公开(公告)号：EP0422654A2

公开(公告)日：1991-04-17

申请号：EP90119522.2

申请日：1990-10-11

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Uecker, Darrin R.

IPC分类号： G06K9/66

CPC分类号： G06K9/6211 ,  G06K9/66 ,  G06N3/04

摘要： A point pattern matching method and system for use in an object recognizing system for deciding pair combinations between a first group of n points p j (n: integer of 2 or more) (j: integer between 1 and n) in a K-dimensional space (K: integer of 2 or more) and a second group of n second points q i (i: integer between 1 and n) in the same space as the K-dimensional space, wherein a total of n 2 of neurons are provided one for each one of point pair combinations between the first group of points and the second group of points, and, when an output of each of the neurons has a value of substantially "1 ", it is determined that the point pair combination associated with the neuron is matched, whereas, when the output of the neuron has a value of substantially "0", it is determined that the point pair combination associated with the neuron is not matched.

摘要翻译： 的点图案上的对象匹配的使用的方法和系统在确认系统，用于决定第一组的n个点PJ之间的对组合中的K维空间：（1和n之间的整数j）（N 2或更大的整数） 被设置在相同的空间K维空间：（整数1，n之间i）中，worin神经元<2>总共n的：（K为2以上的整数）和n个第二个气的第二组 一个用于第一组点，并且点的第二组，并且，当每个神经元的输出具有基本上为“1”的值之间点的对组合中的每一个，它是确定性的开采并与相关联的点对组合 神经元被匹配，而当该神经元的输出具有基本上为“0”，它被确定的采空做了与神经元相关联的点对组合不匹配的值。

公开(公告)号：EP0422654B1

公开(公告)日：1996-03-06

申请号：EP90119522.2

申请日：1990-10-11

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Uecker, Darrin R.

IPC分类号： G06K9/66

CPC分类号： G06K9/6211 ,  G06K9/66 ,  G06N3/04

公开(公告)号：EP0560587A3

公开(公告)日：1995-12-06

申请号：EP93301810.3

申请日：1993-03-10

申请人： HITACHI, LTD.

发明人： Abe, Masahiro Hitachi Europe Ltd.Research and Deve ,  Sakou, Hiroshi ,  Sagawa, Hirohiko ,  Nitin, Indurkhya, c/o Telecom Research Lab.

IPC分类号： G09B21/00

CPC分类号： G06F17/2872 ,  G06F17/2881 ,  G06K9/00335 ,  G06K9/6293 ,  G06K9/685 ,  G09B19/06 ,  G09B21/00 ,  G09B21/009

摘要： A sign language translation system and method not only recognizes words of a sign language but also supplements omitted words between the words of the sign language, to thereby generate a spoken language. The sign language translation system has an input unit (105) for inputting at least the motion of hands, a language generating unit (102) responsive to the inputted motion of hands for recognizing the words corresponding to the motion of hands and generating a spoken language using the relationship between the recognized words, and an output unit (103) for outputting the generated spoken language. The sign language translation system and method can translate a sign language into an easy-to-understand spoken language.

摘要翻译： 手语翻译系统和方法不仅能识别手语的单词，而且可以补充手语之间的省略词，从而产生口语。 手语翻译系统具有用于至少输入手的运动的输入单元（105），响应于所输入的手的运动来识别与手的运动相对应的单词并产生口语的语言生成单元（102） 使用识别词之间的关系，以及用于输出生成的口语的输出单元（103）。 手语翻译系统和方法可以将手语翻译成易于理解的口语。

公开(公告)号：EP0585098A3

公开(公告)日：1995-01-11

申请号：EP93306674.8

申请日：1993-08-23

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Sagawa, Hirohiko, Hitachi Daiyon Kyoshinryo ,  Abe, Masahiro ,  Ichikawa, Akira ,  Inoue, Kiyoshi ,  Arai, Kiyoshi ,  Shimura, Takanori ,  Toda, Yuji

IPC分类号： G06K9/00

CPC分类号： G06F17/2872 ,  G06K9/00355 ,  G06K9/6293 ,  G06K9/685 ,  G09B21/009

摘要： In continuous sign language recognition, reference sign language patterns of good quality are generated. Continuous sign language patterns and reference sign language patterns are efficiently compressed. The compressed continuous sign language patterns are sequentially and directly matched with the compressed reference sign language patterns to recognize the sign language at high speed and with high precision. A reference sign pattern generating unit (3) generates a reference sign language pattern by normalizing sample patterns while taking into consideration of their nonlinear compression/expansion and by calculating an average of the sample patterns. A continuous sign language recognition unit (5) recognizes a continuous sign language at high speed by sequentially matching the continuous sign language of time sequential patterns with reference sign language patterns while allowing nonlinear expansion and compression in the time domain. A sign language translation system is provided in which a sign language as well as the facial expression or emotion of a sign language user is recognized and converted into a spoken language with emotion, and transferred in the form of texts, voices, sign languages of another type to a particular partner among a plurality of unknown system users.

公开(公告)号：EP0422654A3

公开(公告)日：1993-01-13

申请号：EP90119522.2

申请日：1990-10-11

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Uecker, Darrin R.

IPC分类号： G06K9/66

CPC分类号： G06K9/6211 ,  G06K9/66 ,  G06N3/04

摘要： A point pattern matching method and system for use in an object recognizing system for deciding pair combinations between a first group of n points p j (n: integer of 2 or more) (j: integer between 1 and n) in a K-dimensional space (K: integer of 2 or more) and a second group of n second points q i (i: integer between 1 and n) in the same space as the K-dimensional space, wherein a total of n 2 of neurons are provided one for each one of point pair combinations between the first group of points and the second group of points, and, when an output of each of the neurons has a value of substantially "1 ", it is determined that the point pair combination associated with the neuron is matched, whereas, when the output of the neuron has a value of substantially "0", it is determined that the point pair combination associated with the neuron is not matched.

公开(公告)号：EP0388725A2

公开(公告)日：1990-09-26

申请号：EP90104476.8

申请日：1990-03-08

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Matsushima, Hitoshi

IPC分类号： G06K9/20

CPC分类号： G06K9/38 ,  G06K2209/01

摘要： To reliably discriminate the characters only from the headlines having any background textures, the present invention analyzes the projection profile of a grey image in a headline area In order to automatically set a learning area A in the area of background texture only of the periphery in the headline area, and set a learning area B in the area that includes background texture of a central portion and characters; determines a discriminant function having, as variables, characteristics that use a plurality of pixel densities in the vicinity of a pixel which is processed so that output values of the discriminant function at each of the positions in the learning area A forms a profile with an average Va, that the output values at each of the positions in the learning area B forms a profile with an average Vb, and that the sum of dispersion values of the two profiles becomes smaller than a predetermined value, in order to discriminate in which area is included the pixel which is processed in the headline area; and determines in which area of the background pattern or the characters the pixel is included depending upon whether the output value of the discriminant function is close to the value Va or to the value Vb for each of the pixels in the headline area, in order to discriminate the headline area into areas.

摘要翻译： 为了从具有任何背景纹理的标题中可靠地区分字符，本发明分析了标题区域中的灰度图像的投影轮廓，以便仅在背景纹理的区域中自动设置学习区域A 标题区域，并在包括中心部分和字符的背景纹理的区域中设置学习区域B; 确定具有在处理的像素附近使用多个像素密度的特性作为变量的判别函数，使得学习区域A中的每个位置处的判别函数的输出值形成具有平均值的轮廓 Va，学习区域B中的每个位置处的输出值形成具有平均值Vb的轮廓，并且两个轮廓的色散值的和变得小于预定值，以便区分哪个区域是 包括在标题区域中处理的像素; 并且根据判别函数的输出值是否接近于值Va还是标题区域中的每个像素的值Vb，确定背景图案的哪个区域或者像素的包含的字符，以便 将标题区域区分为区域。

公开(公告)号：EP0560587B1

公开(公告)日：1999-06-02

申请号：EP93301810.3

申请日：1993-03-10

申请人： HITACHI, LTD.

发明人： Abe, Masahiro Hitachi Europe Ltd.Research and Deve ,  Sakou, Hiroshi ,  Sagawa, Hirohiko ,  Nitin, Indurkhya, c/o Telecom Research Lab.

IPC分类号： G09B21/00

CPC分类号： G06F17/2872 ,  G06F17/2881 ,  G06K9/00335 ,  G06K9/6293 ,  G06K9/685 ,  G09B19/06 ,  G09B21/00 ,  G09B21/009

公开(公告)号：EP0586259A3

公开(公告)日：1996-04-10

申请号：EP93306994.0

申请日：1993-09-03

申请人： HITACHI, LTD.

发明人： Masahiro, Abe ,  Sakou, Hiroshi ,  Sagawa, Hirohiko, Hitachi Daiyon Kyoshinryo ,  Ichikawa, Akira ,  Inoue, Kiyoshi ,  Shimura, Takanori ,  Toda, Yuji ,  Arai, Kiyoshi

IPC分类号： G09B21/00

CPC分类号： G09B21/009

摘要： In a sign-language learning system, the data of sign-language desired by a learner can be outputted quickly and accurately and moreover in the display method matching the requirement of individual learner and the individual learners can easily make additional registration. The sign-language data is preserved in a sign-language dictionary (1) and a desired sign-language data is searched on the basis of an entry word or contents by means of a dictionary search device (2). The searched sign-language data is displayed in a display output device (8) in accordance with a requirement of a learner by means of image synthesis. The sign-language data is registered by a dictionary registration device (3).

公开(公告)号：EP0585098A2

公开(公告)日：1994-03-02

申请号：EP93306674.8

申请日：1993-08-23

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Sagawa, Hirohiko, Hitachi Daiyon Kyoshinryo ,  Abe, Masahiro ,  Ichikawa, Akira ,  Inoue, Kiyoshi ,  Arai, Kiyoshi ,  Shimura, Takanori ,  Toda, Yuji

IPC分类号： G06K9/00

CPC分类号： G06F17/2872 ,  G06K9/00355 ,  G06K9/6293 ,  G06K9/685 ,  G09B21/009

摘要： In continuous sign language recognition, reference sign language patterns of good quality are generated. Continuous sign language patterns and reference sign language patterns are efficiently compressed. The compressed continuous sign language patterns are sequentially and directly matched with the compressed reference sign language patterns to recognize the sign language at high speed and with high precision. A reference sign pattern generating unit (3) generates a reference sign language pattern by normalizing sample patterns while taking into consideration of their nonlinear compression/expansion and by calculating an average of the sample patterns. A continuous sign language recognition unit (5) recognizes a continuous sign language at high speed by sequentially matching the continuous sign language of time sequential patterns with reference sign language patterns while allowing nonlinear expansion and compression in the time domain. A sign language translation system is provided in which a sign language as well as the facial expression or emotion of a sign language user is recognized and converted into a spoken language with emotion, and transferred in the form of texts, voices, sign languages of another type to a particular partner among a plurality of unknown system users.

摘要翻译： 在连续手语识别，生成质量好的符号语言模式。 连续手语图案和符号语言模式有效地压缩。 压缩连续符号的语言模式是顺序并直接与压缩基准符号语言模式匹配来识别手语以高速和高精确度。 参考符号图案通过归一化，同时考虑到它们的非线性压缩/膨胀的样本图案和通过计算在样品图案的平均生成部（3）基因率的参考符号的语言模式。 的连续手语识别单元（5）确认通过顺序地以高速连续手语与附图标记语言模式匹配的时间序列模式的连续的手语，同时允许在时域非线性膨胀和压缩。 手语翻译系统是将提供手语和手语使用者的面部表情或情绪被识别并转换成与情绪的口语，并在文字，声音的形式传输，签署的另一种语言 键入未知系统用户的多元化中的特定的合作伙伴。

公开(公告)号：EP0388725A3

公开(公告)日：1992-08-12

申请号：EP90104476.8

申请日：1990-03-08

申请人： HITACHI, LTD.

发明人： Sakou, Hiroshi ,  Matsushima, Hitoshi

IPC分类号： G06K9/20

CPC分类号： G06K9/38 ,  G06K2209/01

摘要： To reliably discriminate the characters only from the headlines having any background textures, the present invention analyzes the projection profile of a grey image in a headline area In order to automatically set a learning area A in the area of background texture only of the periphery in the headline area, and set a learning area B in the area that includes background texture of a central portion and characters; determines a discriminant function having, as variables, characteristics that use a plurality of pixel densities in the vicinity of a pixel which is processed so that output values of the discriminant function at each of the positions in the learning area A forms a profile with an average Va, that the output values at each of the positions in the learning area B forms a profile with an average Vb, and that the sum of dispersion values of the two profiles becomes smaller than a predetermined value, in order to discriminate in which area is included the pixel which is processed in the headline area; and determines in which area of the background pattern or the characters the pixel is included depending upon whether the output value of the discriminant function is close to the value Va or to the value Vb for each of the pixels in the headline area, in order to discriminate the headline area into areas.