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

US08571274B2 Person-judging device, method, and program 有权
标题翻译：人员判断设备，方法和程序
公开(公告)号：US08571274B2
公开(公告)日：2013-10-29
申请号：US13141446
申请日：2009-12-14
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/00
CPC分类号： G06K9/00362 , G06T7/73 , G06T2207/30196
摘要： A person-judging device comprises: an obstruction storage which stores information indicating an area of an obstruction which is extracted from an image based on a video signal from an external camera, the obstruction being extracted from the image; head portion range calculation means which, when a portion of an object which is extracted from the image is hidden by the obstruction, assumes that a potential range of grounding points where the object touches a reference face on the image is the area of the obstruction which is stored in the obstruction storage, and which, based on the assumed range and the correlation between the height of a person and the size and position of the head portion that are previously provided, calculates the potential range of the head portion on the image by assuming that a portion farthest from the grounding points of the object is the head portion of the person; and head portion detection means that judges whether an area including a shape corresponding to the head portion exists in the calculated range of the head portion.
摘要翻译：个人判断装置包括：障碍物存储器，其存储指示从图像提取的障碍物的区域的信息，所述信息是根据来自外部摄像机的视频信号提取的，所述障碍物从所述图像中提取; 头部范围计算装置，当从图像提取的对象的一部分被障碍物隐藏时，假定物体与图像上的参考面接触的接地点的潜在范围是阻塞区域，存储在障碍物存储器中，并且基于假定的范围和人的高度与预先提供的头部的尺寸和位置之间的相关性，通过以下方式计算图像上的头部的潜在范围：假设距物体的接地点最远的部分是人的头部; 以及头部检测装置，其判断在头部的计算范围内是否存在包括与头部相对应的形状的区域。

2. 发明申请

US20100142821A1 OBJECT RECOGNITION SYSTEM, OBJECT RECOGNITION METHOD AND OBJECT RECOGNITION PROGRAM 有权
标题翻译：对象识别系统，对象识别方法和对象识别程序
公开(公告)号：US20100142821A1
公开(公告)日：2010-06-10
申请号：US12595312
申请日：2008-04-04
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/46 , G06K9/62
CPC分类号： G06K9/6278 , G06K9/468
摘要： An object recognition system in which fall of the recognition rate is suppressed when an object is recognized based on an image even if there is a partial concealment and the object can be recognized even if the region of concealment is large with large calculation amount. With regard to each of a plurality of partial regions of an object image, partial recognition score of recognition object category is determined by judging whether it is a recognition object category or not. Under a condition that it is a recognition object category, total score is calculated using the total product of nonoccurrence probability of the partial recognition score, and a judgment is made that the object is not a recognition object category by that total score.
摘要翻译：一种对象识别系统，其中当基于图像识别对象时识别率的下降被抑制，即使存在部分隐藏，并且即使隐藏区域大，计算量大，也能够识别对象。关于对象图像的多个部分区域中的每一个，通过判断是否是识别对象类别来确定识别对象类别的部分识别分数。在识别对象类别的条件下，使用部分识别分数的不合格概率的总乘积来计算总分数，并且通过该总分判断对象不是识别对象类别。

3. 发明授权

US08965111B2 Learning apparatus, a learning system, learning method and a learning program for object discrimination 有权
标题翻译：学习设备，学习系统，学习方法和对象辨别学习程序
公开(公告)号：US08965111B2
公开(公告)日：2015-02-24
申请号：US13821864
申请日：2011-08-02
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/62 , G06K9/52 , G06N99/00
CPC分类号： G06K9/52 , G06K9/6256 , G06N99/005
摘要： A learning apparatus in the present invention includes a weak discriminator generation unit that generates a weak discriminator which calculates a discrimination score of an instance of a target based on a feature and a bag label, a weak discrimination unit which calculates the discrimination score based on the generated weak discriminator, an instance probability calculation unit that calculates an instance probability of the target instance based on the calculated the discrimination score, a bag probability calculation unit that calculates a probability that no smaller than two positive instances are included in the bag based on the calculated instance probability and a likelihood calculation unit which calculates likelihood representing plausibility of the bag probability based on the bag label.
摘要翻译：本发明的学习装置包括：弱鉴别器生成单元，其生成基于特征和袋子标签计算目标的实例的辨别分数的弱识别器;弱识别单元，其基于基于所计算的所述判别分数计算所述目标实例的实例概率的实例概率计算单元，基于所述判别分数计算所述袋中包含不少于两个正实例的概率的袋概率计算单元; 计算的实例概率和似然度计算单元，其基于袋子标签计算表示袋概率的似然性的似然。

4. 发明授权

US08660321B2 Authentication system, apparatus, authentication method, and storage medium with program stored therein 有权
标题翻译：验证系统，装置，认证方法和存储有程序的存储介质
公开(公告)号：US08660321B2
公开(公告)日：2014-02-25
申请号：US13129523
申请日：2009-10-05
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/00 , G06F21/00 , G06F7/04
CPC分类号： G06K9/00288
摘要： Unauthorized use of a biological pattern registered in a face image authorization system is made difficult. With respect to the previously registered biological pattern for authorization, additional information is held concerning a change that can be reproduced by a user having the biological pattern for authentication, and success or failure of the authentication is evaluated according to consistency between the biological pattern for authentication that is reproduced using the additional information and a pattern input at the time of authentication as an evaluation factor. By changing the additional information as necessary, unauthorized use of biological pattern data or the like is made difficult.
摘要翻译：未经授权使用注册在面部图像授权系统中的生物模式变得困难。关于以前登记的授权生物模式，关于可以由具有用于认证的生物学模式的用户再现的变化的附加信息，并且根据用于认证的生物学模式之间的一致性来评估认证的成败使用附加信息和认证时的模式输入作为评估因子进行再现。通过根据需要改变附加信息，难以使未经授权使用生物图案数据等。

5. 发明申请

US20130170739A1 LEARNING APPARATUS, A LEARNING SYSTEM, LEARNING METHOD AND A LEARNING PROGRAM FOR OBJECT DISCRIMINATION 有权
标题翻译：学习设备，学习系统，学习方法和对象歧视的学习计划
公开(公告)号：US20130170739A1
公开(公告)日：2013-07-04
申请号：US13821864
申请日：2011-08-02
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/52
CPC分类号： G06K9/52 , G06K9/6256 , G06N99/005
摘要： A learning apparatus in the present invention includes a weak discriminator generation unit that generates a weak discriminator which calculates a discrimination score of an instance of a target based on a feature and a bag label, a weak discrimination unit which calculates the discrimination score based on the generated weak discriminator, an instance probability calculation unit that calculates an instance probability of the target instance based on the calculated the discrimination score, a bag probability calculation unit that calculates a probability that no smaller than two positive instances are included in the bag based on the calculated instance probability and a likelihood calculation unit which calculates likelihood representing plausibility of the bag probability based on the bag label.
摘要翻译：本发明的学习装置包括：弱鉴别器生成单元，其生成基于特征和袋子标签计算目标的实例的辨别分数的弱识别器;弱识别单元，其基于基于所计算的所述判别分数计算所述目标实例的实例概率的实例概率计算单元，基于所述判别分数计算所述袋中包含不少于两个正实例的概率的袋概率计算单元; 计算的实例概率和似然度计算单元，其基于袋子标签计算表示袋概率的似然性的似然。

6. 发明授权

US07680299B2 Unauthorized person detection device and unauthorized person detection method 失效
标题翻译：未经授权的人员检测设备和未经授权的人员检测方法
公开(公告)号：US07680299B2
公开(公告)日：2010-03-16
申请号：US10545373
申请日：2004-02-12
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/00
CPC分类号： G06K9/2036 , G06K9/00255 , G06K9/00899
摘要： In masquerading determination processing, a masquerading determination unit reads image data representing an image of an identification target on which a striped pattern is projected from an image storage unit to extract the striped pattern appearing in a face region of the image represented by the read image data. Subsequently, the masquerading determination unit determines whether a stripe in the face region in the image is a straight line or not. When the stripe is a straight line, because the identification target is a plane object such as a photograph or an image display device so that it can be determined that the target is at least not a person himself, the masquerading determination unit determines that the target masquerades. On the other hand, unless the stripe is a straight line, because the identification target has a solid configuration having three-dimensional irregularities to have a possibility of being a person himself, the unit determines that the target might not masquerade.
摘要翻译：在伪装判定处理中，伪装判定部从图像存储部读取表示其上投射有条纹图案的识别对象的图像的图像数据，以提取出现在由读取图像数据表示的图像的面部区域中的条纹图案。随后，伪装判定单元确定图像中的脸部区域中的条纹是否为直线。当条纹是直线时，由于识别目标是诸如照片或图像显示装置的平面对象，从而可以确定目标至少不是人本身，伪装确定单元确定目标化装舞会另一方面，除非条纹是直线，否则由于识别目标具有具有三维不规则性的实体构造以具有自己的人的可能性，所以该单元确定目标可能不会伪装。

7. 发明申请

US20060093183A1 Unauthorized person detection device and unauthorized person detection method 失效
标题翻译：未经授权的人员检测设备和未经授权的人员检测方法
公开(公告)号：US20060093183A1
公开(公告)日：2006-05-04
申请号：US10545373
申请日：2004-02-12
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/00
CPC分类号： G06K9/2036 , G06K9/00255 , G06K9/00899
摘要： In masquerading determination processing, a masquerading determination unit reads image data representing an image of an identification target on which a striped pattern is projected from an image storage unit to extract the striped pattern appearing in a face region of the image represented by the read image data. Subsequently, the masquerading determination unit determines whether a stripe in the face region in the image is a straight line or not. When the stripe is a straight line, because the identification target is a plane object such as a photograph or an image display device so that it can be determined that the target is at least not a person himself, the masquerading determination unit determines that the target masquerades. On the other hand, unless the stripe is a straight line, because the identification target has a solid configuration having three-dimensional irregularities to have a possibility of being a person himself, the unit determines that the target might not masquerade.
摘要翻译：在伪装判定处理中，伪装判定部从图像存储部读取表示其上投射有条纹图案的识别对象的图像的图像数据，以提取出现在由读取图像数据表示的图像的面部区域中的条纹图案。随后，伪装判定单元确定图像中的脸部区域中的条纹是否为直线。当条纹是直线时，由于识别目标是诸如照片或图像显示装置的平面对象，从而可以确定目标至少不是人本身，伪装确定单元确定目标化装舞会另一方面，除非条纹是直线，否则由于识别目标具有具有三维不规则性的实体构造以具有自己的人的可能性，所以该单元确定目标可能不会伪装。

8. 发明授权

US09036903B2 Learning device, identification device, learning identification system and learning identification device 有权
标题翻译：学习装置，识别装置，学习识别系统和学习识别装置
公开(公告)号：US09036903B2
公开(公告)日：2015-05-19
申请号：US13520766
申请日：2010-12-24
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G06K9/00248 , G06K9/4614
摘要： A learning device includes a gradient feature extraction unit which extracts a gradient feature amount including a gradient direction at each coordinate and a gradient intensity value thereof based on an amount of variation between luminance at each coordinate of an inputted learning target pattern and luminance at a periphery thereof, a sum difference feature extraction unit which calculates a predetermined sum difference feature amount by adding the gradient intensity values according to the gradient directions included in a predetermined gradient range indicating a range of the predetermined gradient direction based on the extracted gradient feature amount and subtracting the gradient intensity values according to the gradient directions included in the other gradient range adjacent to the predetermined gradient range from the calculated sum, and a learning unit which acquires a learning parameter at each coordinate.
摘要翻译：学习装置包括梯度特征提取单元，该梯度特征提取单元基于输入的学习目标图案的各坐标处的亮度与周边的亮度之间的变化量，提取包括各坐标的梯度方向的梯度特征量及其梯度强度值和差差特征提取单元，其通过基于提取的梯度特征量，根据包括在指示预定梯度方向的范围的预定梯度范围内的梯度方向相加梯度强度值来计算预定和差特征量，并减去根据从计算出的和相邻于预定梯度范围的另一个梯度范围中包括的梯度方向的梯度强度值，以及获取每个坐标处的学习参数的学习单元。

9. 发明授权

US08478055B2 Object recognition system, object recognition method and object recognition program which are not susceptible to partial concealment of an object 有权
标题翻译：对象识别系统，对象识别方法和对象识别程序，不易受到对象的局部隐藏
公开(公告)号：US08478055B2
公开(公告)日：2013-07-02
申请号：US12595312
申请日：2008-04-04
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/62 , G06K9/00 , G06K9/34 , G06F17/18
CPC分类号： G06K9/6278 , G06K9/468
摘要： An object recognition system in which fall of the recognition rate is suppressed when an object is recognized based on an image even if there is a partial concealment and the object can be recognized even if the region of concealment is large with large calculation amount. With regard to each of a plurality of partial regions of an object image, partial recognition score of recognition object category is determined by judging whether it is a recognition object category or not. Under a condition that it is a recognition object category, total score is calculated using the total product of nonoccurrence probability of the partial recognition score, and a judgment is made that the object is not a recognition object category by that total score.
摘要翻译：一种对象识别系统，其中当基于图像识别对象时识别率的下降被抑制，即使存在部分隐藏，并且即使隐藏区域大，计算量大，也能够识别对象。关于对象图像的多个部分区域中的每一个，通过判断是否是识别对象类别来确定识别对象类别的部分识别分数。在识别对象类别的条件下，使用部分识别分数的不合格概率的总乘积来计算总分数，并且通过该总分判断对象不是识别对象类别。

10. 发明申请

US20120281909A1 LEARNING DEVICE, IDENTIFICATION DEVICE, LEARNING IDENTIFICATION SYSTEM AND LEARNING IDENTIFICATION DEVICE 有权
标题翻译：学习设备，识别设备，学习识别系统和学习识别设备
公开(公告)号：US20120281909A1
公开(公告)日：2012-11-08
申请号：US13520766
申请日：2010-12-24
申请人： Toshinori Hosoi
发明人： Toshinori Hosoi
IPC分类号： G06K9/62 , G06K9/46
CPC分类号： G06K9/00248 , G06K9/4614
摘要： A learning device includes a gradient feature extraction unit which extracts a gradient feature amount including a gradient direction at each coordinate and a gradient intensity value thereof based on an amount of variation between luminance at each coordinate of an inputted learning target pattern and luminance at a periphery thereof, a sum difference feature extraction unit which calculates a predetermined sum difference feature amount by adding the gradient intensity values according to the gradient directions included in a predetermined gradient range indicating a range of the predetermined gradient direction based on the extracted gradient feature amount and subtracting the gradient intensity values according to the gradient directions included in the other gradient range adjacent to the predetermined gradient range from the calculated sum, and a learning unit which acquires a learning parameter at each coordinate.
摘要翻译：学习装置包括梯度特征提取单元，该梯度特征提取单元基于输入的学习目标图案的各坐标处的亮度与周边的亮度之间的变化量，提取包括各坐标的梯度方向的梯度特征量及其梯度强度值和差差特征提取单元，其通过基于提取的梯度特征量，根据包括在指示预定梯度方向的范围的预定梯度范围内的梯度方向相加梯度强度值来计算预定和差特征量，并减去根据从计算出的和相邻于预定梯度范围的另一个梯度范围中包括的梯度方向的梯度强度值，以及获取每个坐标处的学习参数的学习单元。

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