-
131.发明授权公开(公告)号：US07054850B2
公开(公告)日：2006-05-30
申请号：US09878296
申请日：2001-06-12
申请人： Masakazu Matsugu
发明人： Masakazu Matsugu
CPC分类号： G06K9/4628 , G06K9/00973 , G06N3/049 , G06N3/063
摘要： A pattern detecting apparatus has a plurality of hierarchized neuron elements to detect a predetermined pattern included in input patterns. Pulse signals output from the plurality of neuron elements are given specific delays by synapse circuits associated with the individual elements. This makes it possible to transmit the pulse signals to the neuron elements of the succeeding layer through a common bus line so that they can be identified on a time base. The neuron elements of the succeeding layer output the pulse signals at output levels based on a arrival time pattern of the plurality of pulse signals received from the plurality of neuron elements of the preceding layer within a predetermined time window. Thus, the reliability of pattern detection can be improved, and the number of wires interconnecting the elements can be reduced by the use of the common bus line, leading to a small scale of circuit and reduced power consumption.
-
132.发明授权公开(公告)号：US06993184B2
公开(公告)日：2006-01-31
申请号：US10678255
申请日：2003-10-06
申请人： Masakazu Matsugu
发明人： Masakazu Matsugu
IPC分类号： G06K9/34
CPC分类号： G06K9/20
摘要： This invention provides an object extraction method for performing processing for extracting and cutting out a specific object from a sensed image at high speed, and an image sensing apparatus using the method. In this invention, in a method of extracting an object by comparing a sensed image and a standard image, a focusing signal, focal length data, visual axis direction data, and illumination conditions are detected, and the initial size, initial position, or initial color of the standard image is changed on the basis of the detection results, and extraction is started under optimal conditions. In a method of extracting a specific object from the background image, the background image is converted into an image having the same conditions as those of the object image. From a plurality of images obtained under different image sensing conditions, the contour of the object is accurately obtained at high speed. In an object extraction method using a template, the size of the template is determined on the basis of the object distance, object size, or the like.
摘要翻译： 本发明提供了一种用于执行从高速感测图像提取和切除特定对象的处理的对象提取方法以及使用该方法的图像感测装置。 在本发明中，在通过比较感测图像和标准图像来提取对象的方法中，检测聚焦信号，焦距数据，视轴方向数据和照明条件，并且初始尺寸，初始位置或初始 基于检测结果改变标准图像的颜色，并且在最佳条件下开始提取。 在从背景图像中提取特定对象的方法中，将背景图像转换为与对象图像的条件相同条件的图像。 从在不同图像感测条件下获得的多个图像中，以高速精确地获得对象的轮廓。 在使用模板的对象提取方法中，基于对象距离，对象大小等来确定模板的尺寸。
-
公开(公告)号：US06907140B2
公开(公告)日：2005-06-14
申请号：US10265923
申请日：2002-10-07
申请人： Masakazu Matsugu , Katsumi Iijima
发明人： Masakazu Matsugu , Katsumi Iijima
CPC分类号： G06K9/4604 , G06K9/00268 , G06T11/60
摘要： An image recognition/reproduction method includes an extraction step of extracting local feature elements of an image, and a selection step of selecting a pair composed of a prescribed local feature element and position information indicative thereof, this pair being such that the distance between a pair composed of a prescribed local feature element and position information indicative thereof and a pair composed of a local feature element extracted at the extraction step and position information indicative thereof is less than a prescribed distance.
摘要翻译： 图像识别/再现方法包括提取图像的局部特征元素的提取步骤，以及选择由规定的局部特征元素组成的对和表示其的位置信息的选择步骤， 由指定的局部特征元素和指示其的位置信息组成，并且由在提取步骤中提取的局部特征元素和由其指示的位置信息组成的对小于规定的距离。
-
公开(公告)号：US06766055B2
公开(公告)日：2004-07-20
申请号：US10150062
申请日：2002-05-20
IPC分类号： G06K934
CPC分类号： G06K9/48 , G06K9/6203 , G06T7/11 , G06T7/12 , G06T7/174 , G06T7/181 , G06T7/187 , G06T7/194 , G06T2207/10016 , G06T2207/20156 , G06T2207/20224
摘要： This invention relates to an image processing method for precisely and automatically recognizing a specific image extraction region to be divided from an input image, and extracting the specific image extraction region. Thresholding is done for intensity differences of edge data obtained from the input data to extract difference edge data. A main extraction region is estimated from the outermost contour line extracted based on the extraction result of the difference edge data. Thresholding or the like is done in units of pixels of the input image to extract an initial region. Extraction region determination processing is done for extracting an accurate target region by combining the main extraction region and initial region.
摘要翻译： 本发明涉及一种用于精确自动识别要从输入图像中划分的特定图像提取区域并提取特定图像提取区域的图像处理方法。 对从输入数据获得的边缘数据的强度差进行阈值处理，以提取差分边缘数据。 基于差分边缘数据的提取结果，从提取的最外层轮廓线估计主提取区域。 以输入图像的像素为单位进行阈值化等，以提取初始区域。 通过组合主提取区域和初始区域来提取精确目标区域的提取区域确定处理。
-
135.发明授权公开(公告)号：US06674902B1
公开(公告)日：2004-01-06
申请号：US09363655
申请日：1999-07-30
IPC分类号： G06K948
CPC分类号： G06T7/12 , G06T7/181 , G06T7/194 , G06T2207/20104 , G06T2207/20168 , G06T2207/30196
摘要： The objective of the present invention is to provide a simple and accurate process for extracting an object from an image, which is used to impose a great load for an operator. According to the present invention, an image processing apparatus comprises an object extracting unit, for performing a predetermined process for image data for a position or an area that is designated and for extracting a specific object from an image, an outline part deciding unit, for selecting and authenticating an arbitrary segment of an outline obtained by the extracting unit, and an outline synthesis unit, for linking and synthesizing together the outline segments that are authenticated. Since a closed curve is formed by synthesizing the outline segments obtained by repeating the above process, and the outline of the object is thus determined, the outline segment that is extracted from the image and matches the correct outline of the object is sequentially selected and authenticated. The thus authenticated outline segments are linked and synthesized to gradually form the overall outline of the object.
摘要翻译： 本发明的目的是提供一种用于从图像中提取物体的简单且准确的过程，其用于对操作者施加巨大的负载。 根据本发明，图像处理装置包括对象提取单元，用于对图像指定的位置或区域进行图像数据的预定处理，并从图像中提取特定对象，轮廓部分决定单元，用于 选择和认证由提取单元获得的轮廓的任意段，以及轮廓合成单元，用于将被认证的轮廓段链接和合成。 由于通过合成通过重复上述处理获得的轮廓段来形成闭合曲线，并且因此确定对象的轮廓，从图像中提取并与对象的正确轮廓匹配的轮廓线被顺序地选择和认证 。 这样认证的轮廓段被链接和合成，以逐渐形成对象的整体轮廓。
-
136.发明授权公开(公告)号：US06636635B2
公开(公告)日：2003-10-21
申请号：US08742206
申请日：1996-10-31
申请人： Masakazu Matsugu
发明人： Masakazu Matsugu
IPC分类号： G06K968
CPC分类号： G06K9/20
摘要： This invention provides an object extraction method for performing processing for extracting and cutting out a specific object from a sensed image at high speed, and an image sensing apparatus using the method. In this invention, in a method of extracting an object by comparing a sensed image and a standard image, a focusing signal, focal length data, visual axis direction data, and illumination conditions are detected, and the initial size, initial position, or initial color of the standard image is changed on the basis of the detection results, and extraction is started under optical conditions.
摘要翻译： 本发明提供了一种用于执行从高速感测图像提取和切除特定对象的处理的对象提取方法以及使用该方法的图像感测装置。 在本发明中，在通过比较感测图像和标准图像来提取对象的方法中，检测聚焦信号，焦距数据，视轴方向数据和照明条件，并且初始尺寸，初始位置或初始 基于检测结果改变标准图像的颜色，并且在光学条件下开始提取。
-
137.发明授权Image processing method and apparatus for block-based corresponding point extraction 失效基于块的对应点提取的图像处理方法和装置
公开(公告)号：US5734743A
公开(公告)日：1998-03-31
申请号：US503405
申请日：1995-07-11
申请人： Masakazu Matsugu , Katsumi Iijima
发明人： Masakazu Matsugu , Katsumi Iijima
IPC分类号： G01B11/00 , G06T1/00 , G06T7/00 , H04N5/208 , H04N5/268 , H04N13/00 , H04N19/102 , H04N19/105 , H04N19/119 , H04N19/134 , H04N19/136 , H04N19/139 , H04N19/14 , H04N19/167 , H04N19/176 , H04N19/192 , H04N19/196 , H04N19/20 , H04N19/423 , H04N19/46 , H04N19/50 , H04N19/51 , H04N19/537 , H04N19/57 , H04N19/70 , H04N19/80 , H04N19/85 , G06T9/20
CPC分类号： G06T1/00
摘要： An image processing method and apparatus for block-based corresponding-point extraction with high-precision, even if an image includes a discontinuous portion. The method comprises an extraction step of extracting edges or outline of a plurality of images, a dividing step of dividing the images into a plurality of blocks in such a manner that every block contains no edge and the sides of every block do not intersect with an edge, and a corresponding-point determination step of determining corresponding points between the images, based on similarity between one block of one image and a corresponding block of another image. Thus, even if one of the images includes a discontinuous portion, the corresponding-point extraction can be smoothly performed.
摘要翻译： 即使图像包括不连续部分，也可以高精度地进行基于块的对应点提取的图像处理方法和装置。 该方法包括：提取步骤，提取多个图像的边缘或轮廓;分割步骤，将图像分割成多个块，使得每个块不包含边缘，并且每个块的边不与 边缘，以及基于一个图像的一个块和另一个图像的对应块之间的相似度来确定图像之间的对应点的对应点确定步骤。 因此，即使图像中的一个包括不连续部分，也可以平滑地进行对应点提取。
-
公开(公告)号：US5162656A
公开(公告)日：1992-11-10
申请号：US841790
申请日：1992-03-02
申请人： Masakazu Matsugu , Kenji Saitoh , Shigeyuki Suda , Ryo Kuroda , Yukichi Niwa , Noriyuki Nose
发明人： Masakazu Matsugu , Kenji Saitoh , Shigeyuki Suda , Ryo Kuroda , Yukichi Niwa , Noriyuki Nose
IPC分类号： G03F9/00
CPC分类号： G03F9/7023 , G03F9/7049
摘要： A device for detecting positional relationship between a first and second objects in a predetermined direction is disclosed. The device includes light source for projecting light upon the first object so that the light incident on the first object is deflected thereby and emanates therefrom in a direction perpendicular to the predetermined direction; a light receiving portion disposed in a direction in which the light having been deflected perpendicularly to the predetermined direction and having been deflected again by the second object advances, the light receiving portion being operable to detect the position of incidence of the light thereupon, wherein the position of the light upon the light receiving means is changeable with the position of incidence of the light upon the second object; and a detecting system for detecting the positional relationship between the first and second objects in the predetermined direction, on the basis of the detection by the light receiving portion.
摘要翻译： 公开了一种用于检测预定方向上的第一和第二物体之间的位置关系的装置。 该装置包括用于将光投射到第一物体上的光源，使得入射在第一物体上的光由此偏转，并在垂直于预定方向的方向上从其发出; 光接收部分沿着垂直于预定方向偏转并被第二物体再次偏转的方向设置的方向延伸，光接收部分可操作以检测其上的光的入射位置，其中， 光在光接收装置上的位置可随着第二物体上的光入射位置而改变; 以及检测系统，用于基于光接收部分的检测来检测第一和第二物体在预定方向上的位置关系。
-
公开(公告)号：US5114236A
公开(公告)日：1992-05-19
申请号：US562656
申请日：1990-08-03
IPC分类号： G03F9/00
CPC分类号： G03F9/7076
摘要： A position detecting method for detecting the position of a substrate by use of a grating pattern provided on the substrate includes irradiating the grating pattern with first and second radiation beams having different wavelengths to produce first and second diffraction beams of different wavelengths; and receiving the first and second diffraction beams by use of a sensor to determine the position of the substrate on the basis of the position of incidence of each of the first and second diffraction beams on the sensor.
-
公开(公告)号：US4840473A
公开(公告)日：1989-06-20
申请号：US908725
申请日：1986-09-18
申请人： Nobuo Kushibiki , Noriyuki Nose , Toshiyuki Nakajima , Takeshi Baba , Masakazu Matsugu , Yukichi Niwa
发明人： Nobuo Kushibiki , Noriyuki Nose , Toshiyuki Nakajima , Takeshi Baba , Masakazu Matsugu , Yukichi Niwa
CPC分类号： G02B26/0875 , G11B7/09
摘要： An optical device is composed by sandwiching a deformable member between sandwiching members. The deformable member has a shear modulus decreasing toward the inside. The deformable member may be a combination of a core and a coating with different shear moduli or a single body having a continuoudly decreasing shear modulus. The sandwiching members may be a flat plate either transparent or opaque or a lens with or without reflecting film. Because of inner soft and outer hard elastic nature of the deformable member, the sandwiching members can easily change their relative position to change an optical path and an imaging position of the optical device with good durability.
摘要翻译： 光学装置通过将可变形构件夹在夹层构件之间而构成。 可变形构件的剪切模量向内侧减小。 可变形构件可以是具有不同剪切模量的芯和涂层的组合，或者具有连续降低的剪切模量的单体。 夹层构件可以是透明或不透明的平板或具有或不具有反射膜的透镜。 由于可变形构件的内部软和外部的硬弹性，因此夹持构件可以容易地改变其相对位置，以改变具有良好耐用性的光学装置的光路和成像位置。
-
-
-
-
-
-
-
-
-
搜索结果
200 条记录 (耗时 0.057 秒)
