利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5 条记录 (耗时 0.018 秒)

    IMAGE DENOISING METHOD
    1.
    发明申请
    IMAGE DENOISING METHOD 有权
    图像吸收方法

    公开(公告)号：US20110069902A1

    公开(公告)日：2011-03-24

    申请号：US12829424

    申请日：2010-07-02

    申请人： Shu Sian Yang ,  Wen Han Yao ,  Chuan Hsin Lee

    发明人： Shu Sian Yang ,  Wen Han Yao ,  Chuan Hsin Lee

    IPC分类号： G06K9/40

    CPC分类号： G06T5/002 ,  G06T5/20 ,  G06T2207/20012 ,  G06T2207/20021

    摘要： An image denoising method includes the steps of: sequentially selecting a pixel in an image as a current pixel; dynamically determining a current search block and a strength parameter; pre-denoising the comparison block of each pixel in the current search block; comparing the comparison block of the pre-denoised neighborhood pixel and the comparison block of the pre-denoised current pixel to obtain a similarity between each neighborhood pixel and the current pixel in the current search block; determining a weighting of each neighborhood pixel related to the current pixel according to the strength parameter, and a distance and the similarity between each neighborhood pixel and the current pixel in the current search block; and weighted averaging each neighborhood pixel and the current pixel in the current search block according to the weighting to obtain a reconstruction value of the current pixel.

    摘要翻译： 图像去噪方法包括以下步骤：顺序地选择图像中的像素作为当前像素; 动态地确定当前搜索块和强度参数; 对当前搜索块中每个像素的比较块进行预去噪; 比较预去噪相邻像素的比较块和预去噪的当前像素的比较块，以获得当前搜索块中每个邻域像素与当前像素之间的相似度; 根据强度参数确定与当前像素相关的每个邻域像素的加权，以及当前搜索块中每个邻域像素与当前像素之间的距离和相似度; 并且根据加权对当前搜索块中的每个邻域像素和当前像素进行加权平均，以获得当前像素的重建值。

    Image denoising method
    2.
    发明授权
    Image denoising method 有权
    图像去噪方法

    公开(公告)号：US08885965B2

    公开(公告)日：2014-11-11

    申请号：US12829424

    申请日：2010-07-02

    申请人： Shu Sian Yang ,  Wen Han Yao ,  Chuan Hsin Lee

    发明人： Shu Sian Yang ,  Wen Han Yao ,  Chuan Hsin Lee

    IPC分类号： G06K9/40 ,  G06T5/00 ,  G06T5/20

    CPC分类号： G06T5/002 ,  G06T5/20 ,  G06T2207/20012 ,  G06T2207/20021

    摘要： An image denoising method includes the steps of: sequentially selecting a pixel in an image as a current pixel; dynamically determining a current search block and a strength parameter; pre-denoising the comparison block of each pixel in the current search block; comparing the comparison block of the pre-denoised neighborhood pixel and the comparison block of the pre-denoised current pixel to obtain a similarity between each neighborhood pixel and the current pixel in the current search block; determining a weighting of each neighborhood pixel related to the current pixel according to the strength parameter, and a distance and the similarity between each neighborhood pixel and the current pixel in the current search block; and weighted averaging each neighborhood pixel and the current pixel in the current search block according to the weighting to obtain a reconstruction value of the current pixel.

    摘要翻译： 图像去噪方法包括以下步骤：顺序地选择图像中的像素作为当前像素; 动态地确定当前搜索块和强度参数; 对当前搜索块中每个像素的比较块进行预去噪; 比较预去噪相邻像素的比较块和预去噪的当前像素的比较块，以获得当前搜索块中每个邻域像素与当前像素之间的相似度; 根据强度参数确定与当前像素相关的每个邻域像素的加权，以及当前搜索块中每个邻域像素与当前像素之间的距离和相似度; 并且根据加权对当前搜索块中的每个邻域像素和当前像素进行加权平均，以获得当前像素的重建值。

    Image denoising method
    3.
    发明授权
    Image denoising method 有权
    图像去噪方法

    公开(公告)号：US08594456B2

    公开(公告)日：2013-11-26

    申请号：US12829447

    申请日：2010-07-02

    申请人： Shu Sian Yang ,  Chuan Hsin Lee ,  Wen Han Yao

    发明人： Shu Sian Yang ,  Chuan Hsin Lee ,  Wen Han Yao

    IPC分类号： G06K9/40 ,  G06K9/38

    CPC分类号： G06T5/002 ,  G06T5/10 ,  G06T2207/20012

    摘要： An image denoising method according to the present invention includes the steps of: sequentially selecting a pixel in an image as a current pixel; dynamically determining a current search block and a strength parameter; transferring the comparison block of each pixel in the current search block to a frequency domain; determining a current frequency basis; obtaining a similarity between each neighborhood pixel and the current pixel in the current search block according to the current frequency basis; determining a weighting of each neighborhood pixel related to the current pixel according to the strength parameter, and a distance and the current pixel in the current search block; and weighted averaging each neighborhood pixel and the current pixel in the current search block according to the weighting so as to obtain a reconstruction value of the current pixel.

    摘要翻译： 根据本发明的图像去噪方法包括以下步骤：顺序地选择图像中的像素作为当前像素; 动态地确定当前搜索块和强度参数; 将当前搜索块中的每个像素的比较块传送到频域; 确定当前频率的基础; 根据当前频率基准获得当前搜索块中每个相邻像素与当前像素之间的相似度; 根据强度参数确定与当前像素相关的每个邻域像素的加权，以及当前搜索块中的距离和当前像素; 并且根据加权对当前搜索块中的每个邻域像素和当前像素进行加权平均，以便获得当前像素的重建值。

    HUMAN FACE DETECTION AND TRACKING DEVICE
    5.
    发明申请
    HUMAN FACE DETECTION AND TRACKING DEVICE 有权
    人脸检测和跟踪装置

    公开(公告)号：US20100328442A1

    公开(公告)日：2010-12-30

    申请号：US12821828

    申请日：2010-06-23

    申请人： Shu Sian Yang ,  Ren Hau Gu ,  Yi Fang Lee ,  Ming Tsan Kao ,  Teo Chin Chiang ,  Chi Chieh Liao ,  Wei Ting Chan ,  Yu Hao Huang ,  Wen Han Yao

    发明人： Shu Sian Yang ,  Ren Hau Gu ,  Yi Fang Lee ,  Ming Tsan Kao ,  Teo Chin Chiang ,  Chi Chieh Liao ,  Wei Ting Chan ,  Yu Hao Huang ,  Wen Han Yao

    IPC分类号： H04N7/18

    CPC分类号： H04N5/232 ,  G06K9/00234 ,  G06K9/00261 ,  G06T7/11 ,  G06T7/136 ,  G06T7/248 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30201 ,  H04N5/23219

    摘要： A human face detection device includes a photosensitive element, a human face detection unit, and a skin color threshold generation unit. The photosensitive element is used for capturing a first image containing a first human face block. The human face detection unit compares the first image with at least one human face feature, so as to detect the first human face block. The skin color threshold generation unit is used for updating a skin color threshold value according to the detected first human face block. The skin color threshold value is used for filtering the first image signal to obtain a candidate region, the human face detection unit compares the candidate region with the at least one human face feature to obtain the first human face block, and the skin color threshold value determines whether the first human face block detected by the human face detection unit is correct.

    摘要翻译： 人脸检测装置包括感光元件，人脸检测单元和肤色阈值生成单元。 感光元件用于捕获包含第一人脸块的第一图像。 人脸检测单元将第一图像与至少一个人脸特征进行比较，以便检测第一人脸区块。 皮肤颜色阈值生成单元用于根据检测到的第一人脸块来更新肤色阈值。 皮肤颜色阈值用于对第一图像信号进行滤波以获得候选区域，人脸检测单元将候选区域与至少一个人脸特征进行比较以获得第一人脸图像块，并且肤色阈值 确定由人脸检测单元检测到的第一人脸部块是否正确。