-
公开(公告)号：US10330583B2
公开(公告)日：2019-06-25
申请号：US15437806
申请日：2017-02-21
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
IPC分类号： C12Q1/02 , G06K9/00 , G01N15/00 , G01N15/10 , G01N15/14 , G02B21/36 , H04N5/225 , H04N5/445 , G01N33/483
摘要： There is provided a cell imaging apparatus and method capable of generating a high-quality composite image as an image to be evaluated. The cell imaging apparatus includes: an imaging unit 10 that images a cell group including a plurality of periodically moving cells while changing an imaging range; a phase information acquisition unit 21 that acquires information based on the timing of the same phase in each period of the periodic movement; and a composite image generation unit 22 that generates a composite image by arranging images of the respective imaging ranges. The imaging unit 10 captures images with the same phase for the respective imaging ranges on the basis of the information based on the timing of the same phase, and the composite image generation unit 22 generates the composite image by arranging the images with the same phase.
-
公开(公告)号：US11030751B2
公开(公告)日：2021-06-08
申请号：US16544369
申请日：2019-08-19
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
摘要： Provided are a cell image evaluation device, method, and program which are capable of performing more accurate and high reliable evaluation even though a captured image of each part to be observed within a container is an image of which contrast is low due to influence of meniscus. The cell image evaluation device includes a region determination unit that determines whether a captured image obtained by capturing an inside of a container that contains a cell is an image obtained by capturing a meniscus region within the container or an image obtained by capturing a non-meniscus region within the container and an image evaluation unit that evaluates a state of the cell included in the captured image. The image evaluation unit evaluates the image of the meniscus region and the image of the non-meniscus region by different evaluation methods.
-
公开(公告)号：US09894245B2
公开(公告)日：2018-02-13
申请号：US15408249
申请日：2017-01-17
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
CPC分类号： H04N1/4051 , G06K15/1843 , G06K15/1873 , G06K15/1876 , G06K15/1881 , G06K2215/0057 , G06K2215/0094 , H04N1/2369 , H04N1/3935 , H04N1/40068 , H04N1/4052
摘要： An image processing device which generates a halftone image includes: an image size adjustment unit which adjusts a size of the input image; and a halftone processing unit which performs halftone processing on the input image size-adjusted to generate a halftone image, wherein: the image size adjustment unit adjusts the input image to a same size in two or more printing modes among the plurality of printing modes, and the input image of the same size is subjected to the halftone processing; the unit limits arrangement of dots constituting the halftone image to dot arrangeable places of a selected printing mode among the plurality of printing modes, and performs the halftone processing based on an error diffusion method using an error diffusion coefficient matrix according to the selected printing mode; and the functions performed by the image size adjustment unit and the halftone processing unit are achieved using a computer.
-
公开(公告)号：US09259940B2
公开(公告)日：2016-02-16
申请号：US14806658
申请日：2015-07-23
申请人： FUJIFILM CORPORATION
发明人： Takashi Wakui
CPC分类号： B41J2/2121 , B41J2/2054 , B41J2/2128 , H04N1/4057
摘要： There are provided an image formation device, method, and program capable of forming an image, which is appropriate for a combination of dot sizes, with high flexibility in design for optimizing halftone processing in a case of using a plurality of dot sizes. Two or more combinations are selected among combinations of a plurality of types of threshold matrix and at least one type of division information for classifying a whole range of threshold values covered by the types of threshold matrix into a plurality of divisions. Then, by respectively applying the two or more combinations, dot sizes of pixels are determined on the basis of assigned two or more code values.
摘要翻译： 提供了一种能够形成图像的图像形成装置，方法和程序，其适用于点尺寸的组合，在使用多个点尺寸的情况下优化设计中的优化半色调处理的灵活性。 在多种类型的阈值矩阵的组合和至少一种类型的分割信息中选择两种或多种组合，用于将由阈值矩阵的类型覆盖的整个阈值范围分类成多个分割。 然后，通过分别应用两个或多个组合，基于分配的两个或多个代码值来确定像素的点大小。
-
公开(公告)号：US12062184B2
公开(公告)日：2024-08-13
申请号：US17485535
申请日：2021-09-27
申请人： FUJIFILM CORPORATION
发明人： Takashi Wakui
IPC分类号： G06T7/149 , G06F18/2431 , G06N20/00 , G06T7/11
CPC分类号： G06T7/149 , G06F18/2431 , G06N20/00 , G06T7/11 , G06T2207/20081
摘要： An image processing apparatus includes an extraction unit that extracts, from among a plurality of designated regions in which labels of classes are designated, complicated regions which are regions of at least a part of the designated regions and are regions having relatively complicated contours, in an annotation image given as learning data to a machine learning model for performing semantic segmentation in which a plurality of the classes in an image are discriminated on a per-pixel basis, and a setting unit that sets additional labels for the complicated regions separately from original labels originally designated for the annotation image.
-
公开(公告)号：US10761295B2
公开(公告)日：2020-09-01
申请号：US16219193
申请日：2018-12-13
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
摘要： Provided are an imaging device, an imaging method and an imaging control program which make it possible to shorten an imaging time, and to capture an image of each observation region at an appropriate focusing position regardless of the state of installation of a culture vessel on a stage. In a case where an observation target is imaged multiple times, a focusing position of an observation region within a culture vessel is detected by auto-focus control during first imaging, and the first imaging of each observation region is performed using the focusing position. Next, the focusing position of a reference position is detected by auto-focus control during second imaging subsequent to the first imaging, and the focusing position of each observation region detected in the first imaging is corrected on the basis of the detected focusing position and the focusing position of the reference position in the first imaging.
-
7.发明授权Image processing device adapting halftone process to plural printing modes with different resolution and dot arrangement 有权图像处理装置将半色调处理适应于具有不同分辨率和点布置的多种打印模式公开(公告)号：US09571695B2
公开(公告)日：2017-02-14
申请号：US15078971
申请日：2016-03-23
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
CPC分类号： H04N1/4051 , G06K15/1843 , G06K15/1873 , G06K15/1876 , G06K15/1881 , G06K2215/0057 , G06K2215/0094 , H04N1/2369 , H04N1/3935 , H04N1/40068 , H04N1/4052
摘要： Disclosed are an image processing device, a printing apparatus, an image processing method, and a program capable of making processing common among printing modes to simplify an entire image processing flow in image processing based on a plurality of printing modes with different definition. An image processing unit 14 includes an image size adjustment unit 20 which adjusts the size of an input image, and a halftone processing unit 24 which performs halftone processing on the input image size-adjusted by the image size adjustment unit 20 to generate a halftone image. The image size adjustment unit 20 adjusts the input image to the same size in two or more printing modes among a plurality of printing modes with different definition, and the input image of the same size is subjected to halftone processing in the halftone processing unit 24.
摘要翻译： 公开了一种图像处理装置，打印装置，图像处理方法和程序，其能够使打印模式之间共同的处理，以简化基于具有不同定义的多种打印模式的图像处理中的整个图像处理流程。 图像处理单元14包括调整输入图像的尺寸的图像尺寸调整单元20和对由图像尺寸调整单元20调整的输入图像尺寸进行半色调处理的半色调处理单元24，以产生半色调图像 。 图像尺寸调整单元20在具有不同清晰度的多个打印模式中以两种或更多种打印模式将输入图像调整为相同尺寸，并且相同尺寸的输入图像在半色调处理单元24中进行半色调处理。
-
公开(公告)号：US09387685B2
公开(公告)日：2016-07-12
申请号：US14807891
申请日：2015-07-24
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
CPC分类号： B41J2/2121 , H04N1/40087 , H04N1/405 , H04N1/4055
摘要： There are provided an image formation device, an image formation method, a program, and an image forming product capable of preventing noise and granularity of an image from deteriorating even when dots with a plurality of dot sizes are arranged to be aggregated. When a continuous tone image signal is a signal which indicates a tint image, at least one of dot aggregation portions 16, 18, 68, and 72 is formed through arrangement for aggregation of dots 14 (dots 14L and 14S) with two or more dot sizes, on a part of dot images 10, 12, 66, and 70 which are indicated by dot image signals. In addition, the dot aggregation portions 16, 18, 68, and 72 are formed through arrangement for non-aggregation of the dots 14 (dots 14L) with at least one dot size.
摘要翻译： 提供了即使当具有多个点大小的点被布置成聚集时，也能够防止图像的噪声和粒度劣化的图像形成装置，图像形成方法，程序和图像形成产品。 当连续色调图像信号是指示着色图像的信号时，通过布置形成点聚集部分16,18,68和72中的至少一个，用于聚集具有两个或多个点的点14（点14L和14S） 在点图像10,12,66和70的一部分上由点图像信号指示的尺寸。 另外，点集合部分16,18,68和72通过布置形成，用于非点聚点的点14（点14L）具有至少一个点大小。
-
公开(公告)号：US08851608B2
公开(公告)日：2014-10-07
申请号：US13689124
申请日：2012-11-29
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
CPC分类号： B41J2/2121 , B41J2/005 , B41J2/145 , B41J2/205 , B41J2/21
摘要： At least two dot formers are provided for each of a plurality of colors. Dot formers, which form dots in a particular color, are disposed at a greater interval along a direction perpendicular to an array direction of dot forming elements than intervals along the direction perpendicular to the array direction at which other dot formers, which form dots in the remaining colors, are disposed.
摘要翻译： 为多种颜色中的每一种提供至少两个点形成器。 以特定颜色形成点的点形成器沿着垂直于点形成元件的阵列方向的方向以比与阵列方向垂直的方向的间隔更大的间隔设置，在其上形成点的其他点形成器 剩下的颜色，被处置。
-
公开(公告)号：US11900249B2
公开(公告)日：2024-02-13
申请号：US17336807
申请日：2021-06-02
申请人： FUJIFILM Corporation
发明人： Takashi Wakui
IPC分类号： G06N3/08 , G06T7/11 , G06N20/00 , G06V30/262 , G06F18/214 , G06F18/2431 , G06V30/19 , G06V10/82 , G06V20/69
CPC分类号： G06N3/08 , G06F18/214 , G06F18/2431 , G06N20/00 , G06T7/11 , G06V10/82 , G06V20/698 , G06V30/19147 , G06V30/19173 , G06V30/274 , G06T2207/20081
摘要： In a case where the operation program is started, a CPU of the mini-batch learning apparatus functions as a calculation unit, a specifying unit, and an update unit. The calculation unit calculates an area ratio of each of a plurality of classes in mini-batch data. The specifying unit specifies a rare class of which the area ratio is lower than a setting value. The update unit sets an update level of the machine learning model in a case where the rare class is specified by the specifying unit to be lower than an update level of the machine learning model in a case where the rare class is not specified by the specifying unit.
-
-
-
-
-
-
-
-
-
搜索结果
21 条记录 (耗时 0.023 秒)
