公开(公告)号：US5929906A

公开(公告)日：1999-07-27

申请号：US736257

申请日：1996-10-24

申请人： Yoshifumi Arai ,  Shiro Usui

发明人： Yoshifumi Arai ,  Shiro Usui

IPC分类号： H04N9/04 ,  G06T5/00 ,  H04N1/04 ,  H04N1/60 ,  H04N9/73

CPC分类号： H04N1/6086

摘要： A color correcting unit receives color separation values such as CMY values from an image input unit. Under the control of a control portion, inputs to a first conversion portion constituted by a neural network which has been trained in advance on the basis of the spectral distribution of an arbitrary illuminant are corrected so that outputs from the first conversion portion satisfy the color separation values and a predetermined requirement. The input values to the first conversion portion, which satisfy the predetermined requirement, are sent to an image output unit. The image output unit outputs an image in accordance with these input values.

摘要翻译： 颜色校正单元从图像输入单元接收诸如CMY值的颜色分离值。 在控制部分的控制下，校正由基于任意光源的光谱分布预先训练的神经网络构成的第一转换部分的输入，使得来自第一转换部分的输出满足色分离 值和预定要求。 满足预定要求的第一转换部分的输入值被发送到图像输出单元。 图像输出单元根据这些输入值输出图像。

公开(公告)号：US5351079A

公开(公告)日：1994-09-27

申请号：US977598

申请日：1992-11-17

申请人： Shiro Usui

发明人： Shiro Usui

IPC分类号： G06F15/18 ,  G06G7/60 ,  G06N3/00 ,  G06N99/00 ,  G06T1/00 ,  G06T5/00 ,  G09G5/02 ,  H04N9/73

CPC分类号： H04N9/735

摘要： A color balance adjusting apparatus for adjusting color imbalance due to the difference in color temperature between a preferable standard illuminant and an illuminant under which a color image is obtained, thereby making the colors of the image substantially identical to those obtained under the preferable standard illuminant. This apparatus comprises a decorrelating neural network for receiving three color component signals correlating with one another and indicative of an image, and minimizing the correlation thereamong, the network having learned so as to minimize the correlation among signals indicative of an image obtained under an illuminant, and a converter for mapping the output of the decorrelating means, into a space of the input image signals, with the use of the inverse matrix of a transfer matrix of the neural network having learned under the preferable standard illuminant. The output of the converter is generated as a signal obtained after white balance adjusting.

摘要翻译： 一种颜色平衡调节装置，用于调节由优选标准光源和获得彩色图像的光源之间的色温差引起的色差，从而使图像的颜色与优选的标准光源下获得的颜色基本相同。 该装置包括：去相关神经网络，用于接收彼此相关并指示图像的三个颜色分量信号，并且在所学习的网络中最小化相关性，使得最小化指示在光源下获得的图像的信号之间的相关性， 以及转换器，用于使用在优选标准光源下学习的神经网络的传输矩阵的逆矩阵将解相关装置的输出映射到输入图像信号的空间中。 转换器的输出产生为白平衡调整后获得的信号。

公开(公告)号：US07002624B1

公开(公告)日：2006-02-21

申请号：US09649588

申请日：2000-08-29

申请人： Fumiko Uchino ,  Shiro Usui ,  Shigeki Nakauchi ,  Keisuke Takebe

发明人： Fumiko Uchino ,  Shiro Usui ,  Shigeki Nakauchi ,  Keisuke Takebe

IPC分类号： H04N9/73 ,  H04N5/222

CPC分类号： G06T5/50 ,  H04N1/387 ,  H04N5/2354 ,  H04N9/735

摘要： First image data is obtained by performing an image capturing operation with a flash and, subsequently, second image data is obtained by performing an image capturing operation without a flash. By using data of a differential image between the first and second image data and a relative spectral distribution of flash light, the spectrum reflectivity in a position on a subject corresponding to each pixel is obtained and object-color component data is acquired as data from which an influence of an illumination environment has been removed. On the other hand, illuminant component data indicative of spectral distributions of a plurality of illumination light are prepared. By combining arbitrary illuminant component data to the obtained object-color component data, an image with a different illumination environment can be reproduced.

摘要翻译： 通过执行闪光的图像拍摄操作获得第一图像数据，随后通过执行没有闪光的图像捕获操作来获得第二图像数据。 通过使用第一和第二图像数据之间的差分图像的数据和闪光的相对光谱分布，获得与每个像素对应的被摄体上的位置的光谱反射率，并获取对象颜色分量数据作为数据， 照明环境的影响已经消除。 另一方面，准备表示多个照明光的光谱分布的光源成分数据。 通过将任意的光源分量数据与获得的对象颜色分量数据组合，可以再现具有不同照明环境的图像。

公开(公告)号：US06198843B1

公开(公告)日：2001-03-06

申请号：US08923659

申请日：1997-09-04

申请人： Shigeki Nakauchi ,  Shiro Usui ,  Masahiro Imamura

发明人： Shigeki Nakauchi ,  Shiro Usui ,  Masahiro Imamura

IPC分类号： G06K900

CPC分类号： G06T11/001 ,  H04N1/6058

摘要： Colorimetric values such as L*a*b* are input from an input section to a color gamut mapping portion. A filtering process is performed on an image of the difference between the image sent by the input section and an image obtained as a result of bi-directional conversion at a converter section, and the input to the converter section is controlled so as to satisfy a requirement of minimizing an evaluation function which is defined by the sum of square norm of the filtered image as a whole and a value obtained by performing a thresholding process on norm of the difference in each pixel between images before and after the conversion at the converter section output by a gamut extracting section, obtained for the image as a whole. Device values satisfying predetermined conditions which are output of a first neural network of a first converter section to an image output section.

摘要翻译： 诸如L * a * b *的比色值从输入部分输入到色域映射部分。 对由输入部分发送的图像与在转换器部分作为双向转换的结果获得的图像之间的差异的图像执行滤波处理，并且将转换器部分的输入控制为满足 将由滤波图像的整体的平方范数的和定义的评价函数最小化的要求和通过对转换器部分的转换之前和之后的图像之间的每个像素的差的范数执行阈值处理而获得的值 由整个图像获得的色域提取部分输出。 满足预定条件的装置值，其是第一转换器部分的第一神经网络输出到图像输出部分。

公开(公告)号：US5185850A

公开(公告)日：1993-02-09

申请号：US621058

申请日：1990-11-30

申请人： Shiro Usui ,  Shigeki Nakauchi ,  Masae Nakano

发明人： Shiro Usui ,  Shigeki Nakauchi ,  Masae Nakano

IPC分类号： G01J3/46 ,  G06N3/04 ,  G06T1/00 ,  H04N1/46 ,  H04N1/60

CPC分类号： G06N3/04

摘要： To practice a method of transforming color sensation informations such that multidimensional physical informations and color sensation informations sensed by living bodies in response to the physical informations are non-linearly transformed therebetween, a multilayer feedforward type neural network is used for the purpose of accomplishing the foregoing transformation. The physical informations are provided in the form of data derived from multidimensional spectral distribution of light and the color sensation informations are provided in the form of sensitive colors each sensed by the living bodies as a psychological quantity relative to a certain color. An apparatus for carrying out the method includes an input section into which a physical quantity is inputted as an electrical signal, an information transforming section in which the inputted signal is transformed into a color sensation information representing psychological quantity of color and an output section from which the transformed color information is outputted. The information transforming section includes a multilayer feedforward type neural network.

摘要翻译： 为了实现一种转换颜色感觉信息的方法，使得响应于物理信息的活体感测的多维物理信息和颜色感觉信息在其间非线性变换，为了实现上述目的，使用多层前馈型神经网络 转型。 物理信息以从光的多维光谱分布得到的数据的形式提供，并且彩色感觉信息以每一个活体感测的敏感颜色的形式提供为相对于某种颜色的心理量。 一种用于执行该方法的装置包括输入部件，物理量被输入到其中作为电信号;信息变换部分，其中输入的信号被转换成表示心理颜色的颜色的颜色感觉信息;以及输出部分， 输出变换后的颜色信息。 信息变换部包括多层前馈型神经网络。

公开(公告)号：US4846568A

公开(公告)日：1989-07-11

申请号：US172242

申请日：1988-03-23

申请人： Shiro Usui

发明人： Shiro Usui

IPC分类号： A61B3/10 ,  A61B5/04 ,  A61B5/0496

CPC分类号： A61B5/0496 ,  A61B5/7239

摘要： A method of separating an oscillatory potential wave from an electroretinogram of a subject which contains an "a" wave, a "b" wave and said oscillatory potential wave that overlap each other. The electroretinogram ([1]) is produced by light stimulation to the retina of an eye of the subject, and is detected by a suitable device. The peak-to-peak distances of the detected electroretinogram are determined, and a mean period (T) of the oscillatory potential wave ([10]) to be separated from said electroretinogram is obtained. Then, a tentative start point (A) of the oscillatory potential wave is determined, and an OP-free waveform ([7], [9]) free of said oscillatory potential wave is obtained by obtaining moving averages of a first intermediate waveform ([6], [8]) which is determined based on the electroretinogram and the determined tentative start point (A). The oscillatory potential wave ([10]) is extracted by subtracting the OP-free waveform ([7], [9]) from the electroretinogram ([1]).

摘要翻译： 从包含“a”波，“b”波和所述相互重叠的振荡电位波的受检者的视网膜电图分离振荡电位波的方法。 视网膜电图（[1]）通过对受试者的眼睛的视网膜进行光刺激而产生，并且由合适的装置检测。 确定检测到的视网膜电图的峰 - 峰距离，并且获得与所述视网膜电图分离的振荡电位波（[10]）的平均周期（T）。 然后，确定振荡电位波的暂定起点（A），并且通过获得第一中间波形（的移动平均值）获得没有所述振荡电位波的无OP的波形（[7]，[9] [6]，[8]），其基于视网膜电图和确定的临时起点（A）确定。 通过从视网膜电图（[1]）中减去OP无关波形（[7]，[9]）来提取振荡电位波（[10]）。

公开(公告)号：US4701874A

公开(公告)日：1987-10-20

申请号：US560447

申请日：1983-12-12

申请人： Takashi Akai ,  Katsuro Okamoto ,  Shiro Usui

发明人： Takashi Akai ,  Katsuro Okamoto ,  Shiro Usui

IPC分类号： G06F7/544 ,  H03H17/02 ,  G06F7/38

CPC分类号： G06F7/5443 ,  H03H17/02

摘要： A digital signal processing apparatus is disclosed. A delay circuit generates (2p+1) signals x.sub.k-n to x.sub.k+n (n=0, 1, 2, . . . , p), each having a difference respective delay time. The apparatus further comprises a computation circuit responsive to the foregoing signal for computing ##EQU1## wherein coefficients j and h.sub.0 to h.sub.n are ".+-.1" and "1" or "0", respectively.

摘要翻译： 公开了一种数字信号处理装置。 延迟电路产生（2p + 1）信号xk-n至xk + n（n = 0,1,2，...，p），每个具有相应的延迟时间差。 该装置还包括响应于前述信号的计算电路，用于计算，其中系数j和h0至hn分别为“+/- 1”和“1”或“0”。