公开(公告)号：US08493476B2

公开(公告)日：2013-07-23

申请号：US12887171

申请日：2010-09-21

申请人： Makoto Yonaha ,  Hirokazu Kameyama

发明人： Makoto Yonaha ,  Hirokazu Kameyama

IPC分类号： H04N5/262 ,  H04N5/235 ,  H04N5/225 ,  H04N7/12 ,  G06K9/00 ,  G06K9/32

CPC分类号： H04N5/2353 ,  H04N5/2355 ,  H04N5/2356

摘要： The present invention provides a video in which a subject image looks clear while reducing the amount of transmitted data. An image capturing apparatus includes: an image capturing section that successively captures a plurality of images under a plurality of image capturing conditions different from each other; an image generating section that generates an output image by overlapping the plurality of captured images captured under the plurality of image capturing conditions; and an output section that outputs the output image generated by the image generating section. The image capturing section may successively capture the plurality of images by means of exposure in different exposure time lengths from each other. The image capturing section may successively capture the plurality of images also by means of exposure in different aperture openings from each other.

摘要翻译： 本发明提供了一种视频，其中被摄体图像看起来清晰，同时减少了传送的数据量。 一种图像捕获装置包括：图像捕获部分，其在彼此不同的多个图像捕获条件下连续地捕获多个图像; 图像生成部，其通过将在所述多个图像拍摄条件下捕获的所述多个拍摄图像重叠而生成输出图像; 以及输出部，其输出由图像生成部生成的输出图像。 图像拍摄部分可以通过彼此以不同的曝光时间长度的曝光来连续地拍摄多个图像。 图像拍摄部分也可以通过彼此不同孔径开口中的曝光来连续地捕获多个图像。

公开(公告)号：US09129149B2

公开(公告)日：2015-09-08

申请号：US13090083

申请日：2011-04-19

申请人： Hirokazu Kameyama ,  Kouji Yamaguchi

发明人： Hirokazu Kameyama ,  Kouji Yamaguchi

IPC分类号： G06K9/00

CPC分类号： G06K9/00275

摘要： Disclosed is a method for accurately and efficiently detecting a modality of input data, including the steps of projecting the input data into a plurality of projection data using each of a plurality of transformation matrix groups U1·(Σ12U2T), generating a plurality of inverse projection data by performing inverse projection of the transformation matrix groups on the plurality of generated projection data, calculating a correlation between the input data and the generated inverse projection data with respect to each transformation matrix group U1·(Σ12U2T), and identifying a modality represented by a transformation matrix group having a highest calculated correlation as the modality of the input data.

摘要翻译： 公开了一种准确有效地检测输入数据的方式的方法，包括以下步骤：使用多个变换矩阵组U1·（＆Sgr; 12U2T）中的每一个将输入数据投影到多个投影数据中，生成多个 通过对多个生成的投影数据进行逆变换矩阵组的反投影，计算相对于每个变换矩阵组U1·（＆Sgr; 12U2T）的输入数据和所生成的反投影数据之间的相关性，并且识别 由具有最高计算相关性的变换矩阵组表示的模态作为输入数据的模态。

公开(公告)号：US08498483B2

公开(公告)日：2013-07-30

申请号：US12720311

申请日：2010-03-09

申请人： Yukinori Noguchi ,  Hirokazu Kameyama

发明人： Yukinori Noguchi ,  Hirokazu Kameyama

IPC分类号： G06K9/00 ,  G06K9/36

CPC分类号： H04N19/59 ,  G06T7/194 ,  G06T7/70 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30201 ,  H04N19/17 ,  H04N19/20 ,  H04N19/29 ,  H04N19/31 ,  H04N19/33 ,  H04N19/597 ,  H04N19/61

摘要： Provided is an image processing apparatus, including a characteristic region detecting section that detects a characteristic region from an input image; an image generating section that generates, from the input image, a low-quality image, which is of lower quality than the input image, and a characteristic region image, which is of higher quality than the low-quality image at least at the characteristic region; a difference processing section that generates a characteristic region difference image indicating a difference between an image of the characteristic region in the characteristic region image and an image of the characteristic region in the low-quality image; and an encoding section that encodes the characteristic region difference image and the low-quality image.

摘要翻译： 提供一种图像处理装置，包括从输入图像检测特征区域的特征区域检测部分; 图像生成部，从输入图像生成质量低于输入图像的低质量图像，以及特征区域图像，其质量比低质量图像至少具有特征 地区; 差分处理部，其生成表示特征区域图像中的特征区域的图像与低质量图像中的特征区域的图像之间的差异的特征区域差异图像; 以及对特征区域差异图像和低质量图像进行编码的编码部分。

公开(公告)号：US08306316B2

公开(公告)日：2012-11-06

申请号：US12846899

申请日：2010-07-30

申请人： Hirokazu Kameyama

发明人： Hirokazu Kameyama

IPC分类号： G06K9/62

CPC分类号： G06K9/6247 ,  G06K9/4642 ,  G06T3/4053

摘要： The image processing apparatus and method, and the program and the recording medium according to the present invention can make the coefficient vector into high precision by noise elimination or correction utilizing the mutual correlation of the divided image areas in the intermediate eigenspace, and allows relaxation of the input condition and robustness. The high correlation in the divided image areas in the intermediate eigenspace can reduce the divided image areas to be processed, and actualize reduction in processing load and enhancement of the processing speed.

摘要翻译： 根据本发明的图像处理装置和方法以及程序和记录介质可以通过利用中间本征空间中划分的图像区域的相互关联的噪声消除或校正来使系数向量成为高精度，并且允许放松 输入条件和鲁棒性。 中间特征空间中分割图像区域的高相关性可以减少待处理的分割图像区域，并实现处理负载的降低和处理速度的提高。

公开(公告)号：US08078010B2

公开(公告)日：2011-12-13

申请号：US12754718

申请日：2010-04-06

申请人： Hirokazu Kameyama ,  Wataru Ito

发明人： Hirokazu Kameyama ,  Wataru Ito

IPC分类号： G06K9/32

CPC分类号： G06T3/4053 ,  G06T7/32 ,  H04N5/145

摘要： To acquire a high-resolution frame from a plurality of frames sampled from a video image, it is necessary to obtain a high-resolution frame with reduced picture quality degradation regardless of motion of a subject included in the frame. Because of this, between a plurality of contiguous frames FrN and FrN+1, there is estimated a correspondent relationship. Based on the correspondent relationship, the frames FrN+1 and FrN are interposed to obtain first and second interpolated frames FrH1 and FrH2. Based on the correspondent relationship, the coordinates of the frame FrN+1 are transformed, and from a correlation value with the frame FrN, there is obtained a weighting coefficient α(x°, y°) that makes the weight of the first interpolated frame FrH1 greater as a correlation becomes greater. With the weighting coefficient, the first and second interpolated frames are weighted and added to acquire a synthesized frame FrG.

摘要翻译： 为了从从视频图像采样的多个帧获取高分辨率帧，需要获得具有降低的图像质量劣化的高分辨率帧，而不管帧中包括的对象的运动如何。 因此，在多个相邻帧FrN和FrN + 1之间，估计出对应关系。 基于对应关系，插入帧FrN + 1和FrN以获得第一和第二内插帧FrH1和FrH2。 基于对应关系，对帧FrN + 1的坐标进行变换，并且从与帧FrN的相关值获得加权系数α（x°，y°），其使得第一内插帧的权重 相关性较高的FrH1变大。 利用加权系数，对第一和第二内插帧进行加权和相加以获得合成帧FrG。

公开(公告)号：US20110091103A1

公开(公告)日：2011-04-21

申请号：US12972962

申请日：2010-12-20

申请人： Hirokazu Kameyama

发明人： Hirokazu Kameyama

IPC分类号： G06K9/00

CPC分类号： H04N1/62 ,  H04N1/628

摘要： On the basis of image data representing the area of a face image contained in an image represented by applied image data, a color correction value calculating circuit calculates a color correction value and a color image probability calculating circuit calculates the probability that the area of the face image is a color image. A color correction value adjusting circuit then adjusts the color correction value based upon the probability that the area of the face image is a color image. The adjusted color correction value is used in correction processing in an image correcting circuit.

摘要翻译： 基于表示由应用图像数据表示的图像中包含的面部图像的区域的图像数据，颜色校正值计算电路计算颜色校正值，彩色图像概率计算电路计算面部区域的概率 图像是彩色图像。 然后，颜色校正值调整电路基于面部图像的区域是彩色图像的概率来调整颜色校正值。 调整后的色彩校正值用于图像校正电路的校正处理。

公开(公告)号：US07680326B2

公开(公告)日：2010-03-16

申请号：US11082783

申请日：2005-03-18

申请人： Hirokazu Kameyama

发明人： Hirokazu Kameyama

IPC分类号： G06K9/00 ,  G06K9/40

CPC分类号： G06T5/50

摘要： An image processing system has a scale-down section for scaling down frames of a moving image to obtain thumbnail images, a temporary correction value calculation section for calculating a temporary correction value by employing a first feature quantity calculated from the thumbnail image by a feature quantity calculation section, and a temporary correction section for calculating a second feature quantity of a temporarily corrected thumbnail image obtained by correcting each thumbnail image with the temporary correction value. The image processing system further has a target feature quantity calculation section for calculating a target feature quantity of each frame so that the second feature quantities vary smoothly in a temporal direction, an object correction value calculation section for calculating an object correction value so that the first feature quantity becomes the target feature quantity, and a correction section for obtaining a corrected moving image by correcting each frame with the object correction value.

摘要翻译： 图像处理系统具有用于缩小运动图像的帧以缩小图像的缩小部分;临时校正值计算部分，用于通过使用由缩略图图像计算的第一特征量乘以特征量来计算临时校正值 计算部分和临时校正部分，用于计算通过用临时校正值校正每个缩略图图像获得的临时校正的缩略图像的第二特征量。 图像处理系统还具有：目标特征量计算部，其计算各帧的目标特征量，使得第二特征量在时间方向上平滑变化;对象校正值计算部，其计算物体校正值，使得第一 特征量成为目标特征量，以及校正部，用于通过用对象校正值校正每个帧来获得校正的运动图像。

公开(公告)号：US20070223047A1

公开(公告)日：2007-09-27

申请号：US11723682

申请日：2007-03-21

申请人： Hirokazu Kameyama

发明人： Hirokazu Kameyama

IPC分类号： H04N1/23

CPC分类号： H04N5/2628 ,  H04N1/3875

摘要： When trimming is performed on a photograph image obtained by a photography apparatus, a plurality of trimming range candidates is set by analyzing the photograph image. A judgment is made as to whether the zoom magnification ratio of the photography apparatus during photography corresponds to a predetermined limit, the limit being a maximum zoom magnification ratio or a minimum zoom magnification ratio that can be set by the photography apparatus. A trimming range is set by selecting one of the plurality of trimming range candidates. If the zoom magnification ratio is judged to be a magnification ratio corresponding to the predetermined limit, a trimming range candidate that has a smaller or larger range than that of a trimming range candidate selected if the zoom magnification ratio is judged to be a magnification ratio that does not correspond to the predetermined limit is selected as the trimming range.

摘要翻译： 当对由摄影装置获得的照片图像进行修整时，通过分析照片图像来设置多个修剪范围候选。 判断摄影装置中的拍摄装置的变倍倍率是否为预定的限制，该极限是可以由摄影装置设定的最大变倍倍率或最小变倍倍率。 通过选择多个修剪范围候选中的一个来设置修整范围。 如果将变焦倍率判断为与预定极限相对应的倍率，则如果将变焦放大率判定为放大倍率，则修整范围候选具有比选择的修整范围候选者更小或更大的范围 不对应于预定极限作为修剪范围。

公开(公告)号：US20050286099A1

公开(公告)日：2005-12-29

申请号：US11168409

申请日：2005-06-29

申请人： Hirokazu Kameyama

发明人： Hirokazu Kameyama

IPC分类号： G03F3/08 ,  H04N1/62

CPC分类号： H04N1/628 ,  H04N1/62

摘要： Fed image data is used, to respectively calculate two color correction values in two correction value calculating circuits. Further, a target skin color chromaticity value and significance levels indicating which of the two color correction values should be attached importance to are inputted from an input device. Respective confidence levels for the two color correction values are calculated on the basis of the two color correction values and the inputted target skin color chromaticity value. On the basis of the calculated confidence levels, the inputted significance levels, and the two color correction values, both of the confidence levels and the significance levels are reflected, to calculate a new color correction value in a color correction value calculating circuit.

摘要翻译： 使用馈送图像数据，分别计算两个校正值计算电路中的两个颜色校正值。 此外，从输入装置输入指示两个颜色校正值中哪一个重要的目标肤色色度值和显着度水平。 基于两种颜色校正值和输入的目标肤色色度值来计算两种颜色校正值的相关置信水平。 基于所计算的置信水平，反映输入的显着性水平和两种颜色校正值两者的置信水平和显着性水平，以计算颜色校正值计算电路中的新颜色校正值。

公开(公告)号：US08805105B2

公开(公告)日：2014-08-12

申请号：US13457025

申请日：2012-04-26

申请人： Tetsuya Takamori ,  Hirokazu Kameyama

发明人： Tetsuya Takamori ,  Hirokazu Kameyama

IPC分类号： G06K9/36

CPC分类号： G06K9/36 ,  H04N19/132 ,  H04N19/167 ,  H04N19/17 ,  H04N19/172 ,  H04N19/33

摘要： An image compression apparatus capable of compressing an input image that includes a predetermined target object at a high compression ratio while allowing high quality image restoration. In the apparatus, the input image is reduced and compressed. A region of interest corresponding to a predetermined target object is set in the input image. A partial area image of an expanded image of the compressed reduced image corresponding to the region of interest is converted to a high resolution image by applying a prediction process that uses a learning result obtained by learning the predetermined object in advance. With respect to the region of interest portion, a differential image between the image converted to the high resolution and the input image is generated and encoded. Reduced image compression data and differential image encoded data are outputted.

摘要翻译： 一种能够以高压缩率压缩包含预定目标对象的输入图像同时允许高质量图像恢复的图像压缩装置。 在设备中，输入图像被减少和压缩。 在输入图像中设置与预定目标对象相对应的感兴趣区域。 将与感兴趣区域相对应的压缩缩小图像的扩大图像的局部区域图像通过应用预先进行了通过学习该预定对象而获得的学习结果的预测处理而被转换为高分辨率图像。 对于感兴趣区域，生成并编码转换成高分辨率的图像与输入图像之间的差分图像。 输出缩小的图像压缩数据和差分图像编码数据。