公开(公告)号：US08290259B2

公开(公告)日：2012-10-16

申请号：US12181903

申请日：2008-07-29

申请人： Kiyoshi Umeda ,  Ryosuke Iguchi

发明人： Kiyoshi Umeda ,  Ryosuke Iguchi

IPC分类号： G06K9/00 ,  G06K9/40 ,  G03F3/08

CPC分类号： H04N1/6027 ,  H04N1/62 ,  H04N1/628

摘要： The present invention provides an image processing device which adaptively switches between emphasis of a specified color in an image and emphasis of the entire image. The image processing device of the present invention includes: a storage unit storing a plurality of color emphasis tables for emphasizing a specified color; a calculation unit calculating magnitudes of respective color emphasis effects when the plurality of color emphasis tables stored by the storage unit is applied to the image; a selection unit selecting one or more color emphasis tables according to the magnitudes of the color emphasis effects; and a correction unit correcting the specified color in the image by applying the color emphasis tables selected by the selection unit to the image.

摘要翻译： 本发明提供了一种图像处理装置，其自适应地在图像中的指定颜色的强调和整个图像的强调之间切换。 本发明的图像处理装置包括：存储单元，存储用于强调特定颜色的多个着色表; 当将由存储单元存储的多个着色表应用于图像时，计算各颜色强调效果的大小的计算单元; 选择单元，根据所述着色效果的大小选择一个或多个着色表; 以及校正单元，通过将由选择单元选择的着色表应用于图像来校正图像中的指定颜色。

公开(公告)号：US20120189213A1

公开(公告)日：2012-07-26

申请号：US13437089

申请日：2012-04-02

申请人： Kiyoshi Umeda

发明人： Kiyoshi Umeda

IPC分类号： G06K9/68

CPC分类号： G06K9/0061

摘要： In case of an image region having a property of abrupt changes in luminance and tint, even when a region made up of pixels having luminance values and tint levels similar to those of one point designated by the user is extracted as a correction region with reference to the user designated point, it is difficult to extract a region to be corrected without omission. To solve this problem, a user instruction indicating a point inside or near an image region which is to undergo correction is input, and a plurality of origin pixels corresponding to start points of region expansion are set in a region which includes the input point and has a predetermined size. The region expansion is executed from each origin pixel, and a correction region is decided according to the result of the region expansion.

摘要翻译： 在具有亮度和色调突然变化的特性的图像区域的情况下，即使当由具有与由用户指定的一个点相似的亮度值和色调等级的像素组成的区域提取作为校正区域时，参考 用户指定点，很难提取要修正的区域，而不会遗漏。 为了解决这个问题，输入指示要进行校正的图像区域内部或附近的用户指令，并且将与区域扩展的开始点相对应的多个原点像素设置在包括输入点的区域中并具有 预定尺寸。 从每个原始像素执行区域扩展，并且根据区域扩展的结果来确定校正区域。

公开(公告)号：US20100328686A1

公开(公告)日：2010-12-30

申请号：US12819996

申请日：2010-06-21

申请人： Kiyoshi Umeda

发明人： Kiyoshi Umeda

IPC分类号： G06K9/40 ,  G06K15/02 ,  G06F15/00

CPC分类号： H04N1/4072 ,  H04N1/4092

摘要： When printing by generating a composite low-frequency image based on an input image, performing dodging processing, and changing a size of the input image to an output image size, if the output image size is much smaller than the input image size, wastefulness occurs in the composite processing of the low-frequency image, and the overall performance of the printing process deteriorates. To solve these problems, a plurality of blurry images having a different blurriness level from an input image are generated, print setting information to be used in printing of the input image is input, a size of a composite low-frequency image is calculated based on the print setting information, a composite low-frequency image is generated in the calculated size from the plurality of blurry images, and dodging processing is performed on the input image using the generated composite low-frequency image.

摘要翻译： 当通过基于输入图像生成复合低频图像进行打印，执行躲避处理并将输入图像的大小改变为输出图像大小时，如果输出图像尺寸远小于输入图像尺寸，则产生浪费 在低频图像的复合处理中，印刷过程的整体性能恶化。 为了解决这些问题，产生具有与输入图像不同的模糊度的多个模糊图像，输入用于输入图像的打印中使用的打印设置信息，基于以下方式计算复合低频图像的尺寸： 打印设置信息，从多个模糊图像以计算出的尺寸生成复合低频图像，并且使用所生成的复合低频图像对输入图像执行闪避处理。

公开(公告)号：US07826659B2

公开(公告)日：2010-11-02

申请号：US11440401

申请日：2006-05-25

申请人： Kiyoshi Umeda

发明人： Kiyoshi Umeda

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/34

CPC分类号： G06K9/0061 ,  G06T5/005 ,  G06T7/11 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/30201 ,  G06T2207/30216

摘要： An embedded system of a digital camera or printer has limited available memory resources. Under such environment, devices are required to detect a red-eye region from a high-resolution image. To solve this problem, an input image is divided into band images each including a predetermined number of lines, so that an overlap area exists between neighboring band images, and candidate pixels which form an image region exhibiting poor color tone are extracted for each band image. The band image which is to undergo characteristic amount determination is determined based on the position of the candidate region which includes the candidate pixels in the overlap area.

摘要翻译： 数码相机或打印机的嵌入式系统具有有限的可用内存资源。 在这种环境下，需要设备从高分辨率图像中检测红眼区域。 为了解决这个问题，输入图像被分成包括预定数量的行的频带图像，使得在相邻频带图像之间存在重叠区域，并且为每个频带图像提取形成表现出差的色调的图像区域的候选像素 。 基于在重叠区域中包括候选像素的候选区域的位置来确定要进行特征量确定的频带图像。

公开(公告)号：US07724950B2

公开(公告)日：2010-05-25

申请号：US11423898

申请日：2006-06-13

申请人： Kiyoshi Umeda

发明人： Kiyoshi Umeda

IPC分类号： G06K9/00

CPC分类号： G06K9/0061 ,  G06T5/005 ,  G06T7/11 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30201 ,  G06T2207/30216

摘要： An image processing apparatus configured to detect an image region indicating a poor color tone of eyes from candidate regions includes: a first determination unit configured to perform a determination relating to an evaluation amount with respect to the poor color tone based on a predetermined color component in a target candidate region, and the evaluation amount in a peripheral region of the candidate region, a second determination unit configured to update the candidate region based on the first determination result, and to perform a determination relating to the evaluation amount or a predetermined color component with reference to pixels in an updated second candidate region, and a third determination unit configured to update the second candidate region based on the second determination result, and to perform a determination relating to a characteristic amount of a peripheral region with reference to pixels in a peripheral region of an updated third candidate region. A calculation amount of the third determination is greater than a calculation amount of the first or second determination.

摘要翻译： 一种图像处理装置，被配置为从候选区域检测指示眼睛的色调不良的图像区域，包括：第一确定单元，被配置为基于预定的颜色成分执行关于色差不足的评估量的判定 目标候选区域和候选区域的外围区域中的评价量，第二确定单元，被配置为基于第一确定结果来更新候选区域，并且执行与评估量或预定颜色分量有关的确定 参考更新的第二候选区域中的像素，以及第三确定单元，被配置为基于第二确定结果来更新第二候选区域，并且参考第二候选区域中的像素执行与周围区域的特征量相关的确定 更新的第三候选区域的外围区域。 第三确定的计算量大于第一或第二确定的计算量。

公开(公告)号：US20090034837A1

公开(公告)日：2009-02-05

申请号：US12174276

申请日：2008-07-16

申请人： Minako Kato ,  Kiyoshi Umeda ,  Ryosuke Iguchi

发明人： Minako Kato ,  Kiyoshi Umeda ,  Ryosuke Iguchi

IPC分类号： G06K9/40 ,  G06K9/46 ,  G06K9/20

CPC分类号： H04N1/608 ,  G06T5/007 ,  G06T5/40 ,  G06T2207/10024 ,  H04N1/60

摘要： An image processing method is a method for correcting both an image quality of an overall image and an image quality of a partial image with excellent balance.

摘要翻译： 图像处理方法是用于校正整体图像的图像质量和具有良好平衡的部分图像的图像质量的方法。

公开(公告)号：US07408680B2

公开(公告)日：2008-08-05

申请号：US10247519

申请日：2002-09-20

申请人： Nobutaka Miyake ,  Kiyoshi Umeda ,  Minoru Kusakabe

发明人： Nobutaka Miyake ,  Kiyoshi Umeda ,  Minoru Kusakabe

IPC分类号： G06K15/00 ,  H04N1/40

CPC分类号： G06T1/0028 ,  G06T2201/0051 ,  G06T2201/0061 ,  H04N1/32144 ,  H04N1/32229 ,  H04N1/32315 ,  H04N2201/0082

摘要： There is disclosed an image processing apparatus developed considering that an embedding or extracting method has not heretofore been changed based on a spatial coordinate on a recording medium or reading device, the apparatus comprising: an input unit for inputting an image, an embedding unit for embedding predetermined information to the inputted image by a predetermined embedding method, an image formation unit for forming the image to which the predetermined information is embedded on the recording medium, and a changeover unit for changing the embedding method by the embedding unit based on the spatial coordinate of the recording medium.

摘要翻译： 公开了一种图像处理装置，其考虑到基于记录介质或读取装置上的空间坐标尚未改变嵌入或提取方法，该装置包括：用于输入图像的输入单元，用于嵌入的嵌入单元 通过预定的嵌入方法对输入图像的预定信息，用于形成预定信息嵌入在记录介质上的图像的图像形成单元和用于基于空间坐标改变嵌入单元的嵌入方法的转换单元 的记录介质。

公开(公告)号：US20060280363A1

公开(公告)日：2006-12-14

申请号：US11440401

申请日：2006-05-25

申请人： Kiyoshi Umeda

发明人： Kiyoshi Umeda

IPC分类号： G06K9/00

CPC分类号： G06K9/0061 ,  G06T5/005 ,  G06T7/11 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/30201 ,  G06T2207/30216

摘要： An embedded system of a digital camera or printer has limited available memory resources. Under such environment, devices are required to detect a red-eye region from a high-resolution image. To solve this problem, an input image is divided into band images each including a predetermined number of lines, so that an overlap area exists between neighboring band images, and candidate pixels which form an image region exhibiting poor color tone are extracted for each band image. The band image which is to undergo characteristic amount determination is decided based on the position of the candidate region which includes the candidate pixels in the overlap area.

摘要翻译： 数码相机或打印机的嵌入式系统具有有限的可用内存资源。 在这种环境下，需要设备从高分辨率图像中检测红眼区域。 为了解决这个问题，输入图像被分成包括预定数量的行的频带图像，使得在相邻频带图像之间存在重叠区域，并且为每个频带图像提取形成表现出差的色调的图像区域的候选像素 。 基于在重叠区域中包括候选像素的候选区域的位置来决定要进行特征量确定的频带图像。

公开(公告)号：US20060280361A1

公开(公告)日：2006-12-14

申请号：US11423898

申请日：2006-06-13

申请人： Kiyoshi Umeda

发明人： Kiyoshi Umeda

IPC分类号： G06K9/00

CPC分类号： G06K9/0061 ,  G06T5/005 ,  G06T7/11 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30201 ,  G06T2207/30216

摘要： An image processing apparatus configured to detect an image region indicating a poor color tone of eyes from candidate regions includes: a first determination unit configured to perform a determination relating to an evaluation amount with respect to the poor color tone based on a predetermined color component in a target candidate region, and the evaluation amount in a peripheral region of the candidate region, a second determination unit configured to update the candidate region based on the first determination result, and to perform a determination relating to the evaluation amount or a predetermined color component with reference to pixels in an updated second candidate region, and a third determination unit configured to update the second candidate region based on the second determination result, and to perform a determination relating to a characteristic amount of a peripheral region with reference to pixels in a peripheral region of an updated third candidate region. A calculation amount of the third determination is greater than a calculation amount of the first or second determination.

摘要翻译： 一种图像处理装置，被配置为从候选区域检测指示眼睛的色调不良的图像区域，包括：第一确定单元，被配置为基于预定的颜色成分执行关于色差不足的评估量的判定 目标候选区域和候选区域的外围区域中的评价量，第二确定单元，被配置为基于第一确定结果来更新候选区域，并且执行与评估量或预定颜色分量有关的确定 参考更新的第二候选区域中的像素，以及第三确定单元，被配置为基于第二确定结果来更新第二候选区域，并且参考第二候选区域中的像素执行与周围区域的特征量相关的确定 更新的第三候选区域的外围区域。 第三确定的计算量大于第一或第二确定的计算量。

公开(公告)号：US07079267B2

公开(公告)日：2006-07-18

申请号：US10244016

申请日：2002-09-16

申请人： Kiyoshi Umeda ,  Nobutaka Miyake ,  Minoru Kusakabe

发明人： Kiyoshi Umeda ,  Nobutaka Miyake ,  Minoru Kusakabe

IPC分类号： G06K9/00 ,  G06F15/00

CPC分类号： G06T1/0021 ,  G06T2201/0061

摘要： Provided are an image processing apparatus, method, computer program and recording medium capable of embedding a large quantity of additional information in image information upon dispersing the information in such a manner that it will not be noticeable visually. An error correction code is calculated from additional information [x(i)] to be added to image information (D1), and multiplexed information [y(j)] in which the error correction code has been added to the additional information is generated by an error correction encoder (13). Next, the bit sequence of the multiplexed information [y(j)] that has been generated is rearranged into a prescribed bit sequence by a shuffling unit (14), whereby multiplexed information [z(j)] is generated. Furthermore, the multiplexed information [z(j)] whose bit sequence has been rearranged is embedded in the image information (D1) by an additional-information multiplexer (15), whereby image information (D2) is generated. The image information (D2) in which the multiplexed information [z(j)] has been embedded is printed by a printer (16) and is output as a printed image (17).

摘要翻译： 提供了一种图像处理装置，方法，计算机程序和记录介质，其能够以不可视觉的方式分散信息，从而在图像信息中嵌入大量的附加信息。 根据要添加到图像信息（D 1）的附加信息[x（i）]计算纠错码，并且生成其中添加了纠错码的多路复用信息[y（j）]，生成 通过纠错编码器（13）。 接下来，通过混洗单元（14）将生成的多路复用信息[y（j）]的比特序列重排为规定的比特序列，从而生成多路复用信息[z（j）]。 此外，通过附加信息多路复用器（15）将其位序列重新排列的复用信息[z（j）]嵌入在图像信息（D 1）中，从而生成图像信息（D 2）。 已经嵌入多路复用信息[z（j）]的图像信息（D 2）由打印机（16）打印并作为打印图像输出（17）。