公开(公告)号：EP0198481B1

公开(公告)日：1996-03-13

申请号：EP86105213.2

申请日：1986-04-15

申请人： HITACHI, LTD.

发明人： Orita, Miyahiko ,  Kanasaki, Morio ,  Toda, Yuji ,  Mishima, Tadaaki ,  Suzuki, Masato ,  Onuma, Chieko ,  Takatoo, Masao

IPC分类号： G06T5/40

CPC分类号： G06T7/00

公开(公告)号：EP0287995A3

公开(公告)日：1991-05-29

申请号：EP88106158.4

申请日：1988-04-18

申请人： HITACHI, LTD.

发明人： Mishima, Tadaaki ,  Kanasaki, Morio ,  Takatoo, Masao ,  Ota, Hideo

IPC分类号： G06K9/46

CPC分类号： G06K9/4647 ,  G06K9/36 ,  G06K2209/01

摘要： In a method of recognizing a pattern of a halftone image of a first invention, a halftone image to be processed is subjected to a normalization process (3), local halftone feature parameters are extracted (4, 7, 8, 9) from the normalized image at its sampling points, and the pattern is identified (5) by using the extracted feature parameters in accordance with a predetermined recognition procedure. An apparatus for recognizing a pattern of a halftone image of a second invention, comprises a memory (211) for storing a halftone image having several brightness tone levels, a normalization circuit (3, 212 - 216) for normalizing the brightness of the halftone image to be processed, an extraction circuit (4, 212 - ­216) for extracting local halftone feature parameters from the obtained normalized image at specific points, and a recognition circuit (5) for identifying the pattern by using the feature parameters in accordance with a predetermined recognition procedure.

公开(公告)号：EP0287995B1

公开(公告)日：1994-08-24

申请号：EP88106158.4

申请日：1988-04-18

申请人： HITACHI, LTD.

发明人： Mishima, Tadaaki ,  Kanasaki, Morio ,  Takatoo, Masao ,  Ota, Hideo

IPC分类号： G06K9/46

CPC分类号： G06K9/4647 ,  G06K9/36 ,  G06K2209/01

公开(公告)号：EP0287995A2

公开(公告)日：1988-10-26

申请号：EP88106158.4

申请日：1988-04-18

申请人： HITACHI, LTD.

发明人： Mishima, Tadaaki ,  Kanasaki, Morio ,  Takatoo, Masao ,  Ota, Hideo

IPC分类号： G06K9/46

CPC分类号： G06K9/4647 ,  G06K9/36 ,  G06K2209/01

摘要： In a method of recognizing a pattern of a halftone image of a first invention, a halftone image to be processed is subjected to a normalization process (3), local halftone feature parameters are extracted (4, 7, 8, 9) from the normalized image at its sampling points, and the pattern is identified (5) by using the extracted feature parameters in accordance with a predetermined recognition procedure. An apparatus for recognizing a pattern of a halftone image of a second invention, comprises a memory (211) for storing a halftone image having several brightness tone levels, a normalization circuit (3, 212 - 216) for normalizing the brightness of the halftone image to be processed, an extraction circuit (4, 212 - ­216) for extracting local halftone feature parameters from the obtained normalized image at specific points, and a recognition circuit (5) for identifying the pattern by using the feature parameters in accordance with a predetermined recognition procedure.

摘要翻译： 在识别第一发明的半色调图像的图案的方法中，对要处理的半色调图像进行归一化处理（3），从标准化的（5,7,8,9）中提取局部半色调特征参数（4,7,8,9） 在其采样点处的图像，并且根据预定的识别过程通过使用提取的特征参数来识别图案（5）。 一种用于识别第二发明的半色调图像的图案的装置，包括用于存储具有多个亮度色调级别的半色调图像的存储器（211），用于对半色调图像进行标准化的归一化电路（3,212-216） 用于从特定点处获得的归一化图像中提取局部半色调特征参数的提取电路（4,212-216），以及用于根据预定的方法使用特征参数来识别图案的识别电路（5） 识别程序。

公开(公告)号：EP0198481A3

公开(公告)日：1990-05-16

申请号：EP86105213.2

申请日：1986-04-15

申请人： HITACHI, LTD.

发明人： Orita, Miyahiko ,  Kanasaki, Morio ,  Toda, Yuji ,  Mishima, Tadaaki ,  Suzuki, Masato ,  Onuma, Chieko ,  Takatoo, Masao

IPC分类号： G06T5/40

CPC分类号： G06T7/00

摘要： An image processing apparatus comprises a character extraction unit (12, 24) for extracting an area whose density distribution characteristic meets a predetermined condition such as a binarization threshold and a size and a type of local filtering, from an input image (11) of multiple gray levels, and extracts an object area (15a) as an output image - (13) from the input image by using the characteristic extraction unit. Area designation means (15, 25) designates an area having a uniform density distribution and containing the object area, to the input image. Condition determination means (16, 26) determines the condition for the characteristic extraction unit based on the density distribution characteristic of the input image in the designated area. In an image processing expert system, the image characteristics of the object image and the background in the area designated by the area designation means are evaluated and analyzed (227, 223, 224) and the inquiry in the form of message is effected to quantize the evaluation of the image characteristic. As a result, the area extraction procedure (222) can be easily executed by the interaciton with an operator.

摘要翻译： 一种图像处理设备包括：字符提取单元（12,24），用于从多个输入图像（11）中提取密度分布特性满足诸如二值化阈值和局部滤波的大小和类型的预定条件的区域 灰度级，并且通过使用特征提取单元从输入图像中提取作为输出图像的对象区域（15a） - （13）。 区域指定装置（15,25）向输入图像指定具有均匀密度分布并包含对象区域的区域。 条件确定装置（16,26）基于指定区域中的输入图像的密度分布特性确定特征提取单元的条件。 在图像处理专家系统中，评估和分析由区域指定装置指定的区域中的对象图像和背景的图像特征（227,223,224），并且以消息形式进行查询以量化 评估图像特征。 结果，区域提取过程（222）可以通过与操作者的交互来容易地执行。

公开(公告)号：EP0198481A2

公开(公告)日：1986-10-22

申请号：EP86105213.2

申请日：1986-04-15

申请人： HITACHI, LTD.

发明人： Orita, Miyahiko ,  Kanasaki, Morio ,  Toda, Yuji ,  Mishima, Tadaaki ,  Suzuki, Masato ,  Onuma, Chieko ,  Takatoo, Masao

IPC分类号： G06T5/40

CPC分类号： G06T7/00

摘要： An image processing apparatus comprises a character extraction unit (12, 24) for extracting an area whose density distribution characteristic meets a predetermined condition such as a binarization threshold and a size and a type of local filtering, from an input image (11) of multiple gray levels, and extracts an object area (15a) as an output image - (13) from the input image by using the characteristic extraction unit. Area designation means (15, 25) designates an area having a uniform density distribution and containing the object area, to the input image. Condition determination means (16, 26) determines the condition for the characteristic extraction unit based on the density distribution characteristic of the input image in the designated area. In an image processing expert system, the image characteristics of the object image and the background in the area designated by the area designation means are evaluated and analyzed (227, 223, 224) and the inquiry in the form of message is effected to quantize the evaluation of the image characteristic. As a result, the area extraction procedure (222) can be easily executed by the interaciton with an operator.