专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11488279B2 Image processing apparatus, image processing system, imaging apparatus, image processing method, and storage medium 有权
公开(公告)号：US11488279B2
公开(公告)日：2022-11-01
申请号：US16688150
申请日：2019-11-19
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06T1/00 , G06T1/60 , G06T7/00 , G06T1/20
摘要： An image processing apparatus includes an image acquisition unit configured to acquire a plurality of temporally different images each of which has degraded by a turbulence, a parameter acquisition unit configured to acquire a learned network parameter, and a measurement unit configured to measure a turbulence strength from the plurality of images using the network parameter and a neural network.

2. 发明授权

US11354537B2 Image processing apparatus, imaging apparatus, image processing method, and storage medium 有权
公开(公告)号：US11354537B2
公开(公告)日：2022-06-07
申请号：US16715042
申请日：2019-12-16
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06K9/62 , G06N3/04 , G06N3/08 , G06T5/00 , G06V10/44
摘要： An image processing apparatus includes a main unit configured to convert an input image into information of a first feature amount using a first convolutional neural network having at least two layers, an input unit configured to convert the input image into information of a second feature amount using a second convolutional neural network, and an output unit configured to convert information of a third feature amount generated by adding the information of the first feature amount and the information of the second feature amount to each other, into an output image using a third convolutional neural network.

3. 发明申请

US20200167885A1 IMAGE PROCESSING APPARATUS, IMAGE PROCESSING SYSTEM, IMAGING APPARATUS, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM 审中-公开
公开(公告)号：US20200167885A1
公开(公告)日：2020-05-28
申请号：US16688150
申请日：2019-11-19
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06T1/00 , G06T1/60 , G06T1/20 , G06T7/00
摘要： An image processing apparatus includes an image acquisition unit configured to acquire a plurality of temporally different images each of which has degraded by a turbulence, a parameter acquisition unit configured to acquire a learned network parameter, and a measurement unit configured to measure a turbulence strength from the plurality of images using the network parameter and a neural network.

4. 发明申请

US20180336662A1 IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, IMAGE CAPTURING APPARATUS, AND STORAGE MEDIUM 审中-公开
公开(公告)号：US20180336662A1
公开(公告)日：2018-11-22
申请号：US15978555
申请日：2018-05-14
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06T3/40 , G06T5/00
摘要： An image processing apparatus includes a weighting unit configured to calculate an error between an estimated image obtained by providing an input image to a convolution neural network and a ground truth image corresponding to the input image and to weight a frequency component of the error, and a parameter setter configured to calculate a gradient based on the weighted error, and to set a network parameter for the convolution neural network.

5. 发明申请

US20140055595A1 IMAGE RESTORATION METHOD, IMAGE RESTORATION APPARATUS, AND IMAGE-PICKUP APPARATUS 有权
标题翻译：图像恢复方法，图像恢复装置和图像拾取装置
公开(公告)号：US20140055595A1
公开(公告)日：2014-02-27
申请号：US13968628
申请日：2013-08-16
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： H04N7/18
CPC分类号： H04N7/18 , G02B21/365 , G06T5/002 , G06T2207/10056 , G06T2207/20081 , G06T2207/30024
摘要： A method includes performing an approximate partially coherent imaging operation for elements of a first basis generated from a model image having no noise and no blur, and generating based upon the first basis a second basis that is blurred, the approximate partially coherent imaging operation being expressed by a convolution integral on an eigenfunction corresponding to a maximum eigenvalue of a Kernel matrix and each element of the first basis, generating an intermediate image in which each pixel value of the observed image that has been denoised is replaced with its square root, and obtaining a restored image by approximating each of a plurality of patches that are set to entirely cover the intermediate image, using a linear combination of elements of the first basis and linear combination coefficients obtained when each patch is approximated by a linear combination of elements of the second basis.
摘要翻译：一种方法包括对从没有噪声和无模糊的模型图像产生的第一基础的元素执行近似部分相干成像操作，以及基于第一基础生成模糊的第二基础，表示近似部分相干成像操作通过在对应于内核矩阵的最大特征值和第一基础的每个元素的特征函数上积分的卷积，生成中间图像，其中已经去噪的观察图像的每个像素值被其平方根替换，并且获得通过使用所述第一基底和线性组合系数的元素的线性组合来逼近被设置为完全覆盖所述中间图像的多个斑块中的每一个的恢复图像，所述第一基底和线性组合系数的元素通过所述第二基底的元素的线性组合基础。

6. 发明授权

US11080832B2 Image processing method, image processing apparatus, imaging apparatus, and storage medium 有权
公开(公告)号：US11080832B2
公开(公告)日：2021-08-03
申请号：US16576937
申请日：2019-09-20
申请人： CANON KABUSHIKI KAISHA
发明人： Chiaki Inoue , Yoshinori Kimura
IPC分类号： G06T5/50 , G06T5/00 , H04N5/232 , H04N5/247
摘要： An image processing method includes the steps of acquiring a first image, acquiring a second image that has a noise amount larger than that of the first image and has high frequency components of an object more than those of the first image, and inputting the first image and the second image into a neural network, and generating a third image having the high frequency components of the object more than those of the first image and having the noise amount smaller than that of the second image.

7. 发明申请

US20200098100A1 IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, IMAGING APPARATUS, AND STORAGE MEDIUM 审中-公开
公开(公告)号：US20200098100A1
公开(公告)日：2020-03-26
申请号：US16576937
申请日：2019-09-20
申请人： CANON KABUSHIKI KAISHA
发明人： Chiaki Inoue , Yoshinori Kimura
IPC分类号： G06T5/50 , G06T5/00 , H04N5/247 , H04N5/232
摘要： An image processing method includes the steps of acquiring a first image, acquiring a second image that has a noise amount larger than that of the first image and has high frequency components of an object more than those of the first image, and inputting the first image and the second image into a neural network, and generating a third image having the high frequency components of the object more than those of the first image and having the noise amount smaller than that of the second image.

8. 发明授权

US09443287B2 Image processing method and apparatus using trained dictionary 有权
标题翻译：使用训练有素的字典的图像处理方法和装置
公开(公告)号：US09443287B2
公开(公告)日：2016-09-13
申请号：US14612756
申请日：2015-02-03
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06K9/00 , G06T5/00 , G06T3/40
CPC分类号： G06T5/002 , G06K9/00 , G06T3/4053 , G06T2207/20081
摘要： The image processing method includes providing first dictionaries produced by dictionary learning and second dictionaries corresponding to the first dictionaries, performing, on each first dictionary, a process to approximate the first image by linear combination of elements of the first dictionary so as to produce a linear combination coefficient and thereby acquiring multiple linear combination coefficients, and calculating, for each linear combination coefficient, a ratio between a largest coefficient element and a second-largest coefficient element and selecting a specific linear combination coefficient in which the ratio is largest among the multiple linear combination coefficients. The method further includes selecting, from the multiple second dictionaries, a specific dictionary corresponding to the first dictionary for which the specific linear combination coefficient is produced, and producing the second image by using linear combination of the specific linear combination coefficient and elements of the specific dictionary.
摘要翻译：图像处理方法包括提供由字典学习产生的第一词典和对应于第一词典的第二词典，在每个第一辞典中，通过第一词典的元素的线性组合对第一图像进行近似，从而产生线性从而获得多个线性组合系数，并且对于每个线性组合系数，计算最大系数元素和第二最大系数元素之间的比率，并且选择其中该多个线性中的比率最大的特定线性组合系数组合系数。该方法还包括从多个第二词典中选择与产生特定线性组合系数的第一辞典对应的特定字典，并且通过使用特定线性组合系数和特定线性组合系数的元素的线性组合来产生第二图像字典。

9. 发明授权

US09436867B2 Image processing method using sparse coding, and non-transitory computer-readable storage medium storing image processing program and image processing apparatus 有权
标题翻译：使用稀疏编码的图像处理方法，以及存储图像处理程序和图像处理装置的非暂时性计算机可读存储介质
公开(公告)号：US09436867B2
公开(公告)日：2016-09-06
申请号：US14573151
申请日：2014-12-17
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06K9/36 , G06K9/00 , G06K9/62 , H04N19/94 , G06K9/40
CPC分类号： G06K9/0014 , G06K9/40 , G06K9/6255 , H04N19/94
摘要： The method produces, from a first image, a second image with sparse coding. The method produces, from the first image, a processing intermediate image having a pixel value distribution that a difference among pixel values in a region of the intermediate image is equal to a DC component in a corresponding region of the first image, performs a first process of acquiring, using an AC component in a first region of the intermediate image and a basis produced by dictionary learning, an AC component in a second region, performs a second process of acquiring a difference among pixel values in the second region as a DC component in a corresponding region of the second image, and repeats the first and second processes with changing a position of the first region in the intermediate image to acquire DC components in regions of the second image.
摘要翻译：该方法从第一图像产生具有稀疏编码的第二图像。该方法从第一图像生成具有像素值分布的处理中间图像，其中中间图像的区域中的像素值之间的差等于第一图像的相应区域中的DC分量，执行第一处理在所述中间图像的第一区域中使用AC分量和通过字典学习产生的基准来获取第二区域中的AC分量，执行将所述第二区域中的像素值之间的差作为DC分量的第二处理在所述第二图像的相应区域中，并且通过改变所述中间图像中的所述第一区域的位置来重复所述第一和第二处理，以获取所述第二图像的区域中的DC分量。

10. 发明申请

US20160078312A1 IMAGE PROCESSING METHOD AND APPARATUS USING TRAINING DICTIONARY 审中-公开
标题翻译：使用训练词典的图像处理方法和装置
公开(公告)号：US20160078312A1
公开(公告)日：2016-03-17
申请号：US14847248
申请日：2015-09-08
申请人： CANON KABUSHIKI KAISHA
发明人： Yoshinori Kimura
IPC分类号： G06K9/62 , G06T7/00
CPC分类号： G06K9/627 , G06K9/00624 , G06K9/4619 , G06K9/6255
摘要： The image processing method extracts, from a first image, partial areas such that they overlap one another, and provides, by dictionary learning using model images corresponding to multiple types, a set of linear combination approximation bases and a set of classification bases to acquire classification identification values indicating the multiple types to which each partial area belongs. The method approximates the partial areas by linear combination of the linear combination approximation bases to acquire linear combination coefficients, sets the classification identification values by a linear combination of the classification bases and the linear combination coefficients, sets, for each pixel of the first image, one classification identification value from those set for two or more of the partial areas including that pixel, and produces the second image whose each pixel corresponds to that of the first image and has the one classification identification value.
摘要翻译：图像处理方法从第一图像提取部分区域使得它们彼此重叠，并且通过使用对应于多种类型的模型图像的字典学习提供一组线性组合近似基准和一组分类基础以获取分类指示每个部分区域所属的多种类型的识别值。该方法通过线性组合近似基线的线性组合逼近部分区域以获取线性组合系数，通过对第一图像的每个像素的分类基和线性组合系数集合的线性组合来设置分类识别值，一个分类识别值，从包括该像素的两个或更多个部分区域设置的分类识别值，并且产生其每个像素对应于第一图像的第二图像并具有一个分类识别值的第二图像。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式