专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08538172B2 Image recognition apparatus with a plurality of classifiers 有权
标题翻译：具有多个分类器的图像识别装置
公开(公告)号：US08538172B2
公开(公告)日：2013-09-17
申请号：US12804715
申请日：2010-07-28
申请人： Takashi Bandou , Naoki Fukaya
发明人： Takashi Bandou , Naoki Fukaya
IPC分类号： G06K9/62
CPC分类号： G06K9/6257
摘要： In an apparatus, an applying unit applies selected classifiers in sequence to an object image. A score calculating unit calculates, each time a classifier is applied to the object image, a summation of an output of an at least one classifier already applied to the object image to thereby obtain an acquisition score as the summation. The output of the at least one already applied classifier is weighed by a corresponding weight. A distribution calculating unit calculates, each time a classifier is applied to the object image, a predicted distribution of the acquisition score that would be obtained if at least one unapplied classifier in the classifiers, which has not yet been applied to the object image, were applied to the object image. A judging unit judges, based on the predicted distribution, whether to terminate an application of the at least one unapplied classifier to the object image.
摘要翻译：在装置中，应用单元依次将选定的分类器应用于对象图像。分数计算单元在将分类器应用于对象图像时，计算已经应用于对象图像的至少一个分类器的输出的和，从而获得获取分数作为求和。至少一个已经应用的分选机的输出被相应的重量称重。分配计算单元在分类器被应用于对象图像的每一次时，计算如果还没有应用于对象图像的分类器中的至少一个未应用的分类器，将获得的获取分数的预测分布为应用于对象图像。判断单元基于预测分布来判断是否终止至少一个未应用的分类器到对象图像的应用。

2. 发明授权

US07668337B2 Ellipsoid detecting method, figure center detecting method, image recognizing device, and controller based on image 有权
标题翻译：椭圆体检测方法，图形中心检测方法，图像识别装置和基于图像的控制器
公开(公告)号：US07668337B2
公开(公告)日：2010-02-23
申请号：US11512482
申请日：2006-08-30
申请人： Naoki Fukaya , Hironobu Fujiyoshi , Yuusuke Sakashita , Hisanori Takamaru
发明人： Naoki Fukaya , Hironobu Fujiyoshi , Yuusuke Sakashita , Hisanori Takamaru
IPC分类号： G06K9/00 , G09B23/02
CPC分类号： G06K9/00604 , G06K9/6205
摘要： A method for detecting an ellipsoid includes: extracting an ellipsoid candidate; extracting an ellipsoid contour; calculating an ellipsoid parameter; calculating an adaptability ratio; and eliminating the ellipsoid candidate. Extracting the ellipsoid candidate includes: inputting an image with figures; selecting the ellipsoid candidate from the figures; and extracting a contour candidate point and a center point. Extracting the ellipsoid contour includes: drawing straight lines; determining contour candidate points; calculating first and second distances; and defining ellipsoid contour points. Calculating the ellipsoid parameter is based on the ellipsoid contour points and the center point. Calculating the adaptability ratio includes: drawing a complete ellipsoid; and calculating the adaptability ratio between the complete ellipsoid and the ellipsoid candidate. Eliminating the ellipsoid candidate is performed when the adaptability ratio is equal to or smaller than a threshold.
摘要翻译：一种用于检测椭球的方法包括：提取椭球候选; 提取椭球轮廓; 计算椭球参数; 计算适应性比率; 并消除椭球候选。提取椭球候选者包括：用图形输入图像; 从图中选择椭球候选者; 并提取轮廓候选点和中心点。提取椭球轮廓包括：绘制直线; 确定轮廓候选点; 计算第一和第二距离; 并定义椭圆轮廓点。计算椭球参数是基于椭球轮廓点和中心点。计算适应性比例包括：绘制完整的椭圆体; 并计算完整椭球和椭球候选的适应度比。当适应性比例等于或小于阈值时，执行消除椭球候选。

3. 发明授权

US08165408B2 Image recognition apparatus utilizing plurality of weak classifiers for evaluating successive sub-images extracted from an input image 有权
标题翻译：利用多个弱分类器来评估从输入图像提取的连续子图像的图像识别装置
公开(公告)号：US08165408B2
公开(公告)日：2012-04-24
申请号：US12455854
申请日：2009-06-08
申请人： Naoki Fukaya , Takashi Bando
发明人： Naoki Fukaya , Takashi Bando
IPC分类号： G06K9/62
CPC分类号： G06K9/00228 , G06K9/00281 , G06K9/629 , G06K9/68
摘要： The position of a face image within an input image is detected based on results from applying a plurality of weak classifiers in sequence to each of sub-images extracted from the input image. A decision whether to interrupt the sequence and reject a currently extracted sub-image is made based on the sum of a total of weighted decision values obtained up to the current point in the sequence and a total of potential weighted decision values obtainable from the remaining weak classifiers if the extracted sub-image were a face image.
摘要翻译：基于从输入图像提取的每个子图像依次应用多个弱分类器的结果来检测输入图像内的面部图像的位置。基于在该序列中的当前点获得的加权决策值的总和和从剩余的弱的可获得的潜在加权决策值的总和来进行是否中断该序列并拒绝当前提取的子图像的决定如果提取的子图像是面部图像，则分类器。

4. 发明授权

US07813544B2 Estimation device 有权
标题翻译：估计装置
公开(公告)号：US07813544B2
公开(公告)日：2010-10-12
申请号：US11642763
申请日：2006-12-20
申请人： Naoki Fukaya , Mikio Shimizu , Shin Ishii , Tomohiro Shibata , Takashi Bando
发明人： Naoki Fukaya , Mikio Shimizu , Shin Ishii , Tomohiro Shibata , Takashi Bando
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00248
摘要： An estimation device estimates a hidden state of an estimation subject from an observable state in a manner of a time series. The observable state is observed from the hidden state of the estimation subject under a procedure that has a hierarchical structure, which includes the hidden state of the estimation subject, the observable state, and an intermediate hidden state therebetween. The estimation device includes an estimation subject hidden state predicting means, an intermediate hidden state predicting means based on the state transition structure of the hidden state of the estimation subject, an intermediate hidden state likelihood observing means, an intermediate hidden state estimating means, an estimation subject hidden state likelihood observing means, estimation subject hidden state estimating means, an intermediate hidden state predicting means based on the state transition structure of the intermediate hidden state, and the mixing means.
摘要翻译：估计装置以时间序列的方式估计估计对象的可观察状态的隐藏状态。从具有层次结构的程序的估计对象的隐藏状态观察可观察状态，其包括估计对象的隐藏状态，可观察状态和它们之间的中间隐藏状态。估计装置包括估计对象隐藏状态预测装置，基于估计对象的隐藏状态的状态转移结构的中间隐藏状态预测装置，中间隐藏状态似然观察装置，中间隐藏状态估计装置，估计被摄体隐藏状态似然观察装置，估计对象隐藏状态估计装置，基于中间隐藏状态的状态转移结构的中间隐藏状态预测装置和混合装置。

5. 发明授权

US07705738B2 Database apparatus, attention calling apparatus and driving support apparatus 有权
标题翻译：数据库设备，注意呼叫装置和驾驶辅助装置
公开(公告)号：US07705738B2
公开(公告)日：2010-04-27
申请号：US12079134
申请日：2008-03-25
申请人： Naoki Fukaya , Kentarou Hitomi
发明人： Naoki Fukaya , Kentarou Hitomi
IPC分类号： G08B23/00
CPC分类号： B60T7/22 , B60W40/09 , B60W2040/0818
摘要： An attention calling apparatus operates in the following manner. That is, eyes distribution pattern is generated from the behavior of the eyes of the vehicle driver captured by a camera in a predetermined time, and driver's condition is estimated based on the distribution pattern. Further, concentration of the driver on driving is estimated based on the comparison between the distribution pattern and the stored information of distribution pattern. When the distribution pattern indicates that the degree of concentration on driving is high, the driving operation is stored in storage in association with the concentration degree. When the operation situation fulfills a notification provision condition, driver's attention is called depending on the concentration degree.
摘要翻译：注意呼叫装置以如下方式操作。也就是说，从预定时间内由摄像机拍摄的车辆驾驶员的眼睛的行为产生眼睛分布图案，并且基于分布模式来估计驾驶员的状况。此外，基于分配模式和分配模式的存储信息之间的比较来估计驾驶员在驾驶中的浓度。当分配模式表明驾驶集中度高时，将驾驶操作与集中度相关联地存储在存储中。当操作情况满足通知提供条件时，根据集中程度来调用驾驶员的注意力。

6. 发明授权

US06620104B2 Vital signal detecting apparatus and noninvasive blood pressure meter 失效
标题翻译：生命信号检测仪和无创血压计
公开(公告)号：US06620104B2
公开(公告)日：2003-09-16
申请号：US09745839
申请日：2000-12-26
申请人： Shinichi Tamura , Naoki Fukaya
发明人： Shinichi Tamura , Naoki Fukaya
IPC分类号： A61B500
CPC分类号： A61B5/02125 , A61B5/022 , A61B5/7239
摘要： A vital signal detecting apparatus is composed of sensors for detecting pulse waves, an A/D converter for converting analog signals, corresponding to the pulse waves and derived from the sensors, into digital signals, a separation matrix calculation means, and a signal separation calculation circuit. The separation matrix calculation circuit calculates a separation matrix for separating an outer disturbance caused by body movement from the pulse waves. The signal separation calculation means divides the digital signals converted by the A/D converter into a vital signal containing no outer disturbance and a body movement signal indicating the outer disturbance by using the separation matrix.
摘要翻译：重要的信号检测装置由用于检测脉搏波的传感器组成，A / D转换器将与传感器相对应的脉冲波的模拟信号转换为数字信号，分离矩阵计算装置和信号分离计算电路。分离矩阵计算电路计算用于分离由身体移动引起的外部干扰与脉冲波的分离矩阵。信号分离计算装置通过使用分离矩阵将由A / D转换器转换的数字信号分成不包含外部干扰的重要信号和指示外部干扰的体动信号。

7. 发明授权

US08107735B2 Three dimensional shape reconstitution device and estimation device 有权
标题翻译：三维形状重构装置及估计装置
公开(公告)号：US08107735B2
公开(公告)日：2012-01-31
申请号：US11906557
申请日：2007-10-02
申请人： Mikio Shimizu , Naoki Fukaya , Takashi Bando , Tomohiro Shibata , Shin Ishii
发明人： Mikio Shimizu , Naoki Fukaya , Takashi Bando , Tomohiro Shibata , Shin Ishii
IPC分类号： G06K9/00
CPC分类号： G06K9/00248 , G06K9/00281
摘要： A face model providing portion provides an stored average face model to an estimation portion estimating an affine parameter for obtaining a head pose. An individual face model learning portion obtains a result of tracking feature points by the estimation portion and learns an individual face model. The individual face model learning portion terminates the learning when a free energy of the individual face model is over a free energy of the average face model, and switches a face model provided to the estimation portion from the average face model to the individual face model. While learning the individual face mode, an observation matrix is factorized using a reliability matrix showing reliability of each observation value forming the observation matrix with emphasis on the feature point having higher reliability.
摘要翻译：面部模型提供部分将估计部分的存储的平均面部模型提供给用于获得头部姿势的仿射参数。个人面部模型学习部分通过估计部分获得跟踪特征点的结果，并学习个人面部模型。当个人面部模型的自由能超过平均面部模型的自由能时，个人面部模型学习部分终止学习，并将提供给估计部分的面部模型从平均面部模型切换到个人面部模型。在学习个人面部模式的同时，使用显示形成观察矩阵的每个观察值的可靠性的可靠度矩阵来分解观察矩阵，强调特征点具有较高的可靠性。

8. 发明申请

US20110026829A1 Image recognition apparatus with a plurality of classifiers 有权
标题翻译：具有多个分类器的图像识别装置
公开(公告)号：US20110026829A1
公开(公告)日：2011-02-03
申请号：US12804715
申请日：2010-07-28
申请人： Takashi Bandou , Naoki Fukaya
发明人： Takashi Bandou , Naoki Fukaya
IPC分类号： G06K9/68 , G06K9/46
CPC分类号： G06K9/6257
摘要： In an apparatus, an applying unit applies selected classifiers in sequence to an object image. A score calculating unit calculates, each time a classifier is applied to the object image, a summation of an output of an at least one classifier already applied to the object image to thereby obtain an acquisition score as the summation. The output of the at least one already applied classifier is weighed by a corresponding weight. A distribution calculating unit calculates, each time a classifier is applied to the object image, a predicted distribution of the acquisition score that would be obtained if at least one unapplied classifier in the classifiers, which has not yet been applied to the object image, were applied to the object image. A judging unit judges, based on the predicted distribution, whether to terminate an application of the at least one unapplied classifier to the object image.
摘要翻译：在装置中，应用单元依次将选定的分类器应用于对象图像。分数计算单元在将分类器应用于对象图像时，计算已经应用于对象图像的至少一个分类器的输出的和，从而获得获取分数作为求和。至少一个已经应用的分选机的输出被相应的重量称重。分配计算单元在分类器被应用于对象图像的每一次时，计算如果还没有应用于对象图像的分类器中的至少一个未应用的分类器，将获得的获取分数的预测分布为应用于对象图像。判断单元基于预测分布来判断是否终止至少一个未应用的分类器到对象图像的应用。

9. 发明申请

US20080253610A1 Three dimensional shape reconstitution device and estimation device 有权
标题翻译：三维形状重构装置及估计装置
公开(公告)号：US20080253610A1
公开(公告)日：2008-10-16
申请号：US11906557
申请日：2007-10-02
申请人： Mikio Shimizu , Naoki Fukaya , Takashi Bando , Tomohiro Shibata , Shin Ishii
发明人： Mikio Shimizu , Naoki Fukaya , Takashi Bando , Tomohiro Shibata , Shin Ishii
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00248 , G06K9/00281
摘要： A face model providing portion provides an stored average face model to an estimation portion estimating an affine parameter for obtaining a head pose. An individual face model learning portion obtains a result of tracking feature points by the estimation portion and learns an individual face model. The individual face model learning portion terminates the learning when a free energy of the individual face model is over a free energy of the average face model, and switches a face model provided to the estimation portion from the average face model to the individual face model. While learning the individual face mode, an observation matrix is factorized using a reliability matrix showing reliability of each observation value forming the observation matrix with emphasis on the feature point having higher reliability.
摘要翻译：面部模型提供部分将估计部分的存储的平均面部模型提供给用于获得头部姿势的仿射参数。个人面部模型学习部分通过估计部分获得跟踪特征点的结果，并学习个人面部模型。当个人面部模型的自由能超过平均面部模型的自由能时，个人面部模型学习部分终止学习，并将提供给估计部分的面部模型从平均面部模型切换到个人面部模型。在学习个人面部模式的同时，使用显示形成观察矩阵的每个观察值的可靠性的可靠度矩阵来分解观察矩阵，强调特征点具有较高的可靠性。

10. 发明申请

US20070133879A1 Ellipsoid detecting method, figure center detecting method, image recognizing device, and controller based on image 有权
标题翻译：椭圆体检测方法，图形中心检测方法，图像识别装置和基于图像的控制器
公开(公告)号：US20070133879A1
公开(公告)日：2007-06-14
申请号：US11512482
申请日：2006-08-30
申请人： Naoki Fukaya , Hironobu Fujiyoshi , Yuusuke Sakashita , Hisanori Takamaru
发明人： Naoki Fukaya , Hironobu Fujiyoshi , Yuusuke Sakashita , Hisanori Takamaru
IPC分类号： G06K9/46
CPC分类号： G06K9/00604 , G06K9/6205
摘要： A method for detecting an ellipsoid includes: extracting an ellipsoid candidate; extracting an ellipsoid contour; calculating an ellipsoid parameter; calculating an adaptability ratio; and eliminating the ellipsoid candidate. Extracting the ellipsoid candidate includes: inputting an image with figures; selecting the ellipsoid candidate from the figures; and extracting a contour candidate point and a center point. Extracting the ellipsoid contour includes: drawing straight lines; determining contour candidate points; calculating first and second distances; and defining ellipsoid contour points. Calculating the ellipsoid parameter is based on the ellipsoid contour points and the center point. Calculating the adaptability ratio includes: drawing a complete ellipsoid; and calculating the adaptability ratio between the complete ellipsoid and the ellipsoid candidate. Eliminating the ellipsoid candidate is performed when the adaptability ratio is equal to or smaller than a threshold.
摘要翻译：一种用于检测椭球的方法包括：提取椭球候选; 提取椭球轮廓; 计算椭球参数; 计算适应性比率; 并消除椭球候选。提取椭球候选者包括：用图形输入图像; 从图中选择椭球候选者; 并提取轮廓候选点和中心点。提取椭球轮廓包括：绘制直线; 确定轮廓候选点; 计算第一和第二距离; 并定义椭圆轮廓点。计算椭球参数是基于椭球轮廓点和中心点。计算适应性比例包括：绘制完整的椭圆体; 并计算完整椭球和椭球候选的适应度比。当适应性比例等于或小于阈值时，执行消除椭球候选。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式