,并实现低成本。
    • 2. 发明授权
    • Method and apparatus for processing edges of a gray image
    • 用于处理灰色图像边缘的方法和装置
    • US09299163B2
    • 2016-03-29
    • US14290169
    • 2014-05-29
    • FUJITSU LIMITED
    • Jianrong WuXuan FuAkihiro Higashi
    • G06K9/40G06T7/40G06T5/20
    • G06T7/408G06T5/20G06T7/90G06T2207/10004G06T2207/20021G06T2207/20052
    • A method and apparatus for processing a gray image, including: calculating a mean value and a standard difference of each edge pixel needing processing in an original gray image, and determining a predefined noise variance of each edge pixel according to the mean value and the standard difference; performing two-dimensional discrete cosine transform on an original gray image of a first adjacent area of each edge pixel; performing Wiener filtering on the two-dimensional discrete cosine transformed image data according to the noise variance; performing discrete cosine inverse transform on the two-dimensional Wiener filtered image data to obtain a filtered gray image of the first adjacent area; and extracting a filtered pixel value of each edge pixel from the filtered gray image of the first adjacent area, and obtaining a processed pixel value of each edge pixel by performing weighted summation on the filtered pixel value and an original pixel value.
    • 一种用于处理灰度图像的方法和装置,包括:计算原始灰度图像中每个边缘像素需要处理的平均值和标准差,以及根据平均值和标准确定每个边缘像素的预定噪声方差 区别; 对每个边缘像素的第一相邻区域的原始灰度图像执行二维离散余弦变换; 根据噪声方差对二维离散余弦变换图像数据进行维纳滤波; 对二维维纳滤波图像数据进行离散余弦逆变换以获得第一相邻区域的滤波灰度图像; 以及从所述第一相邻区域的经滤波的灰度图像提取每个边缘像素的滤波像素值,并且通过对所述滤波像素值和原始像素值执行加权求和来获得每个边缘像素的经处理像素值。
    • 3. 发明授权
    • Flicker detection method and flicker detection apparatus
    • 闪烁检测方法和闪烁检测装置
    • US09167175B2
    • 2015-10-20
    • US14336283
    • 2014-07-21
    • FUJITSU LIMITED
    • Jianrong WuXuan FuAkihiro Higashi
    • H04N9/73H04N5/235H04N5/14
    • H04N5/2357H04N5/145
    • The present invention discloses a flicker detection method and a flicker detection apparatus. The method includes: calculating the mean values of selected rows of image frames to constitute a mean value vector; calculating a differential vector between the mean value vectors of a current frame and a previous frame; calculating a DC-free difference vector; building a first square wave and a second square wave, and a third square wave and a fourth square wave; calculating a first frequency reference value; calculating a second frequency reference value; and if the difference between the first and second frequency reference values is above a threshold, then it is determined that flicker is present in the current frame; otherwise, it is determined that no flicker is present.
    • 本发明公开了一种闪烁检测方法和闪烁检测装置。 该方法包括:计算图像帧的所选行的平均值以构成平均值向量; 计算当前帧的平均值向量与前一帧的差分向量; 计算无DC差分矢量; 构造第一方波和第二方波,以及第三方波和第四方波; 计算第一频率参考值; 计算第二频率参考值; 并且如果第一和第二频率参考值之间的差异高于阈值,则确定在当前帧中存在闪烁; 否则,确定不存在闪烁。
    • 5. 发明授权
    • Filtering method and device in image processing
    • 图像处理过滤方法和设备
    • US09286660B2
    • 2016-03-15
    • US14298160
    • 2014-06-06
    • Fujitsu Limited
    • Xuan FuJiangli Ye
    • G06K9/40G06T5/00G06T5/40H04N1/62
    • G06T5/002G06T5/40G06T2207/20012G06T2207/20021G06T2207/20024H04N1/62
    • Embodiments provide a filtering method and device in image processing. The device includes: a dividing unit to divide a first filtering window into blocks; a determining unit to determine a filtering window area according to relevance between a central block and other non-central blocks in the blocks; and a filtering unit to perform filtering processing on an image in the determined filtering window area. With the method and device of the embodiments, a boundary of an object will not be crossed in filtering, and in removing noise, information on other objects will not be introduced to affect the result of filtering. A filtering window size may be determined while filtering is performing, which may be carried out in one path, avoiding time delay resulting from execution of two paths of a conventional method where an edge is detected and then the size of a filtering window is determined.
    • 实施例提供了图像处理中的滤波方法和装置。 该装置包括:分割单元,用于将第一过滤窗口划分成块; 确定单元,用于根据所述块中的中央块和其他非中心块之间的相关性来确定过滤窗口区域; 以及滤波单元,对确定的滤波窗口区域中的图像进行滤波处理。 利用实施例的方法和装置,在过滤中不会越过对象的边界,并且在消除噪声时,不会引入关于其他对象的信息来影响滤波结果。 可以在执行滤波时确定滤波窗口大小,其可以在一个路径中执行,避免由检测到边缘的传统方法的两个路径的执行导致的时间延迟,然后确定滤波窗口的大小。
    • 6. 发明授权
    • Flicker detection method and flicker detection apparatus
    • 闪烁检测方法和闪烁检测装置
    • US09148583B2
    • 2015-09-29
    • US14336281
    • 2014-07-21
    • FUJITSU LIMITED
    • Jianrong WuXuan FuAkihiro Higashi
    • H04N5/235H04N5/14
    • H04N5/2357H04N5/144
    • The present invention discloses a flicker detection method and a flicker detection apparatus. The method includes: calculating the mean values of selected rows of image frames to constitute a mean value vector; calculating a differential vector between the mean value vectors of a current frame and a previous frame; calculating a DC-free difference vector by subtracting a direct current component from respective elements of the differential vector; calculating a power spectrum corresponding to the DC-free difference vector; obtaining a first frequency reference value; obtaining a second frequency reference value; and if the difference between the first and second frequency reference values is above a threshold, then it is determined that flicker is present in the current frame; otherwise, it is determined that no flicker is present.
    • 本发明公开了一种闪烁检测方法和闪烁检测装置。 该方法包括:计算图像帧的所选行的平均值以构成平均值向量; 计算当前帧的平均值向量与前一帧的差分向量; 通过从差分矢量的各个元素中减去直流分量来计算无DC差分矢量; 计算与无DC差分矢量对应的功率谱; 获得第一频率参考值; 获得第二频率参考值; 并且如果第一和第二频率参考值之间的差异高于阈值,则确定在当前帧中存在闪烁; 否则,确定不存在闪烁。