公开(公告)号：WO2005096178A8

公开(公告)日：2006-02-09

申请号：PCT/GB2005001124

申请日：2005-03-11

Applicant: ISIS INNOVATION ,  ZISSERMAN ANDREW ,  FERGUS ROBERT ,  PERONA PIETRO

Inventor： ZISSERMAN ANDREW ,  FERGUS ROBERT ,  PERONA PIETRO

IPC: G06F17/30 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06F17/30259 ,  G06F17/30265 ,  G06K9/46

Abstract: A method for determining the relevance of images retrieved from a database to a specified visual object category, represented by the query keyword, the method comprising learning a model defining features of said visual object category and a spatial relationship therebetween, storing said model, comparing a set of images retrieved from said database with said stored model and calculating a likelihood value relating to each image based on its correspondence with said model.

Abstract translation: 一种用于确定从数据库检索到指定视觉对象类别的图像的相关性的方法，由查询关键字表示，所述方法包括学习定义所述视觉对象类别的特征的模型及其间的空间关系，存储所述模型，比较 基于与所述模型的对应关系，利用所述存储的模型从所述数据库检索的图像集合，并且计算与每个图像相关的似然值。

公开(公告)号：WO2004111931A2

公开(公告)日：2004-12-23

申请号：PCT/US2004/018497

申请日：2004-06-10

Applicant: CALIFORNIA INSTITUTE OF TECHNOLOGY ,  KOCH, Christof ,  PERONA, Pietro ,  RUTISHAUSER, Ueli ,  WALTHER, Dirk

Inventor： KOCH, Christof ,  PERONA, Pietro ,  RUTISHAUSER, Ueli ,  WALTHER, Dirk

IPC: G06T

CPC classification number: G06K9/4628 ,  G06K9/3233 ,  G06K9/4671 ,  G06K9/6256

Abstract: The present invention relates to a system and method for attentional selection. More specifically, the present invention relates to a system and method for the automated selection and isolation of salient regions likely to contain objects, based on bottom-up visual attention, in order to allow unsupervised one-shot learning of multiple objects in cluttered images.

Abstract translation: 本发明涉及一种用于注意选择的系统和方法。 更具体地，本发明涉及一种用于基于自下而上的视觉注意自动选择和分离可能包含对象的显着区域的系统和方法，以便允许在混乱图像中的多个对象的无监督的单次学习。

公开(公告)号：WO2008051173A2

公开(公告)日：2008-05-02

申请号：PCT/US2004/018496

申请日：2004-06-12

Applicant: CALIFORNIA INSTITUTE OF TECHNOLOGY ,  KOCH, Christof ,  PERONA, Pietro ,  RUTISHAUSER, Ueli ,  WALTHER, Dirk

Inventor： KOCH, Christof ,  PERONA, Pietro ,  RUTISHAUSER, Ueli ,  WALTHER, Dirk

CPC classification number: G06K9/4671

Abstract: The present invention relates to a system and method for attentional selection. More specifically, the present invention relates to a system and method for the automated selection and isolation of salient regions likely to contain objects, based on bottom-up visual attention, in order to allow unsupervised one-shot learning of multiple objects in cluttered images.

Abstract translation: 本发明涉及一种用于注意选择的系统和方法。 更具体地，本发明涉及一种用于基于自下而上的视觉注意自动选择和分离可能包含对象的显着区域的系统和方法，以便允许在混乱图像中的多个对象的无监督的单次学习。

公开(公告)号：WO2004111931A3

公开(公告)日：2005-02-24

申请号：PCT/US2004018497

申请日：2004-06-10

Applicant: CALIFORNIA INST OF TECHN ,  KOCH CHRISTOF ,  PERONA PIETRO ,  RUTISHAUSER UELI ,  WALTHER DIRK

Inventor： KOCH CHRISTOF ,  PERONA PIETRO ,  RUTISHAUSER UELI ,  WALTHER DIRK

IPC: G06K9/32 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06K9/4628 ,  G06K9/3233 ,  G06K9/4671 ,  G06K9/6256

Abstract: The present invention relates to a system and method for attentional selection. More specifically, the present invention relates to a system and method for the automated selection and isolation of salient regions likely to contain objects, based on bottom-up visual attention, in order to allow unsupervised one-shot learning of multiple objects in cluttered images.

Abstract translation: 本发明涉及一种用于注意选择的系统和方法。 更具体地，本发明涉及一种用于基于自下而上的视觉注意自动选择和分离可能包含对象的显着区域的系统和方法，以便允许在混乱图像中的多个对象的无监督的单次学习。

公开(公告)号：WO2004019004A9

公开(公告)日：2004-05-27

申请号：PCT/US0326484

申请日：2003-08-21

Applicant: UNIV COLUMBIA ,  VAN GEEN ALEXANDER ,  PERONA PIETRO ,  MOSER CHRISTOPHE ,  PSALTIS DEMETRI

Inventor： VAN GEEN ALEXANDER ,  PERONA PIETRO ,  MOSER CHRISTOPHE ,  PSALTIS DEMETRI

IPC: G01J3/02 ,  G01J3/10 ,  G01J3/42 ,  G01N21/27 ,  G01N21/35 ,  G01N21/78 ,  G01N33/18 ,  G01J3/46 ,  G01N21/25

CPC classification number: G01N33/182 ,  G01J3/02 ,  G01J3/0272 ,  G01J3/0283 ,  G01J3/0286 ,  G01J3/108 ,  G01J3/42 ,  G01N21/274 ,  G01N21/276 ,  G01N21/31 ,  G01N21/3577 ,  G01N21/78 ,  G01N2021/1751

Abstract: A field test-kit for analyzing arsenic concentration in water samples incudes a portable infrared beam photometer for measuring light absorbance in aqueous specimens. An infrared ligth emittng diode (120A, 120B) is configured to direct a beam of light through a specimen. A photodetecotr diode (130A, 130B) measures the intensity of light passing through the specimen. The photodetector (130A, 130B) output voltages relate to the light absorbed in the specimen and are displayed on a LCD (160) screen. To test for arsenic, molybdenum-blue color complexes. The light absorbance of a specimen with both arsenates and phosphates bound in molybdenum-blue color complexes is compared to that of a reference specimen in which phosphates but not arsenates are bound and converted. A quantitative value for the arsenic concentration in the water sample is determined from the differential light absorbance of the two specimens.

Abstract translation: 用于分析水样中砷浓度的现场测试工具包包括用于测量水样中光吸收的便携式红外光度计。 红外线发射二极管（120A，120B）被配置为引导光束通过样本。 光探测器二极管（130A，130B）测量穿过样本的光的强度。 光电探测器（130A，130B）的输出电压与样本中吸收的光有关并显示在LCD（160）屏幕上。 测试砷，钼蓝色复合物。 将砷酸盐和磷酸盐结合在钼 - 蓝色配合物中的样品的光吸收与与其中磷酸盐而非砷酸盐结合并转化的参考样品进行比较。 水样中砷浓度的定量值由两个样品的差示吸光度确定。

公开(公告)号：WO2004019004A3

公开(公告)日：2004-03-04

申请号：PCT/US2003/026484

申请日：2003-08-21

Applicant: THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK ,  VAN GEEN, Alexander ,  PERONA, Pietro ,  MOSER, Christophe ,  PSALTIS, Demetri

Inventor： VAN GEEN, Alexander ,  PERONA, Pietro ,  MOSER, Christophe ,  PSALTIS, Demetri

IPC: G01J03/46

Abstract: A field test-kit for analyzing arsenic concentration in water samples incudes a portable infrared beam photometer for measuring light absorbance in aqueous specimens. An infrared ligth emittng diode (120A, 120B) is configured to direct a beam of light through a specimen. A photodetecotr diode (130A, 130B) measures the intensity of light passing through the specimen. The photodetector (130A, 130B) output voltages relate to the light absorbed in the specimen and are displayed on a LCD (160) screen. To test for arsenic, molybdenum-blue color complexes. The light absorbance of a specimen with both arsenates and phosphates bound in molybdenum-blue color complexes is compared to that of a reference specimen in which phosphates but not arsenates are bound and converted. A quantitative value for the arsenic concentration in the water sample is determined from the differential light absorbance of the two specimens.

公开(公告)号：WO2008156473A3

公开(公告)日：2009-02-19

申请号：PCT/US2007068647

申请日：2007-05-10

Applicant: AOL LLC ,  CALIFORNIA INST OF TECHN ,  ISIS INNOVATION ,  PERLMUTTER KEREN ,  PERLMUTTER SHARON ,  ALSPECTOR JOSH ,  EVERINGHAM MARK ,  HOLUB ALEX ,  ZISSERMAN ANDREW ,  PERONA PIETRO

Inventor： PERLMUTTER KEREN ,  PERLMUTTER SHARON ,  ALSPECTOR JOSH ,  EVERINGHAM MARK ,  HOLUB ALEX ,  ZISSERMAN ANDREW ,  PERONA PIETRO

IPC: G06K9/00

CPC classification number: G06K9/00288 ,  G06F17/30256 ,  G06K9/00281 ,  G06K9/6261 ,  G06K9/6263 ,  G11B27/105 ,  G11B27/28

Abstract: Images are searched to locate faces that are the same as a query face. Images that include a face that is the same as the query face may be presented to a user as search result images. Images also may be sorted by the faces included in the images and presented to the user as sorted search result images. The user may provide explicit or implicit feedback regarding the search result images. Additional feedback may be inferred regarding the search result images based on the user-provided feedback, and the results may be updated based on the user-provided and inferred feedback.

Abstract translation: 搜索图像以查找与查询面相同的面。 包括与查询面相同的面部的图像可以作为搜索结果图像呈现给用户。 图像也可以通过包括在图像中的面部进行排序，并且作为排序的搜索结果图像呈现给用户。 用户可以提供关于搜索结果图像的显式或隐含的反馈。 可以基于用户提供的反馈来推测关于搜索结果图像的附加反馈，并且可以基于用户提供的和推断的反馈来更新结果。

公开(公告)号：WO2005096178A1

公开(公告)日：2005-10-13

申请号：PCT/GB2005/001124

申请日：2005-03-11

Applicant: ISIS INNOVATION LIMITED ,  ZISSERMAN, Andrew ,  FERGUS, Robert ,  PERONA, Pietro

Inventor： ZISSERMAN, Andrew ,  FERGUS, Robert ,  PERONA, Pietro

IPC: G06F17/30

CPC classification number: G06F17/30259 ,  G06F17/30265 ,  G06K9/46

Abstract: A method for determining the relevance of images retrieved from a database to a specified visual object category, represented by the query keyword, the method comprising learning a model defining features of said visual object category and a spatial relationship therebetween, storing said model, comparing a set of images retrieved from said database with said stored model and calculating a likelihood value relating to each image based on its correspondence with said model.

Abstract translation: 一种用于确定从数据库检索到指定视觉对象类别的图像的相关性的方法，由查询关键字表示，所述方法包括学习定义所述视觉对象类别的特征的模型及其间的空间关系，存储所述模型，比较 基于与所述模型的对应关系，利用所述存储的模型从所述数据库检索的图像集合，并且计算与每个图像相关的似然值。

公开(公告)号：WO2008156473A2

公开(公告)日：2008-12-24

申请号：PCT/US2007/068647

申请日：2007-05-10

Applicant: AOL LLC ,  CALIFORNIA INSTITUTE OF TECHNOLOGY ,  ISIS INNOVATION LTD ,  PERLMUTTER, Keren ,  PERLMUTTER, Sharon ,  ALSPECTOR, Josh ,  EVERINGHAM, Mark ,  HOLUB, Alex ,  ZISSERMAN, Andrew ,  PERONA, Pietro

Inventor： PERLMUTTER, Keren ,  PERLMUTTER, Sharon ,  ALSPECTOR, Josh ,  EVERINGHAM, Mark ,  HOLUB, Alex ,  ZISSERMAN, Andrew ,  PERONA, Pietro

IPC: G06T7/40

CPC classification number: G06K9/00288 ,  G06F17/30256 ,  G06K9/00281 ,  G06K9/6261 ,  G06K9/6263 ,  G11B27/105 ,  G11B27/28

Abstract: Images are searched to locate faces that are the same as a query face. Images that include a face that is the same as the query face may be presented to a user as search result images. Images also may be sorted by the faces included in the images and presented to the user as sorted search result images. The user may provide explicit or implicit feedback regarding the search result images. Additional feedback may be inferred regarding the search result images based on the user-provided feedback, and the results may be updated based on the user-provided and inferred feedback.

Abstract translation: 搜索图像以查找与查询面相同的面。 包括与查询面相同的面部的图像可以作为搜索结果图像呈现给用户。 图像也可以通过包括在图像中的面部进行排序，并且作为排序的搜索结果图像呈现给用户。 用户可以提供关于搜索结果图像的显式或隐含的反馈。 可以基于用户提供的反馈来推测关于搜索结果图像的附加反馈，并且可以基于用户提供的和推断的反馈来更新结果。

公开(公告)号：WO2004019004A2

公开(公告)日：2004-03-04

申请号：PCT/US0326484

申请日：2003-08-21

Applicant: UNIV COLUMBIA ,  VAN GEEN ALEXANDER ,  PERONA PIETRO ,  MOSER CHRISTOPHE ,  PSALTIS DEMETRI

Inventor： VAN GEEN ALEXANDER ,  PERONA PIETRO ,  MOSER CHRISTOPHE ,  PSALTIS DEMETRI

IPC: G01J3/02 ,  G01J3/10 ,  G01J3/42 ,  G01N21/27 ,  G01N21/35 ,  G01N21/78 ,  G01N33/18 ,  G01N

CPC classification number: G01N33/182 ,  G01J3/02 ,  G01J3/0272 ,  G01J3/0283 ,  G01J3/0286 ,  G01J3/108 ,  G01J3/42 ,  G01N21/274 ,  G01N21/276 ,  G01N21/31 ,  G01N21/3577 ,  G01N21/78 ,  G01N2021/1751

Abstract: A field test-kit for analyzing arsenic concentration in water samples is provided. The kit includes a portable infrared beam photometer for measuring light absorbance in aqueous specimens. An infrared light emitting diode is configured to direct a beam of light through a specimen. A photodetector diode measures the intensity of light passing through the specimen. The photodetector output voltages relate to the light absorbed in the specimen and are displayed on a liquid crystal display screen. The kit is assembled using off-the-shelf electronic and opto-electronic components that have low power requirements. Dry cell batteries or solar cells power the kit. To test for arsenic, molybdenum based chemistries are used to selectively bind and convert arsenates and phosphates in the specimen into molybdenum-blue color complexes. The light absorbance of a specimen with both arsenates and phosphates bound in molybdenum-blue color complexes is compared to that of a reference specimen in which phosphates but not arsenates are bound and converted. The differential light absorbance of the two specimens is used to arrive at a quantitative value for the arsenic concentration in the water sample.

Abstract translation: 提供了一种用于分析水样中砷浓度的现场测试工具。 该套件包括便携式红外光束光度计，用于测量水样中的吸光度。 红外发光二极管被配置为引导光束通过样本。 光检测器二极管测量通过样品的光的强度。 光检测器输出电压与样品中吸收的光有关，并显示在液晶显示屏上。 该套件使用具有低功耗要求的现成的电子和光电组件进行组装。 干电池或太阳能电池为套件供电。 为了测试砷，使用钼基化学物质选择性地将样品中的砷酸盐和磷酸盐结合并转化成钼蓝色复合物。 将与钼蓝色复合体中结合的砷酸盐和磷酸盐的样品的吸光度与其中磷酸盐而不是砷酸盐结合并转化的参考样品的吸光度进行比较。 使用两个样品的差分吸光度来获得水样中砷浓度的定量值。