公开(公告)号：US20090174795A1

公开(公告)日：2009-07-09

申请号：US12260435

申请日：2008-10-29

申请人： Yutaka KATO ,  Yutaka KIUCHI

发明人： Yutaka KATO ,  Yutaka KIUCHI

IPC分类号： H04N9/68

CPC分类号： H04N5/23293 ,  H04N5/23222 ,  H04N5/23232 ,  H04N5/2351 ,  H04N5/2353 ,  H04N9/045

摘要： There is provided an image processing apparatus capable of properly setting a photographing condition in consideration of time allowable for each processing; the image processing apparatus capable of properly setting the photographing condition while referring to an actually generated composite image; the image processing apparatus capable of properly setting the photographing condition even by a user who has no background knowledge; and the image processing apparatus capable of determining whether or not image composition processing is properly executed even by the user who has no background knowledge. A setting mode screen displays a composite image based on generated output image data, together with “processing time”, being expected time required for generating one output image data. The composite image is updated every time the output image data is generated.

摘要翻译： 提供一种能够考虑到每个处理允许的时间来适当地设置拍摄条件的图像处理装置; 所述图像处理装置能够参考实际产生的合成图像来适当地设置拍摄条件; 所述图像处理装置能够即使由没有背景知识的用户适当地设定拍摄条件; 以及图像处理装置，即使没有背景知识的用户也能够确定图像合成处理是否被适当地执行。 设置模式屏幕基于生成的输出图像数据连同“处理时间”一起显示合成图像，作为生成一个输出图像数据所需的预期时间。 每次生成输出图像数据时，更新合成图像。

公开(公告)号：US20110058065A1

公开(公告)日：2011-03-10

申请号：US12714285

申请日：2010-02-26

申请人： Yutaka KIUCHI ,  Yutaka KATO

发明人： Yutaka KIUCHI ,  Yutaka KATO

IPC分类号： H04N5/235

CPC分类号： G06T5/40 ,  G06T5/50 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/30108 ,  G06T2207/30244 ,  H04N5/2355

摘要： This invention provides an image processing device and an image processing method capable of performing image processing of higher accuracy using the synthetic image data with enlarged dynamic range. An image processing method including the steps of acquiring a plurality of input image data with pixel information defined with a first tone range by performing imaging over plural times at different exposure conditions using an imaging unit, generating synthetic image data with pixel information defined with a second tone range wider than the first tone range by synthesizing the plurality of input image data, generating processed image data containing pixel information defined with the second tone range by performing image processing on the synthetic image data for facilitating detection or measurement related to an imaged target; and converting the processed image data to output image data containing pixel information defined with a third tone range narrower than the second tone range is disclosed.

摘要翻译： 本发明提供一种图像处理装置和图像处理方法，其能够使用具有放大的动态范围的合成图像数据进行更高精度的图像处理。 一种图像处理方法，包括以下步骤：通过使用成像单元在不同的曝光条件下进行多次成像来获取用第一色调范围定义的像素信息的多个输入图像数据，生成具有由第二色彩定义的像素信息的合成图像数据 通过合成多个输入图像数据来生成比第一音调范围宽的音调范围，通过对合成图像数据执行图像处理来产生包含用第二音调范围定义的像素信息的处理图像数据，以便于与成像目标相关的检测或测量; 并且将经处理的图像数据转换成包含用比第二色调范围窄的第三色调范围定义的含有像素信息的输出图像数据。

公开(公告)号：US20110222766A1

公开(公告)日：2011-09-15

申请号：US13029451

申请日：2011-02-17

申请人： Yutaka KATO ,  Shiro FUJIEDA ,  Yutaka KIUCHI ,  Shohei NAKAOKA

发明人： Yutaka KATO ,  Shiro FUJIEDA ,  Yutaka KIUCHI ,  Shohei NAKAOKA

IPC分类号： G06K9/00

CPC分类号： G06K9/481 ,  G06T7/74 ,  G06T2207/30164

摘要： An edge code histogram of a model generated in a model image is registered. A target region with respect to the input image is set. An edge code histogram, for the target region is generated. A relative positional relationship between the edge code histogram of the model and the edge code histogram for the target region is sequentially changed, and a degree of coincidence between the edge code histograms at each relative position is calculated. A possibility that the region that matches the model is contained in the set target region from the sequentially calculated degree of coincidence between the edge code histograms is evaluated. Then a candidate point having a possibility of matching the model in the input image is specified while sequentially changing the position of the target region with respect to the input image and repeating steps above for each target region.

摘要翻译： 注册在模型图像中生成的模型的边缘码直方图。 设置相对于输入图像的目标区域。 生成针对目标区域的边缘码直方图。 依次改变模型的边缘码直方图与目标区域的边缘码直方图之间的相对位置关系，并且计算每个相对位置处的边缘码直方图之间的一致度。 评估与依次计算出的边缘码直方图之间的一致度的区域与模型相匹配的区域包含在设定目标区域中的可能性。 然后指定具有与输入图像中的模型匹配的可能性的候选点，同时相对于输入图像依次改变目标区域的位置，并针对每个目标区域重复上述步骤。