-
公开(公告)号：US20120121173A1
公开(公告)日：2012-05-17
申请号：US12999771
申请日：2010-04-30
IPC分类号： G06K9/46
CPC分类号： G06K9/6289 , G06K9/00234 , G06K9/00261 , G06T7/11 , G06T2207/10024 , G06T2207/20016 , G06T2207/30201
摘要： The present invention relates to an image processing apparatus and method, and a program that are capable of more easily identifying an area of a subject in an image.A luminance information extraction unit 21 through to a motion information extraction unit 25 extract predetermined information from an input image and create an information map indicating feature quantities of features possessed by an area of a subject of the input image. Furthermore, the luminance information extraction unit 21 through to the motion information extraction unit 25 subtract an average value of the pixel values of the pixels of the entire information map from the pixel value of each pixel of the created information map so as to normalize the information map. As a result, the information map can be normalized, and noise can be removed with a simple process when compared to a case in which the information map is normalized using a DOG filter. A subject map creation unit 26 linearly combines each information map, and creates a subject map indicating the likelihood of an area being a subject in each area of an input image. The present invention can be applied to an image processing apparatus.
摘要翻译： 本发明涉及能够更容易地识别图像中的被摄体的区域的图像处理装置和方法以及程序。 亮度信息提取单元21至运动信息提取单元25从输入图像中提取预定信息，并创建指示输入图像的对象区域拥有的特征的特征量的信息映射。 此外，亮度信息提取单元21至运动信息提取单元25从创建的信息图的每个像素的像素值中减去整个信息图的像素的像素值的平均值，以便将信息标准化 地图。 结果，与使用DOG滤波器对信息图进行归一化的情况相比，信息图可以被归一化，并且可以用简单的过程去除噪声。 被摄体图生成部26对各信息映像进行线性组合，并生成表示输入图像的各区域中的被摄体的区域的可能性的被摄体图。 本发明可以应用于图像处理装置。
-
公开(公告)号：US08548247B2
公开(公告)日：2013-10-01
申请号：US13002958
申请日：2010-05-06
CPC分类号： H04N5/232 , G06K9/00234 , G06T7/11 , G06T2207/30201
摘要： The present invention relates to an image processing apparatus and method, and a program that make it possible to more accurately specify a photographic subject in an image.A photographic subject map generating unit 21 generates, based on an input image, a photographic subject map indicating the likeliness of each region of the input image being a region of a photographic subject. A gradient map generating unit 22 generates a gradient map indicating the degree of change of the likeliness of the photographic subject map being a photographic subject. A threshold processing unit 23 and a threshold processing unit 24 binarize the gradient map using a high threshold THh and a low threshold TH1, and obtain threshold maps. A composite map generating unit 25 generates a composite map indicating the likeliness of each region of the input image being a photographic subject by regarding that, among regions specified as being likely to be a photographic subject based on the threshold map of the low threshold TH1, a region including a region specified as being likely to be a photographic subject based on the threshold map of the high threshold THh is a region of a photographic subject. The present invention is applicable to an image processing apparatus.
摘要翻译： 本发明涉及一种图像处理装置和方法以及使得能够更准确地指定图像中的被摄体的程序。 摄影对象图生成部21基于输入图像生成表示作为拍摄对象的区域的输入图像的各区域的可能性的拍摄对象图。 梯度图生成单元22生成表示拍摄对象的拍摄对象地图的可能性的变化程度的梯度图。 阈值处理单元23和阈值处理单元24使用高阈值THh和低阈值TH1对梯度图进行二值化，并获得阈值图。 复合地图生成单元25通过关于基于低阈值TH1的阈值映射指定为可拍摄对象的区域，生成表示作为拍摄对象的输入图像的各区域的可能性的复合图， 基于高阈值THh的阈值图，指定为可能是拍摄对象的区域的区域是拍摄对象的区域。 本发明可应用于图像处理装置。
-
公开(公告)号：US08577137B2
公开(公告)日：2013-11-05
申请号：US12999771
申请日：2010-04-30
IPC分类号： G06K9/00
CPC分类号： G06K9/6289 , G06K9/00234 , G06K9/00261 , G06T7/11 , G06T2207/10024 , G06T2207/20016 , G06T2207/30201
摘要： The present invention relates to an image processing apparatus and method, and a program that are capable of more easily identifying an area of a subject in an image.A luminance information extraction unit 21 through to a motion information extraction unit 25 extract predetermined information from an input image and create an information map indicating feature quantities of features possessed by an area of a subject of the input image.Furthermore, the luminance information extraction unit 21 through to the motion information extraction unit 25 subtract an average value of the pixel values of the pixels of the entire information map from the pixel value of each pixel of the created information map so as to normalize the information map. As a result, the information map can be normalized, and noise can be removed with a simple process when compared to a case in which the information map is normalized using a DOG filter. A subject map creation unit 26 linearly combines each information map, and creates a subject map indicating the likelihood of an area being a subject in each area of an input image. The present invention can be applied to an image processing apparatus.
摘要翻译： 本发明涉及能够更容易地识别图像中的被摄体的区域的图像处理装置和方法以及程序。 亮度信息提取单元21至运动信息提取单元25从输入图像中提取预定信息，并创建指示输入图像的被摄体区域拥有的特征的特征量的信息映射。 此外，亮度信息提取单元21至运动信息提取单元25从创建的信息图的每个像素的像素值中减去整个信息图的像素的像素值的平均值，以便将信息标准化 地图。 结果，与使用DOG滤波器对信息图进行归一化的情况相比，信息图可以被归一化，并且可以用简单的过程去除噪声。 被摄体图生成部26对各信息映像进行线性组合，并生成表示输入图像的各区域中的被摄体的区域的可能性的被摄体图。 本发明可以应用于图像处理装置。
-
公开(公告)号：US20120051650A1
公开(公告)日：2012-03-01
申请号：US13002958
申请日：2010-05-06
IPC分类号： G06K9/46
CPC分类号： H04N5/232 , G06K9/00234 , G06T7/11 , G06T2207/30201
摘要： The present invention relates to an image processing apparatus and method, and a program that make it possible to more accurately specify a photographic subject in an image.A photographic subject map generating unit 21 generates, based on an input image, a photographic subject map indicating the likeliness of each region of the input image being a region of a photographic subject. A gradient map generating unit 22 generates a gradient map indicating the degree of change of the likeliness of the photographic subject map being a photographic subject. A threshold processing unit 23 and a threshold processing unit 24 binarize the gradient map using a high threshold THh and a low threshold TH1, and obtain threshold maps. A composite map generating unit 25 generates a composite map indicating the likeliness of each region of the input image being a photographic subject by regarding that, among regions specified as being likely to be a photographic subject based on the threshold map of the low threshold TH1, a region including a region specified as being likely to be a photographic subject based on the threshold map of the high threshold THh is a region of a photographic subject. The present invention is applicable to an image processing apparatus.
摘要翻译： 本发明涉及一种图像处理装置和方法以及使得能够更准确地指定图像中的被摄体的程序。 摄影对象图生成部21基于输入图像生成表示作为拍摄对象的区域的输入图像的各区域的可能性的拍摄对象图。 梯度图生成单元22生成表示拍摄对象的拍摄对象地图的可能性的变化程度的梯度图。 阈值处理单元23和阈值处理单元24使用高阈值THh和低阈值TH1对梯度图进行二值化，并获得阈值图。 复合地图生成单元25通过关于基于低阈值TH1的阈值映射指定为可拍摄对象的区域，生成表示作为拍摄对象的输入图像的各区域的可能性的复合图， 基于高阈值THh的阈值图，指定为可能是拍摄对象的区域的区域是拍摄对象的区域。 本发明可应用于图像处理装置。
-
公开(公告)号：US08300969B2
公开(公告)日：2012-10-30
申请号：US12336477
申请日：2008-12-16
申请人： Masatoshi Yokokawa , Jun Murayama , Kazuki Aisaka
发明人： Masatoshi Yokokawa , Jun Murayama , Kazuki Aisaka
IPC分类号： G06K9/40
CPC分类号： G06K9/4609 , G06T7/0002 , G06T7/13 , G06T2207/20016 , G06T2207/20021
摘要： An edge map creation unit detects an edge intensity of an input image in units of three types of blocks having different sizes. An operation parameter adjustment unit sets initial values of an edge reference value and an extraction reference value on the basis of a dynamic range which is a difference between the maximum and minimum values of the edge intensity. An edge point extraction unit extracts an edge point from the input image on the basis of the edge reference value. Until an extraction amount determination unit determines that the edge point extraction amount is appropriate on the basis of the extraction reference value, the operation parameter adjustment unit repeatedly performs a processing of adjusting the edge reference value, and the edge point extraction unit repeatedly performs a processing of extracting the edge point from the input image on the basis of the adjusted edge reference value.
摘要翻译： 边缘图创建单元以具有不同大小的三种类型的块为单位来检测输入图像的边缘强度。 操作参数调整单元基于作为边缘强度的最大值和最小值之间的差的动态范围来设定边缘基准值和提取基准值的初始值。 边缘点提取单元基于边缘参考值从输入图像中提取边缘点。 直到提取量确定单元基于提取参考值确定边缘点提取量是适当的，操作参数调整单元重复执行调整边缘参考值的处理，并且边缘点提取单元重复执行处理 基于经调整的边缘参考值从输入图像中提取边缘点。
-
公开(公告)号：US20120070102A1
公开(公告)日：2012-03-22
申请号：US13056900
申请日：2010-05-31
申请人： Masatoshi Yokokawa , Kazuki Aisaka , Jun Murayama
发明人： Masatoshi Yokokawa , Kazuki Aisaka , Jun Murayama
IPC分类号： G06K9/36
CPC分类号： H04N17/002 , G06T7/0002 , G06T2207/10024 , G06T2207/20016 , G06T2207/20021 , G06T2207/30168 , G06T2207/30201 , H04N5/23222
摘要： The present invention relates to an image processing apparatus and method, and a program that are capable of more appropriately evaluating the image-capture state of an image.A blur degree score calculation unit 23 through to a chroma score calculation unit 27 extract a feature quantity of a pre-specified feature from an input image, and calculate a feature-by-feature score indicating an evaluation for the input image on the basis of the feature. For example, the luminance score calculation unit 24 extracts, as a feature quantity, a luminance value from the input image, and calculates a luminance score indicating an evaluation based on the distribution of the luminance values in the subject portion of the input image. The overall score calculation unit 28 calculates an overall score indicating the evaluation of the image-capture state of the input image from each feature-by-feature score. As described above, when each feature-by-feature score is to be calculated, by extracting each feature quantity and obtaining a score from the area of the input image suitable for the feature, it is possible to more appropriately evaluate the input image. The present invention can be applied to an image processing apparatus.
摘要翻译： 本发明涉及能够更适当地评价图像的图像拍摄状态的图像处理装置和方法以及程序。 模糊度分数计算单元23至色度分数计算单元27从输入图像中提取预定特征的特征量，并且基于以下方式计算表示对输入图像的评估的特征分数 的功能。 例如，亮度分数计算单元24从输入图像中提取亮度值作为特征量，并且基于输入图像的对象部分中的亮度值的分布来计算指示评估的亮度分数。 总分计算单元28从每个特征点分数计算指示输入图像的图像捕获状态的评估的总分。 如上所述，当要计算每个要素特征得分时，通过从适合于特征的输入图像的区域中提取每个特征量并获得分数，可以更适当地评估输入图像。 本发明可以应用于图像处理装置。
-
公开(公告)号：US20110206295A1
公开(公告)日：2011-08-25
申请号：US13022145
申请日：2011-02-07
IPC分类号： G06K9/32
CPC分类号： H04N1/3875
摘要： An image processing apparatus includes: a subject region detection unit detecting regions of subjects included in an input image; a cropped region setting unit setting a region including all of the regions of the detected subjects as a cropped region; an expansion region addition unit adding an expansion region to expand an end of the cropped region only by a predetermined width; a cutting unit cutting a cut image formed from a cut region including the cropped region and the expansion region from the input image; a subject adaptation size change unit changing a size of an image formed from the cut region by deleting a region where an influence on the subjects is small in the cut image; and an entire image size changing unit changing the size of the entire image changed in size by the subject adaptation size change unit at a predetermined ratio.
摘要翻译： 一种图像处理装置，包括：对象区域检测单元，检测输入图像中包含的被摄体的区域; 裁剪区域设定单元，将包括检测到的被摄体的全部区域的区域设定为裁剪区域; 扩展区域添加单元，其添加扩展区域，以使裁剪区域的端部仅扩展预定宽度; 切割单元，从输入图像切割由包括裁剪区域和扩展区域的切割区域形成的切割图像; 主题适应尺寸改变单元，通过删除在切割图像中对被摄体的影响小的区域来改变由切割区域形成的图像的尺寸; 以及整个图像尺寸改变单元，以预定比例改变由主体适配尺寸改变单元改变尺寸的整个图像的尺寸。
-
公开(公告)号：US20100259649A1
公开(公告)日：2010-10-14
申请号：US12753741
申请日：2010-04-02
申请人： Kazuki Aisaka , Masatoshi Yokokawa , Jun Murayama , Takefumi Nagumo , Ken Tamayama , Tatsuo Fujiwara , Tamaki Eyama
发明人： Kazuki Aisaka , Masatoshi Yokokawa , Jun Murayama , Takefumi Nagumo , Ken Tamayama , Tatsuo Fujiwara , Tamaki Eyama
IPC分类号： H04N5/217
摘要： A photographing apparatus is provided, which includes: a correction data acquiring section that acquires correction data for image correction; a recording section that records the correction data acquired by the correction data acquiring section; a photographing condition acquiring section that acquires image photographing conditions; a retrieving section that retrieves the correction data, corresponding to the photographing conditions acquired by the photographing condition acquiring section, from the correction data recorded in the recording section; and a photographing section that photographs an image on the basis of the correction data retrieved by the retrieving section.
摘要翻译： 提供一种拍摄设备，包括：校正数据获取部分，获取用于图像校正的校正数据; 记录部，其记录由所述校正数据获取部获取的校正数据; 拍摄条件获取部，其获取图像拍摄条件; 检索部分，从记录在记录部分中的校正数据中检索与摄影条件获取部分获取的拍摄条件对应的校正数据; 以及摄影部，其基于由检索部检索出的校正数据拍摄图像。
-
公开(公告)号：US08478072B2
公开(公告)日：2013-07-02
申请号：US13012779
申请日：2011-01-24
IPC分类号： G06K9/36
CPC分类号： G06T11/60
摘要： An image processing device includes a subject region detector that detects a subject region from an input image; a cutting unit that cuts an image of the subject region from the input image; a priority calculator that calculates a priority of each of predetermined regions on a boundary with respect to the subject region, for the input image; a retrieval unit that retrieves a region similar to an image of a predetermined region with a top priority from among the priorities, from the input image after the image of the subject region is cut; a recovery unit that recovers the subject region by copying an image of an adjacent region that is adjacent to the region similar to the predetermined region retrieved by the retrieval unit and includes a region corresponding to a region cut as the subject region, and by pasting the image obtained by copying onto the region that is adjacent to the predetermined region with the top priority and cut as the subject region; and a composition unit that combines the image of the subject region cut by the cutting unit with the image with the subject region recovered by the recovery unit.
摘要翻译： 图像处理装置包括从输入图像检测被摄体区域的被摄体区域检测器; 切割单元，其从所述输入图像切割所述对象区域的图像; 对于所述输入图像，计算相对于所述对象区域的边界上的每个预定区域的优先级的优先级计算器; 检索单元，从所述对象区域的图像之后的输入图像中切出与所述优先级中具有最高优先级的预定区域的图像类似的区域; 复原单元，通过复制与由检索单元检索到的与预定区域相似的区域相邻的相邻区域的图像来恢复被摄体区域，并且包括对应于被切割的区域的区域作为对象区域，并且通过粘贴 通过复制到与优先级最高的预定区域相邻的区域并被切割为对象区域而获得的图像; 以及合成单元，其将由切割单元切割的被摄体区域的图像与由恢复单元回收的对象区域的图像组合。
-
公开(公告)号：US08326082B2
公开(公告)日：2012-12-04
申请号：US13022145
申请日：2011-02-07
IPC分类号： G06K9/36
CPC分类号： H04N1/3875
摘要： An image processing apparatus includes: a subject region detection unit detecting regions of subjects included in an input image; a cropped region setting unit setting a region including all of the regions of the detected subjects as a cropped region; an expansion region addition unit adding an expansion region to expand an end of the cropped region only by a predetermined width; a cutting unit cutting a cut image formed from a cut region including the cropped region and the expansion region from the input image; a subject adaptation size change unit changing a size of an image formed from the cut region by deleting a region where an influence on the subjects is small in the cut image; and an entire image size changing unit changing the size of the entire image changed in size by the subject adaptation size change unit at a predetermined ratio.
摘要翻译： 一种图像处理装置，包括：对象区域检测单元，检测输入图像中包含的被摄体的区域; 裁剪区域设定单元，将包括检测到的被摄体的全部区域的区域设定为裁剪区域; 扩展区域添加单元，其添加扩展区域，以使裁剪区域的端部仅扩展预定宽度; 切割单元，从输入图像切割由包括裁剪区域和扩展区域的切割区域形成的切割图像; 主题适应尺寸改变单元，通过删除在切割图像中对被摄体的影响小的区域来改变由切割区域形成的图像的尺寸; 以及整个图像尺寸改变单元，以预定比例改变由主体适配尺寸改变单元改变尺寸的整个图像的尺寸。
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.028 秒)
