公开(公告)号：US5761384A

公开(公告)日：1998-06-02

申请号：US451977

申请日：1995-05-26

申请人： Tsuyoshi Inoue ,  Teruhiko Matsuoka ,  Takashi Aramaki

发明人： Tsuyoshi Inoue ,  Teruhiko Matsuoka ,  Takashi Aramaki

IPC分类号： G06F15/18 ,  G06F9/44 ,  G06N3/00 ,  G06N3/04 ,  G06N7/02

CPC分类号： G06N3/0436

摘要： A fuzzy neural network system which is provided with an input layer, a membership layer front half section, a membership layer back half section, a rule layer, and an output layer; and constructs a network from a plurality of input/output items. The input layer and the membership layers are structured so as to divide each input value into three regions of fuzzy sets, respectively. The rule layer selects one each respectively from the above mentioned items divided into three regions, and is structured so as to make these the AND rules for the two input items.

摘要翻译： 一种模糊神经网络系统，其具有输入层，隶属层前半部分，隶属层后半部分，规则层和输出层; 并从多个输入/输出项构建网络。 输入层和隶属层被构造成分别将每个输入值分成三个模糊集合区域。 规则层分别从划分为三个区域的上述项目中选择一个，并且被构造成使得这两个输入项目的AND规则。

公开(公告)号：US5819242A

公开(公告)日：1998-10-06

申请号：US620998

申请日：1996-03-22

申请人： Teruhiko Matsuoka ,  Takashi Aramaki

发明人： Teruhiko Matsuoka ,  Takashi Aramaki

IPC分类号： G06G7/12 ,  G06F15/18 ,  G06G7/60 ,  G06N3/00 ,  G06N3/04 ,  G06F9/44

CPC分类号： G06N3/0436

摘要： A fuzzy-neural network system includes: an input layer outputting values of input parameters; a membership layer wherein a multiple number of regions for each of the input parameters are formed by dividing the probable range of the input parameter and a membership function is defined for each of the regions, the membership layer producing membership values as to the regions for each of the input parameters, in accordance with the output values from the input layer; a rule layer wherein specific rules are formed between regions belonging to different input parameters, the rule layer outputting a suitability for each of the rules; an outputting layer producing an output parameter or parameters in accordance with the output values from the rule layer; and a membership value setup means which, if some of the input parameters are unknown, sets up prescribed values as membership values corresponding to the unknown parameters.

摘要翻译： 模糊神经网络系统包括：输入输入参数值的输入层; 隶属层，其中通过划分输入参数的可能范围和隶属度函数形成每个输入参数的多个区域，为每个区域定义关于每个区域的区域的隶属度层生成隶属关系值 的输入参数，根据输入层的输出值; 其中在属于不同输入参数的区域之间形成特定规则的规则层，规则层输出每个规则的适用性; 输出层，其根据来自规则层的输出值产生输出参数或参数; 以及成员值设置装置，如果一些输入参数是未知的，则将规定值设置为对应于未知参数的成员值。

公开(公告)号：US5683605A

公开(公告)日：1997-11-04

申请号：US572079

申请日：1995-12-14

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G03G15/00 ,  G03G15/20 ,  G05B13/02 ,  G05D23/19 ,  H05B3/00 ,  H05B1/02

CPC分类号： G03G15/2003 ,  G05D23/1917 ,  G03G2215/00118 ,  Y10S706/90

摘要： A heater controlling unit used in a heat fusing device of an image forming apparatus, such as a copying machine, comprises a temperature detecting unit for outputting a detected temperature, a temperature change rate computing unit for computing the surface temperature of a heat fusing roller using the output of the temperature detecting unit, and an on-time computing and controlling unit for computing a heater on-time within a predetermined period by means of a fuzzy neural network using the above temperature and a temperature change rate found by the temperature-change rate computing unit, a heater controlling circuit for controlling the on/off action of the heater, a predictive computing unit for predicting the surface temperature, and a comparing and adjusting unit for comparing the actual temperature with the predicted temperature, and, when the difference is greater than a predetermined value (e.g., .+-.5.degree. C.), for adjusting the weights of the links within the network. Accordingly, the roughly-set parameters can be amended to the ones for an optimal on-time by the sequential learning. As a result, the program can be generated in a simpler manner, and the program can be changed easily for individual units depending on aged distortion and environments thereof.

摘要翻译： 一种用于诸如复印机的图像形成装置的热定影装置中的加热器控制单元，包括用于输出检测温度的温度检测单元，用于计算热定影辊的表面温度的温度变化率计算单元，所述温度变化率计算单元使用 温度检测单元的输出和通过使用上述温度的模糊神经网络和由温度变化所发现的温度变化率在预定时段内计时加热器的接通时间计算和控制单元 速率计算单元，用于控制加热器的开/关动作的加热器控制电路，用于预测表面温度的预测计算单元，以及用于将实际温度与预测温度进行比较的比较和调节单元，以及当差异 大于预定值（例如，+/- 5℃），用于调整网络内的链路的权重。 因此，可以通过顺序学习将粗略设置的参数修改为用于最佳接通时间的参数。 结果，可以以更简单的方式生成程序，并且可以根据老化的失真及其环境，针对各个单元容易地改变程序。

公开(公告)号：US08463032B2

公开(公告)日：2013-06-11

申请号：US13008378

申请日：2011-01-18

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K9/36

CPC分类号： H04N1/41

摘要： In a color image processing apparatus, in a compression process section (an image compressing apparatus), when an original document is compressed, the edges of black texts and/or line drawings in the original document is detected, then a foreground layer (a first image) is generated in which the detected edges are expressed in the form of a binary image, and then lossless compression is performed on the foreground layer. Further, a background layer (a second image) is generated in which a density difference of the edges from the other parts in the original document is reduced, and then lossy compression is performed on the background layer. Then, these layers are combined into a compressed file.

摘要翻译： 在彩色图像处理装置中，在压缩处理部（图像压缩装置）中，当原稿被压缩时，检测原稿中的黑色文字和/或线条的边缘，然后前景层（第一 图像），其中检测到的边缘以二进制图像的形式表示，然后在前景层上执行无损压缩。 此外，生成背景层（第二图像），其中边缘与原始文档中的其他部分的浓度差减小，然后对背景层执行有损压缩。 然后，将这些层组合成压缩文件。

公开(公告)号：US08422778B2

公开(公告)日：2013-04-16

申请号：US12784313

申请日：2010-05-20

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K9/34 ,  G06K9/36 ,  G06K9/46 ,  G06K9/48

CPC分类号： H04N1/642 ,  H04N1/4092 ,  H04N1/41

摘要： During compressing an image at the compression processing section (image compressing apparatus), the color image processing apparatus detects edge of text and/or line art, generates the foreground layer represented by binary image for showing the detected edge, compresses the foreground layer with lossless compression, and compresses the background layer which is an image except the foreground layer with lossy compression. Furthermore, the color image processing apparatus sets the foreground layer color different from a color of text or line art, and provides information representing the set color into the compression file. As the set color, the color image processing apparatus utilizes the overall color representative for whole region of the image, or the text-vicinity color in the image. The edge region of the text and/or line art are represented with such the set color on the reproduced image based on the compression file.

摘要翻译： 在压缩处理部（图像压缩装置）压缩图像期间，彩色图像处理装置检测文本和/或线条艺术的边缘，生成用于显示检测到的边缘的二进制图像表示的前景层，用无损压缩前景层 压缩和压缩作为除了前景层之外的图像的背景层，并进行有损压缩。 此外，彩色图像处理装置设置与文本或线条艺术的颜色不同的前景层颜色，并且将表示设置的颜色的信息提供到压缩文件中。 作为设定的颜色，彩色图像处理装置利用图像的整个区域的整体颜色代表或图像中的文本附近颜色。 基于压缩文件，文本和/或线条图像的边缘区域以再现图像上的这种设置的颜色表示。

公开(公告)号：US06272261B1

公开(公告)日：2001-08-07

申请号：US09238847

申请日：1999-01-28

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K936

CPC分类号： G06T3/4007

摘要： The present invention provides an image processing device capable of performing high-resolution conversion, enlargement processing, etc. which, even with images including both text images and photographic images, satisfies both sharpness of text areas and smoothness of photograph areas. The image processing device according to the present invention performs frequency conversion, using a frequency conversion device, of partial images which are the objects of processing, resulting in a matrix of frequency-converted coefficients; divides into a plurality of domains, using a plurality of patterns, the matrix of frequency-converted coefficients; and quantifies each such domain by finding a mean value of the coefficients of that domain as a feature quantity for that domain. The mean coefficient value of each domain is inputted into a conversion filter selecting device, where a hierarchical neural network calculates and outputs the suitability of each conversion filter for the partial image in question, and the conversion filter selecting device selects the conversion filter with the highest suitability. Then an interpolation processing device performs interpolation processing of each partial image using the conversion filter most suited thereto.

摘要翻译： 本发明提供了能够进行高分辨率转换，放大处理等的图像处理装置，即使包括文本图像和摄影图像的图像都满足文本区域的锐度和照片区域的平滑度。 根据本发明的图像处理装置使用频率转换装置对作为处理对象的部分图像进行频率转换，得到频率转换系数的矩阵; 使用多个模式将频率转换系数的矩阵划分成多个域; 并通过找到该域的系数的平均值作为该域的特征量来量化每个这样的域。 每个域的平均系数值被输入到转换滤波器选择装置中，其中分层神经网络计算并输出所讨论的部分图像的每个转换滤波器的适用性，并且转换滤波器选择装置选择具有最高值的转换滤波器 适应性。 然后，内插处理装置使用最适合于其的转换滤波器对每个部分图像进行插值处理。

公开(公告)号：US06263120B1

公开(公告)日：2001-07-17

申请号：US09161482

申请日：1998-09-28

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K932

CPC分类号： G06T3/403 ,  G06T3/4084

摘要： An original image containing different kinds of components-areas is adaptively processed by applying interpolating methods suitably selected for respective areas. The processing method comprises the steps of extracting data of a partial image from data of a multi-gradation original image (STEP 1), converting the partial image data into frequency data by using a frequency transformation matrix (e.g., the same size DCT) and storing the transformed data as coefficients of the matrix (STEP 2), calculating a mean of absolute values of the coefficients for each frequency domain (STEP 3), discriminating whether the partial image contains an edge portion by applying the mean coefficient value to conditional equations (STEP 4), selecting a filter for surface interpolation or linear interpolation on the basis of the discrimination result (STEP 5) and interpolating the data of the partial image (STEP 6).

摘要翻译： 通过应用针对各个区域适当选择的内插方法，自适应地处理包含不同种类的组件区域的原始图像。 该处理方法包括以下步骤：从多灰阶原始图像的数据中提取部分图像的数据（步骤1），通过使用频率变换矩阵（例如，相同尺寸的DCT）将部分图像数据转换成频率数据，以及 将转换的数据作为矩阵的系数存储（步骤2），计算每个频域的系数的绝对值的平均值（步骤3），通过将平均系数值应用于条件方程式来区分部分图像是否包含边缘部分 （步骤4），基于判别结果（步骤5）选择用于表面插值或线性插值的滤波器，并内插部分图像的数据（步骤6）。

公开(公告)号：US08792735B2

公开(公告)日：2014-07-29

申请号：US13086466

申请日：2011-04-14

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K9/36

CPC分类号： H04N1/41 ,  H04N1/40062 ,  H04N1/4092 ,  H04N1/413

摘要： A color image processing apparatus is provided with a black text emphasis mode, in which, when compressing an image in a compression processing section, edges of a black text in the image are detected, a foreground layer in which the detected edges of the black text are represented by a binary image is generated, and lossless compression is performed on the foreground layer. When the black text emphasis mode is selected, a background layer in which the difference in density between the edges of the black text and pixels in the vicinity of the edges in the image is reduced is generated, and lossy compression is performed on the background layer. With this operation, in an image obtained by decompressing a compressed file, outline of the black text is clearly represented, and an artifact caused by the lossy compression is suppressed.

摘要翻译： 彩色图像处理装置具有黑色文本加重模式，其中当在压缩处理部分中压缩图像时，检测图像中的黑色文本的边缘，其中检测到黑色文本的边缘的前景层 由二进制图像生成，并且对前景层执行无损压缩。 当选择黑色文本加重模式时，生成黑色文本的边缘与图像边缘附近的像素之间的密度差减小的背景层，并对背景层进行有损压缩 。 通过该操作，在通过解压缩压缩文件获得的图像中，清楚地表示黑色文本的轮廓，并且抑制由有损压缩引起的伪影。

公开(公告)号：US08280160B2

公开(公告)日：2012-10-02

申请号：US12691271

申请日：2010-01-21

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K9/36

CPC分类号： H04N1/56

摘要： When N kinds of foreground identifiers for identifying color information of a foreground of a color image is to be reduced to M smaller than N, foreground identifiers corresponding to similar chromatic colors are merged and foreground identifiers corresponding to similar achromatic colors are merged but a foreground identifier corresponding to a chromatic color and a foreground identifier corresponding to an achromatic color are not merged. Thus, image quality degradation derived from color change from an achromatic color to a chromatic color or vice versa may be suppressed. On the basis of a foreground layer including the M kinds of foreground identifiers, M binary images respectively corresponding to the M kinds of foreground identifiers are generated, each of the binary images is subjected to lossless compression and a background layer is subjected to lossy compression.

摘要翻译： 当将用于识别彩色图像的前景的颜色信息的N种前景标识符缩减为小于N的M时，将与相似色彩对应的前景标识符合并，并且对应于类似的无彩色的前景标识符被合并，而前景标识符 对应于彩色和与无彩色相对应的前景标识符不对应。 因此，可以抑制从无彩色到彩色或反之亦然的颜色变化导致的图像质量劣化。 在包含M种前景标识符的前景层的基础上，生成分别对应于M种前景标识符的M个二进制图像，对每个二进制图像进行无损压缩，对背景层进行有损压缩。

公开(公告)号：US08254672B2

公开(公告)日：2012-08-28

申请号：US12511196

申请日：2009-07-29

申请人： Teruhiko Matsuoka

发明人： Teruhiko Matsuoka

IPC分类号： G06K9/36

CPC分类号： H04N1/642

摘要： When priority is placed on a small file size, the number N of kinds foreground identifiers used for identifying color information of respective pixels of a foreground of a color image is reduced to M, which is smaller than N. For this purpose, a foreground identifier corresponding to pixels in number not more than a prescribed number K of pixels is replaced with a background identifier. When M is not more than a prescribed number P, M binary images respectively corresponding to the M kinds of identifiers are generated on the basis of a foreground layer including the M kinds of foreground identifiers, the respective binary images are subjected to lossless compression, and a background layer generated on the basis of the foreground layer is subjected to lossy compression.

摘要翻译： 当优先考虑小文件大小时，用于识别彩色图像的前景的各个像素的颜色信息的种类前景标识符的数目N减少到小于N的M。为此，前景标识符 对应于不超过规定数量K的像素的像素的像素被替换为背景标识符。 当M不超过规定数量P时，基于包含M种前景标识符的前景层生成分别对应于M种标识符的M个二进制图像，对各个二进制图像进行无损压缩，并且 基于前景层生成的背景层被进行有损压缩。