公开(公告)号：US07369278B2

公开(公告)日：2008-05-06

申请号：US10731746

申请日：2003-12-08

申请人： Takeshi Nakajima ,  Tsukasa Ito ,  Tsuyoshi Hattori ,  Shoichi Nomura ,  Chizuko Ikeda

发明人： Takeshi Nakajima ,  Tsukasa Ito ,  Tsuyoshi Hattori ,  Shoichi Nomura ,  Chizuko Ikeda

IPC分类号： H04N1/405

CPC分类号： G06T5/005 ,  G06T5/10 ,  G06T2207/20016 ,  G06T2207/20064

摘要： There is described an image-processing apparatus, which makes it possible to compensate for the defect pixel without causing a sense of incongruity in the image. The apparatus includes an image signal acquiring section to acquire the image signals representing an image recorded on a recording medium, a recognizing section to recognize a presence or absence of a defect pixel possibly included in the image signals and a compensating section to compensate for the defect pixel. The compensating section compensates for the defect pixel so that first order differential values of image signals of the defect pixel and those of non-defect pixels adjacent to the defect pixel continue to each other. The compensating section applies a multi-resolution conversion processing to the image signals so as to decompose them into high frequency band components and a low frequency band component, signal intensities of which are compensated for.

摘要翻译： 描述了一种图像处理装置，其可以补偿缺陷像素而不引起图像中的不协调感。 该装置包括图像信号获取部分，用于获取表示记录在记录介质上的图像的图像信号;识别部分，用于识别可能包括在图像信号中的缺陷像素的存在与否;以及补偿部分，用于补偿缺陷 像素。 补偿部补偿缺陷像素，使得缺陷像素的图像信号和与缺陷像素相邻的非缺陷像素的图像信号的一阶微分值彼此连续。 补偿部分对图像信号应用多分辨率转换处理，以便将它们分解成高频带分量和补偿信号强度的低频带分量。

公开(公告)号：US07548656B2

公开(公告)日：2009-06-16

申请号：US10754003

申请日：2004-01-08

申请人： Takeshi Nakajima ,  Tsukasa Ito ,  Tsuyoshi Hattori ,  Shoichi Nomura ,  Chizuko Ikeda

发明人： Takeshi Nakajima ,  Tsukasa Ito ,  Tsuyoshi Hattori ,  Shoichi Nomura ,  Chizuko Ikeda

IPC分类号： G06K9/36 ,  G06K9/46

CPC分类号： G06T5/10 ,  G06T5/002 ,  G06T9/007 ,  G06T2207/20016 ,  G06T2207/20064 ,  G06T2207/20204

摘要： There are described image-processing method and apparatus, which make it possible to reduce the processing load even in the image-processing environment employing the Dyadic Wavelet transform. The apparatus includes a reading section to read an image recorded on a recording medium so as to generate image signals representing the image; a first converting section to apply a multi-resolution conversion processing of at least level 1, which is capable of reducing an image size of the image signals, to the image signals, so as to generate first-converted image signals from the image signals; and a second converting section to apply a Dyadic Wavelet transform of at least level 1 to low frequency band component signals included in the first-converted image signals, so as to generate second-converted image signals from the first-converted image signals. An image size of the first-converted image signals is smaller than that of the image signals.

摘要翻译： 描述了图像处理方法和装置，这使得即使在采用二次小波变换的图像处理环境中也可以减少处理负荷。 该装置包括读取部分，用于读取记录在记录介质上的图像，以产生表示图像的图像信号; 第一转换部分，用于将能够将图像信号的图像尺寸减小的至少1级的多分辨率转换处理应用于图像信号，以便从图像信号生成第一转换图像信号; 以及第二转换部分，用于将包含在第一转换图像信号中的低频带分量信号应用至少1级的二维小波变换，以便从第一转换图像信号产生第二转换图像信号。 第一转换图像信号的图像尺寸小于图像信号的图像尺寸。

公开(公告)号：US07577290B2

公开(公告)日：2009-08-18

申请号：US11017918

申请日：2004-12-22

申请人： Chizuko Ikeda ,  Shoichi Nomura

发明人： Chizuko Ikeda ,  Shoichi Nomura

IPC分类号： G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/00597

摘要： The image for the face candidate region is obtained, extraction conditions are determined for extracting the eye and the mouth pixels from the face candidate region based on the size of the face candidate region. The eye pixels and the mouth pixels are then extracted from the face candidate region based on the determined extraction conditions, and then the area ratio of the eyes and the area ratio of mouth are calculated for the face candidate region based on the eye pixels and the mouth pixels. Next the area ratio for the eyes and mouth is input into the neural network and a determinations is made as to whether the face candidate region is the face of a person using the neural network.

摘要翻译： 获得面部候选区域的图像，根据面部候选区域的大小，确定从面部候选区域提取眼睛和口部像素的提取条件。 然后基于所确定的提取条件，从面部候选区域提取眼睛像素和嘴部像素，然后基于眼睛像素和面部候选区域计算眼睛的面积比和嘴部的面积比， 嘴像。 接下来，将眼睛和嘴的面积比率输入到神经网络中，并且确定脸部候选区域是否是使用神经网络的人的面部。

公开(公告)号：US20050232482A1

公开(公告)日：2005-10-20

申请号：US11017918

申请日：2004-12-22

申请人： Chizuko Ikeda ,  Shoichi Nomura

发明人： Chizuko Ikeda ,  Shoichi Nomura

IPC分类号： G06T1/00 ,  G06K9/00 ,  G06K9/46 ,  G06T1/40 ,  G06T7/00

CPC分类号： G06K9/00281 ,  G06K9/00597

摘要： The image for the face candidate region is obtained, extraction conditions are determined for extracting the eye and the mouth pixels from the candidate region based on the size of the face candidate region. The eye pixels and the mouth pixels are then extracted from the face candidate region based on the determined extraction conditions, and then the area ratio of the eyes and the area ratio of mouth are calculated for the face candidate region based on the eye pixels and the mouth pixels. Next the area ratio for the eyes and mouth is input into the neural network and a determinations is made as to whether the face candidate region is the face of a person using the neural network.

摘要翻译： 获得面部候选区域的图像，根据脸部候选区域的大小，确定从候选区域提取眼睛和嘴部像素的提取条件。 然后基于所确定的提取条件，从面部候选区域提取眼睛像素和嘴部像素，然后基于眼睛像素和面部候选区域计算眼睛的面积比和嘴部的面积比， 嘴像。 接下来，将眼睛和嘴的面积比率输入到神经网络中，并且确定脸部候选区域是否是使用神经网络的人的面部。

公开(公告)号：US07324702B2

公开(公告)日：2008-01-29

申请号：US10647646

申请日：2003-08-25

申请人： Hiroaki Takano ,  Tsukasa Ito ,  Chizuko Ikeda

发明人： Hiroaki Takano ,  Tsukasa Ito ,  Chizuko Ikeda

IPC分类号： B06K9/40 ,  G03F3/08

CPC分类号： H04N1/603

摘要： An image processing method for subjecting captured-image data outputting from an image-capturing device to an optimization processing for appreciation to produce viewing image referred image data. The image processing method has the step of conducting a pre-processing before the optimization processing is carried out, wherein the pre-processing includes the transformation of the frequency characteristic of the captured-image data into the scene-referred frequency characteristic by removing the effect of a frequency characteristic specific to the image-capturing device from the frequency characteristic of the captured-image data.

摘要翻译： 一种图像处理方法，用于将从图像捕获装置输出的捕获图像数据用于欣赏的优化处理，以产生观看图像参考图像数据。 图像处理方法具有在执行优化处理之前进行预处理的步骤，其中预处理包括通过去除效果来将拍摄图像数据的频率特性变换为场景参考频率特性 根据捕获图像数据的频率特性，对图像捕获装置特有的频率特性。

公开(公告)号：US06801296B2

公开(公告)日：2004-10-05

申请号：US10366995

申请日：2003-02-14

申请人： Chizuko Ikeda ,  Tsukasa Ito ,  Hiroaki Takano

发明人： Chizuko Ikeda ,  Tsukasa Ito ,  Hiroaki Takano

IPC分类号： G03B2752

CPC分类号： G03B27/32

摘要： An image processing method to conduct an image processing on image signals indicating an image obtained through photographing by a photographing apparatus for generating image signals for output. The image processing method has a determining process to determine a content of image processing to be conducted on the image signals based on information about environment light in the course of photographing, information about flashlight in the course of photographing, and on at least one of information about zoom magnification in the course of photographing and information about ISO speed.

摘要翻译： 一种对由图像信号进行图像处理的图像处理方法，该图像信号指示通过摄影装置拍摄得到的图像，用于产生用于输出的图像信号。 该图像处理方法具有确定处理，用于基于在拍摄过程中关于环境光的信息，在拍摄过程中关于手电筒的信息，以及至少一个信息来确定要对图像信号进行的图像处理的内容 关于拍摄过程中的变焦倍率以及关于ISO感光度的信息。

公开(公告)号：US06739767B2

公开(公告)日：2004-05-25

申请号：US10366874

申请日：2003-02-14

申请人： Chizuko Ikeda ,  Tsukasa Ito ,  Hiroaki Takano

发明人： Chizuko Ikeda ,  Tsukasa Ito ,  Hiroaki Takano

IPC分类号： G03B300

CPC分类号： G03B27/32 ,  H04N1/6086

摘要： An image processing method to conduct an image processing on image signals indicating a photographed image for generating image signals for output, having the steps of: detecting an area in the photographed image where the mixed ratio of flashlight to environment light in the course of photographing is greater than a prescribed value, based on respective information including information about environment light in the course of photographing, information about flashlight in the course of photographing, and at least one of information about zoom magnification in the course of photographing, information about ISO speed and information about a subject distance in the course of photographing; and determining a content of image processing in accordance with a ratio of the area detected to the total area of the photographed image.

摘要翻译： 一种图像处理方法，用于对指示用于产生用于输出的图像信号的拍摄图像的图像信号进行图像处理，具有以下步骤：检测在拍摄过程中手电筒与环境光的混合比例的拍摄图像中的区域是 基于在拍摄过程中包括关于环境光的信息，在拍摄过程中关于手电筒的信息以及关于摄影过程中关于变焦倍率的信息中的至少一个的信息的相关信息大于规定值，关于ISO感光度的信息，以及 有关拍摄过程中拍摄对象距离的信息; 以及根据检测到的区域与拍摄图像的总面积的比率来确定图像处理的内容。