-
公开(公告)号：US07778462B2
公开(公告)日：2010-08-17
申请号：US12434778
申请日：2009-05-04
CPC分类号： G06F17/30256 , G06F17/3025 , G06F17/30262 , G06F17/30265 , G06K9/4652 , G06K9/4685
摘要： A technique is provided for classifying images in a library (1) for subsequent selective retrieval. Each library image is segmented (2) into a plurality of coherent regions. Each of the regions is analysed in respect of a plurality of visual properties, each of which is ascribed a number according to the value of the visual property. The property numbers are then compared (4) with bands of the available property range and a computer-readable character, such as a letter of the alphabet, is ascribed to each of the property values. The characters are then arranged (5) in a predetermined order to form a region character string. The strings for each region are then indexed (7) to form an index (8) of the images by region character string. For image retrieval, a target image (10) is analysed in the same way to form region character strings which are then supplied to a text retrieval system (12) for detecting matches with entries in the index (8). Library images having matching regions are retrieved from the library (1).
摘要翻译： 提供了用于对图书馆（1）中的图像进行分类以用于随后的选择性检索的技术。 每个库图像被分段（2）成多个相干区域。 针对多个视觉特性来分析每个区域，每个视觉属性根据视觉属性的值归入一个数字。 然后将属性编号与可用属性范围的带进行比较（4），并将计算机可读字符（例如字母表的字母）归因于每个属性值。 然后以预定顺序布置（5）字符以形成区域字符串。 然后对每个区域的字符串进行索引（7），以按区域字符串形成图像的索引（8）。 对于图像检索，以相同的方式分析目标图像（10）以形成区域字符串，然后提供给文本检索系统（12），用于检测与索引（8）中的条目的匹配。 从库（1）检索具有匹配区域的库图像。
-
公开(公告)号：US20090214124A1
公开(公告)日：2009-08-27
申请号：US12434778
申请日：2009-05-04
IPC分类号： G06K9/62
CPC分类号： G06F17/30256 , G06F17/3025 , G06F17/30262 , G06F17/30265 , G06K9/4652 , G06K9/4685
摘要： A technique is provided for classifying images in a library (1) for subsequent selective retrieval. Each library image is segmented (2) into a plurality of coherent regions. Each of the regions is analysed in respect of a plurality of visual properties, each of which is ascribed a number according to the value of the visual property. The property numbers are then compared (4) with bands of the available property range and a computer-readable character, such as a letter of the alphabet, is ascribed to each of the property values. The characters are then arranged (5) in a predetermined order to form a region character string. The strings for each region are then indexed (7) to form an index (8) of the images by region character string. For image retrieval, a target image (10) is analysed in the same way to form region character strings which are then supplied to a text retrieval system (12) for detecting matches with entries in the index (8). Library images having matching regions are retrieved from the library (1).
摘要翻译： 提供了用于对图书馆（1）中的图像进行分类以用于随后的选择性检索的技术。 每个库图像被分段（2）成多个相干区域。 针对多个视觉特性来分析每个区域，每个视觉属性根据视觉属性的值归入一个数字。 然后将属性编号与可用属性范围的带进行比较（4），并将计算机可读字符（例如字母表的字母）归因于每个属性值。 然后以预定顺序布置（5）字符以形成区域字符串。 然后对每个区域的字符串进行索引（7），以按区域字符串形成图像的索引（8）。 对于图像检索，以相同的方式分析目标图像（10）以形成区域字符串，然后提供给文本检索系统（12），用于检测与索引（8）中的条目的匹配。 从库（1）检索具有匹配区域的库图像。
-
公开(公告)号：US07545980B2
公开(公告)日：2009-06-09
申请号：US11760124
申请日：2007-06-08
CPC分类号： G06F17/30256 , G06F17/3025 , G06F17/30262 , G06F17/30265 , G06K9/4652 , G06K9/4685
摘要： A technique is provided for classifying images in a library (1) for subsequent selective retrieval. Each library image is segmented (2) into a plurality of coherent regions. Each of the regions is analysed in respect of a plurality of visual properties, each of which is ascribed a number according to the value of the visual property. The property numbers are then compared (4) with bands of the available property range and a computer-readable character, such as a letter of the alphabet, is ascribed to each of the property values. The characters are then arranged (5) in a predetermined order to form a region character string. The strings for each region are then indexed (7) to form an index (8) of the images by region character string. For image retrieval, a target image (10) is analysed in the same way to form region character strings which are then supplied to a text retrieval system (12) for detecting matches with entries in the index (8). Library images having matching regions are retrieved from the library (1).
摘要翻译： 提供了用于对图书馆（1）中的图像进行分类以用于随后的选择性检索的技术。 每个库图像被分段（2）成多个相干区域。 针对多个视觉特性来分析每个区域，每个视觉属性根据视觉属性的值归入一个数字。 然后将属性编号与可用属性范围的带进行比较（4），并将计算机可读字符（例如字母表的字母）归因于每个属性值。 然后以预定顺序布置（5）字符以形成区域字符串。 然后对每个区域的字符串进行索引（7），以按区域字符串形成图像的索引（8）。 对于图像检索，以相同的方式分析目标图像（10）以形成区域字符串，然后提供给文本检索系统（12），用于检测与索引（8）中的条目的匹配。 从库（1）检索具有匹配区域的库图像。
-
公开(公告)号：US07239746B1
公开(公告)日：2007-07-03
申请号：US10129763
申请日：2000-11-13
IPC分类号： G06K9/34
CPC分类号： G06F17/30256 , G06F17/3025 , G06F17/30262 , G06F17/30265 , G06K9/4652 , G06K9/4685
摘要： A technique is provided for classifying images in a library (1) for subsequent selective retrieval. Each library image is segmented (2) into a plurality of coherent regions. Each of the regions is analyzed in respect of a plurality of visual properties, each of which is ascribed a number according to the value of the visual property. The property numbers are then compared (4) with bands of the available property range and a computer-readable character, such as a letter of the alphabet is ascribed to each of the property values. The characters are then arranged (5) in a predetermined order to form a region character string. The strings for each region are then indexed (7) to form an index (8) of the images by region character string. For image retrieval, a target image (10) is analyzed in the same way to form region character strings which are then supplied to a text retrieval system (12) for detecting matches with entries in the index (8). Library images having matching regions are retrieved from the library (1).
摘要翻译： 提供了用于对图书馆（1）中的图像进行分类以用于随后的选择性检索的技术。 每个库图像被分段（2）成多个相干区域。 针对多个视觉特性来分析每个区域，每个视觉属性根据视觉属性的值归入一个数字。 然后将属性编号与可用属性范围的带进行比较（4），并且将计算机可读字符（例如字母表的字母归属于每个属性值）。 然后以预定顺序布置（5）字符以形成区域字符串。 然后对每个区域的字符串进行索引（7），以按区域字符串形成图像的索引（8）。 对于图像检索，以相同的方式分析目标图像（10）以形成区域字符串，然后提供给文本检索系统（12），用于检测与索引（8）中的条目的匹配。 从库（1）检索具有匹配区域的库图像。
-
公开(公告)号：US06347158B2
公开(公告)日：2002-02-12
申请号：US09729109
申请日：2000-12-05
IPC分类号： G06K936
摘要： A method for encoding digital information to be transmitted from a first device to a second device, wherein the digital information is mapped according to a map of n rows and m columns which define a plurality of cells (n×m) and wherein each of said cells has a pixel value. The method is useful for compressing bitmapped images to be rendered by the simplest of graphics engines. Thus the method is particularly suited to the transmission of images to a relatively slow client on which the images are to be rendered in real time and on which any complex decompression would be too costly for such rendering. Raw compression ratios are comparable to those obtained with standard run-length encoding, but the number of drawing primitive calls required to render the compressed images directly is substantially less.
摘要翻译： 一种用于编码要从第一设备发送到第二设备的数字信息的方法，其中根据定义多个单元（n×m）的n行m列的映射来映射数字信息，并且其中每个所述单元具有 像素值。 该方法对于压缩由最简单的图形引擎呈现的位图图像是有用的。 因此，该方法特别适合于将图像传输到要在其上实时渲染图像的相对较慢的客户端，并且任何复杂的解压缩对于这种渲染将是太昂贵的。 原始压缩比与使用标准游程长度编码获得的压缩比相当，但是直接渲染压缩图像所需的绘图原始调用数量却大大减少。
-
公开(公告)号：US08886298B2
公开(公告)日：2014-11-11
申请号：US10790602
申请日：2004-03-01
IPC分类号： A61B5/04 , H04L29/06 , G06F11/20 , H04M7/00 , H04L12/28 , G06Q20/40 , H04W24/00 , H04L29/12 , A61B5/11 , H04L29/08 , H04N7/01 , H04L12/64 , H04L5/00 , H04L12/851 , H04L12/863 , H04W52/14 , G06Q50/18 , H04W52/24 , H04J13/12 , G06Q20/42 , H04W74/02 , H04B1/04 , H04N1/00 , H04W76/02 , H04W28/14 , H04L12/801 , H04M3/22 , H04L12/54 , H04L12/815 , H04B7/06 , H04N21/647 , G06F21/62 , H04L27/26 , G08B15/00 , H04N7/14 , G06Q20/38 , H04L1/08 , H04N21/61 , H04L12/44 , G08B13/196 , G06Q20/12 , G07F17/16 , H04L12/841 , H01M16/00 , H04L12/24 , H04N7/08 , H04W52/46 , G06Q30/02 , H04L12/12 , H04L9/32 , H04B7/08 , H04M1/253 , G01S19/34 , G06Q30/06 , H04M3/42 , H04B1/40 , G06Q20/10 , H04L1/06 , H04W52/48 , H04L1/00 , H04W84/12 , H04L12/40 , G06F11/16 , H04L1/18 , H04W52/22 , H04B7/155 , H04W8/04 , H04M1/02 , H04W88/16 , H04W28/04 , H04N1/32 , H04W72/08 , H04W48/16 , H04W8/00 , H04W80/10
CPC分类号： H04N7/188 , A61B5/1117 , A61B5/1123 , A61B2562/0219 , G01S19/34 , G03B2217/005 , G06F11/1625 , G06F11/2005 , G06F11/2007 , G06F21/6218 , G06F21/6245 , G06F2221/2101 , G06F2221/2141 , G06F2221/2149 , G06Q20/10 , G06Q20/1235 , G06Q20/385 , G06Q20/401 , G06Q20/425 , G06Q30/0277 , G06Q30/0609 , G06Q50/188 , G07F17/16 , G08B13/19621 , G08B13/19628 , G08B13/19695 , G08B15/004 , H01M16/006 , H01M2250/30 , H04B1/0483 , H04B1/40 , H04B7/0604 , H04B7/084 , H04B7/0894 , H04B7/15507 , H04B7/15535 , H04J13/12 , H04L1/0041 , H04L1/0045 , H04L1/0066 , H04L1/0069 , H04L1/0071 , H04L1/06 , H04L1/08 , H04L1/1819 , H04L1/1841 , H04L1/1845 , H04L1/1848 , H04L5/0023 , H04L5/0042 , H04L5/0044 , H04L5/0083 , H04L9/32 , H04L12/12 , H04L12/2803 , H04L12/2809 , H04L12/2856 , H04L12/2874 , H04L12/40078 , H04L12/40195 , H04L12/44 , H04L12/56 , H04L12/6418 , H04L27/2602 , H04L29/06027 , H04L29/12113 , H04L41/12 , H04L47/10 , H04L47/14 , H04L47/22 , H04L47/2441 , H04L47/28 , H04L47/34 , H04L47/50 , H04L47/621 , H04L61/1541 , H04L63/0428 , H04L63/065 , H04L63/08 , H04L63/0807 , H04L63/102 , H04L63/1441 , H04L65/103 , H04L65/104 , H04L65/1043 , H04L65/80 , H04L67/12 , H04L67/14 , H04L67/16 , H04L67/306 , H04L69/16 , H04L69/168 , H04L69/324 , H04L69/326 , H04L69/329 , H04L2001/0096 , H04L2012/40241 , H04L2012/40273 , H04L2012/6462 , H04L2209/127 , H04M1/0214 , H04M1/0225 , H04M1/0235 , H04M1/2535 , H04M3/22 , H04M3/42 , H04M3/42102 , H04M7/0057 , H04M7/0069 , H04N1/00127 , H04N1/00132 , H04N1/00137 , H04N1/00148 , H04N1/00342 , H04N1/2133 , H04N1/32128 , H04N5/23248 , H04N5/772 , H04N7/0112 , H04N7/08 , H04N7/148 , H04N21/6125 , H04N21/64738 , H04N21/64784 , H04N2201/0017 , H04N2201/0084 , H04N2201/3205 , H04N2201/3226 , H04W8/005 , H04W8/04 , H04W24/00 , H04W28/14 , H04W48/16 , H04W52/143 , H04W52/225 , H04W52/24 , H04W52/241 , H04W52/242 , H04W52/245 , H04W52/46 , H04W52/48 , H04W72/08 , H04W74/02 , H04W76/10 , H04W80/10 , H04W84/12 , H04W88/16 , Y02B90/18 , Y10S707/99933 , Y10S707/99936 , Y10S707/99939
摘要： A small wearable recall device is provided to capture images triggered by a combination of a detection of a capture condition (e.g., changes in motion, temperature or light level) followed by a relatively stable period, as detected by an accelerometer. By triggering on the combination of a detected capture condition followed by a detected stability condition, a clearer image of the environment of an interesting event is expected to be captured. The small size of the recall device makes it possible to integrate it into common portable consumer products, such as MP3 players, purses, clothing, hats, backpacks, necklaces, collars, and other human-wearable products.
摘要翻译： 提供小的可穿戴回收装置以捕获由加速度计检测到的捕获条件（例如，运动变化，温度或光水平）的检测和紧跟相对稳定的周期的组合所触发的图像。 通过触发检测到的捕获条件和检测到的稳定性条件的组合，预期捕获感兴趣事件的环境的更清晰的图像。 召回设备的小尺寸使得可以将其集成到常见的便携式消费产品中，例如MP3播放器，钱包，服装，帽子，背包，项链，项圈和其他人造可穿戴产品。
-
公开(公告)号：US06389175B1
公开(公告)日：2002-05-14
申请号：US09619709
申请日：2000-07-19
IPC分类号： G06K936
摘要： A method for encoding digital information to be transmitted from a first device to a second device, wherein the digital information is mapped according to a map of n rows and m columns which define a plurality of cells (n×m) and wherein each of said cells has a pixel value. The method is useful for compressing bitmapped images to be rendered by the simplest of graphics engines. Thus the method is particularly suited to the transmission of images to a relatively slow client on which the images are to be rendered in real time and on which any complex decompression would be too costly for such rendering. Raw compression ratios are comparable to those obtained with standard runlength encoding, but the number of drawing primitive calls required to render the compressed images directly is substantially less. If the size of the largest area exceeds predetermined limits it is subdivided into smaller areas automatically without having to specify the size and position.
摘要翻译： 一种用于编码要从第一设备发送到第二设备的数字信息的方法，其中根据定义多个单元（n×m）的n行m列的映射来映射数字信息，并且其中每个所述单元具有 像素值。 该方法对于压缩由最简单的图形引擎呈现的位图图像是有用的。 因此，该方法特别适合于将图像传输到要在其上实时渲染图像的相对较慢的客户端，并且任何复杂的解压缩对于这种渲染将是太昂贵的。 原始压缩比与使用标准游程长度编码获得的压缩比相当，但是直接渲染压缩图像所需的绘制原始调用数量要小得多。 如果最大面积的尺寸超过预定限制，则会自动将其细分为更小的区域，而无需指定尺寸和位置。
-
公开(公告)号：US06192159B1
公开(公告)日：2001-02-20
申请号：US08994132
申请日：1997-12-19
IPC分类号： G06K936
摘要： A method for encoding digital information to be transmitted from a first device to a second device, wherein the digital information is mapped according to a map of n rows and m columns which define a plurality of cells (n×m) and wherein each of said cells has a pixel value. The method is useful for compressing bitmapped images to be rendered by the simplest of graphics engines, Thus the method is particularly suited to the transmission of images to a relatively slow client on which the images are to be rendered in real time and on which any complex decompression would be too costly for such rendering. Raw compression ratios are comparable to those obtained with standard run-length encoding, but the number of drawing primitive calls required to render the compressed images directly is substantially less.
摘要翻译： 一种用于编码要从第一设备发送到第二设备的数字信息的方法，其中根据定义多个单元（n×m）的n行m列的映射来映射数字信息，并且其中每个所述单元具有 像素值。 该方法对于压缩由最简单的图形引擎呈现的位图图像是有用的。因此，该方法特别适用于将图像传输到要在其上实时渲染图像的相对较慢的客户端，并且在哪个复合体 减压对于这种渲染来说太贵了。 原始压缩比与使用标准游程长度编码获得的压缩比相当，但是直接渲染压缩图像所需的绘图原始调用数量却大大减少。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.021 秒)
