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

US08275221B2 Evaluating subject interests from digital image records 有权
标题翻译：从数字图像记录评估主题兴趣
公开(公告)号：US08275221B2
公开(公告)日：2012-09-25
申请号：US13235737
申请日：2011-09-19
申请人： Robert B. Poetker , Anthony Scalise , Kevin R. DeLong , Andrew C. Blose
发明人： Robert B. Poetker , Anthony Scalise , Kevin R. DeLong , Andrew C. Blose
IPC分类号： G06K9/54
CPC分类号： G06F17/30244 , G06K2209/27 , G06Q30/0201
摘要： A method of evaluating a user subject interest is based at least upon an analysis of a user's collection of digital image records and is implemented at least in part by a data processing system. The method receives a defined user subject interest, receives a set of content requirements associated with the defined user-subject-interest, and identifies a set of digital image records from the collection of digital image records each having image characteristics in accord with the content requirements. A subject-interest trait associated with the defined user-subject-interest is evaluated based at least upon an analysis of the set of digital image records or characteristics thereof. The subject-interest trait is associated with the defined user-subject-interest in a processor-accessible memory.
摘要翻译：评估用户对象兴趣的方法至少基于用户对数字图像记录的收集的分析，并且至少部分地由数据处理系统来实现。该方法接收定义的用户主题感兴趣，接收与定义的用户主题兴趣相关联的一组内容要求，并且从数字图像记录集合中识别出数字图像记录集合，每个数字图像记录具有符合内容要求的图像特征。至少基于对该组数字图像记录或其特征的分析来评估与所定义的用户主题兴趣相关联的主题兴趣特征。主题兴趣特征与处理器可访问存储器中定义的用户主题兴趣相关联。

2. 发明申请

US20090297045A1 EVALUATING SUBJECT INTERESTS FROM DIGITAL IMAGE RECORDS 审中-公开
标题翻译：从数字图像记录评估主题
公开(公告)号：US20090297045A1
公开(公告)日：2009-12-03
申请号：US12129218
申请日：2008-05-29
申请人： Robert B. Poetker , Anthony Scalise , Kevin R. DeLong , Andrew C. Blose
发明人： Robert B. Poetker , Anthony Scalise , Kevin R. DeLong , Andrew C. Blose
IPC分类号： G06K9/62 , G06Q30/00
CPC分类号： G06Q30/0201 , G06F16/50 , G06K2209/27
摘要： A method of evaluating a user subject interest is based at least upon an analysis of a user's collection of digital image records and is implemented at least in part by a data processing system. The method receives a defined user subject interest, receives a set of content requirements associated with the defined user-subject-interest, and identifies a set of digital image records from the collection of digital image records each having image characteristics in accord with the content requirements. A subject-interest trait associated with the defined user-subject-interest is evaluated based at least upon an analysis of the set of digital image records or characteristics thereof. The subject-interest trait is associated with the defined user-subject-interest in a processor-accessible memory.
摘要翻译：评估用户对象兴趣的方法至少基于用户对数字图像记录的收集的分析，并且至少部分地由数据处理系统来实现。该方法接收定义的用户主题感兴趣，接收与定义的用户主题兴趣相关联的一组内容要求，并且从数字图像记录集合中识别出数字图像记录集合，每个数字图像记录具有符合内容要求的图像特征。至少基于对该组数字图像记录或其特征的分析来评估与所定义的用户主题兴趣相关联的主题兴趣特征。主题兴趣特征与处理器可访问存储器中定义的用户主题兴趣相关联。

3. 发明申请

US20080019574A1 Machine-controlled image cropping with default 审中-公开
标题翻译：默认情况下，机器控制的图像裁剪
公开(公告)号：US20080019574A1
公开(公告)日：2008-01-24
申请号：US11489965
申请日：2006-07-20
申请人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
发明人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
IPC分类号： G06K9/00 , G06K9/20 , G06K9/36
CPC分类号： G06K9/00228 , G06T7/11 , G06T7/194 , G06T7/90 , G06T2207/20132 , G06T2207/30201
摘要： In a machine-controlled imaging method and system, an original digital image is displayed. During the displaying, a user input is accepted designating machine-controlled cropping of the original digital image. The machine-controlled cropping of the original digital image is performed without further user intervention. In that cropping, a subject portion and a background portion of the digital image are found. A retention area of the digital image is set. The retention area is fully inclusive of the subject portion and minimally inclusive of the background portion. When the retention area is larger than a preset percentage of the original digital image, the retention area is reset to a default crop. The digital image is reduced to the retention area as set or reset, respectively.
摘要翻译：在机器控制的成像方法和系统中，显示原始数字图像。在显示期间，接受用户输入指定原始数字图像的机器控制裁剪。原始数字图像的机器控制裁剪在不进一步用户干预的情况下执行。在该裁剪中，找到数字图像的主题部分和背景部分。设置数字图像的保留区域。保留区域完全包含对象部分，并且最小化包括背景部分。当保留区域大于原始数字图像的预设百分比时，保留区域将重置为默认裁剪。分别将数字图像缩小到保留区域。

4. 发明授权

US07836093B2 Image record trend identification for user profiles 有权
标题翻译：用户配置文件的图像记录趋势识别
公开(公告)号：US07836093B2
公开(公告)日：2010-11-16
申请号：US11953908
申请日：2007-12-11
申请人： Kevin M. Gobeyn , Dale F. McIntyre , Robert B. Poetker , Kevin R. Delong , Anthony Scalise
发明人： Kevin M. Gobeyn , Dale F. McIntyre , Robert B. Poetker , Kevin R. Delong , Anthony Scalise
IPC分类号： G06F17/30
CPC分类号： H04H60/59 , G06Q30/0269 , G11B27/28 , H04H60/46 , H04H60/48 , H04N1/32112 , H04N1/32128 , H04N21/44008 , H04N21/4667 , H04N21/4826 , H04N2201/3205 , H04N2201/3214 , H04N2201/3215 , H04N2201/3252 , H04N2201/3253
摘要： Systems and methods for generating user profiles based at least upon an analysis of image content from digital image records are provided. The image content analysis is performed to identify trends that are used to identify user subject interests. The user subject interests may be incorporated into a user profile that is stored in a processor-accessible memory system.
摘要翻译：提供了至少基于从数字图像记录对图像内容的分析来生成用户简档的系统和方法。执行图像内容分析以识别用于识别用户主题兴趣的趋势。用户主体兴趣可以被并入存储在处理器可访问存储器系统中的用户简档中。

5. 发明申请

US20100215259A1 DIGITAL IMAGE CROPPING USING A BLENDED MAP 有权
标题翻译：使用混合图的数字图像编辑
公开(公告)号：US20100215259A1
公开(公告)日：2010-08-26
申请号：US12773362
申请日：2010-05-04
申请人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
发明人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
IPC分类号： G06K9/34
CPC分类号： G06K9/00234 , G06T7/11 , G06T7/194 , G06T7/90 , G06T2207/20132 , G06T2207/30201
摘要： In a method and system for mapping a digital image having a plurality of pixels, a skin color map of the digital image is computed. The skin color map has a plurality of skin color values. Each of the skin color values is associated with a respective set of one or more of the pixels. Each of the skin color values indicates a likelihood that the respective pixel set is skin. A face map of the digital image is generated. The face map is divided into one or more face zones and a background exclusive of the face zones. Each of the face zones is a group of the pixels. Each of the face zones indicates a greater likelihood than the background that the respective group of pixels is a face. In the skin color map, the respective skin color values associated with the pixels of the face zones are increased to provide a revised map, which is used in controlling a procedure producing an output.
摘要翻译：在用于映射具有多个像素的数字图像的方法和系统中，计算数字图像的肤色图。皮肤颜色图具有多个皮肤颜色值。每个皮肤颜色值与一个或多个像素的相应组相关联。每个皮肤颜色值表示各个像素组为皮肤的可能性。生成数字图像的人脸图。脸部地图被分成一个或多个脸部区域和不包括脸部区域的背景。每个脸部区域是一组像素。每个面部区域表示比相应的像素组是面部的背景更大的可能性。在皮肤颜色图中，增加与面部区域的像素相关联的各肤色值，以提供用于控制产生输出的过程的修正图。

6. 发明申请

US20090150330A1 IMAGE RECORD TREND IDENTIFICATION FOR USER PROFILES 有权
标题翻译：用于用户配置文件的图像记录趋势识别
公开(公告)号：US20090150330A1
公开(公告)日：2009-06-11
申请号：US11953908
申请日：2007-12-11
申请人： Kevin M. Gobeyn , Dale F. McIntyre , Robert B. Poetker , Kevin R. Delong , Anthony Scalise
发明人： Kevin M. Gobeyn , Dale F. McIntyre , Robert B. Poetker , Kevin R. Delong , Anthony Scalise
IPC分类号： G06F17/30
CPC分类号： H04H60/59 , G06Q30/0269 , G11B27/28 , H04H60/46 , H04H60/48 , H04N1/32112 , H04N1/32128 , H04N21/44008 , H04N21/4667 , H04N21/4826 , H04N2201/3205 , H04N2201/3214 , H04N2201/3215 , H04N2201/3252 , H04N2201/3253
摘要： Systems and methods for generating user profiles based at least upon an analysis of image content from digital image records are provided. The image content analysis is performed to identify trends that are used to identify user subject interests. The user subject interests may be incorporated into a user profile that is stored in a processor-accessible memory system.
摘要翻译：提供了至少基于从数字图像记录对图像内容的分析来生成用户简档的系统和方法。执行图像内容分析以识别用于识别用户主题兴趣的趋势。用户主体兴趣可以被并入存储在处理器可访问存储器系统中的用户简档中。

7. 发明授权

US07978918B2 Digital image cropping using a blended map 有权
标题翻译：使用混合地图进行数字图像裁剪
公开(公告)号：US07978918B2
公开(公告)日：2011-07-12
申请号：US12773362
申请日：2010-05-04
申请人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
发明人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
IPC分类号： G06K9/34 , G06K9/32 , G06K9/46
CPC分类号： G06K9/00234 , G06T7/11 , G06T7/194 , G06T7/90 , G06T2207/20132 , G06T2207/30201
摘要： An improved method for cropping a main subject from a digital image is disclosed. A skin color map and face map are independently computed and then blended to produce a revised map. A region map is computed by segmenting the digital image into a plurality of regions. A main subject importance map is calculated from the revised map and the region map. The digital image is cropped based on the main subject map.
摘要翻译：公开了一种用于从数字图像中裁剪主要对象的改进方法。独立地计算皮肤颜色图和面部图，然后混合以产生修改的图。通过将数字图像分割成多个区域来计算区域图。从修改后的地图和区域地图中计算出主要重点地图。数字图像根据主要的对象图裁剪。

8. 发明申请

US20080019575A1 Digital image cropping using a blended map 审中-公开
标题翻译：使用混合地图进行数字图像裁剪
公开(公告)号：US20080019575A1
公开(公告)日：2008-01-24
申请号：US11489966
申请日：2006-07-20
申请人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
发明人： Anthony Scalise , Robert B. Poetker , Kevin R. Delong
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/00234 , G06T7/11 , G06T7/194 , G06T7/90 , G06T2207/20132 , G06T2207/30201
摘要： In a method and system for mapping a digital image having a plurality of pixels, a skin color map of the digital image is computed. The skin color map has a plurality of skin color values. Each of the skin color values is associated with a respective set of one or more of the pixels. Each of the skin color values indicates a likelihood that the respective pixel set is skin. A face map of the digital image is generated. The face map is divided into one or more face zones and a background exclusive of the face zones. Each of the face zones is a group of the pixels. Each of the face zones indicates a greater likelihood than the background that the respective group of pixels is a face. In the skin color map, the respective skin color values associated with the pixels of the face zones are increased to provide a revised map, which is used in controlling a procedure producing an output.
摘要翻译：在用于映射具有多个像素的数字图像的方法和系统中，计算数字图像的肤色图。皮肤颜色图具有多个皮肤颜色值。每个皮肤颜色值与一个或多个像素的相应组相关联。每个皮肤颜色值表示各个像素组为皮肤的可能性。生成数字图像的人脸图。脸部地图被分成一个或多个脸部区域和不包括脸部区域的背景。每个脸部区域是一组像素。每个面部区域表示比相应的像素组是面部的背景更大的可能性。在皮肤颜色图中，增加与面部区域的像素相关联的各肤色值，以提供用于控制产生输出的过程的修正图。

9. 发明授权

US08934717B2 Automatic story creation using semantic classifiers for digital assets and associated metadata 有权
标题翻译：使用数字资产和相关元数据的语义分类器自动创建故事
公开(公告)号：US08934717B2
公开(公告)日：2015-01-13
申请号：US11935737
申请日：2007-11-06
申请人： Catherine D. Newell , Mark D. Wood , Kathleen M. Costello , Robert B. Poetker
发明人： Catherine D. Newell , Mark D. Wood , Kathleen M. Costello , Robert B. Poetker
IPC分类号： G06K9/00 , G11B27/034 , G06F17/30 , G11B27/32
CPC分类号： G11B27/034 , G06F17/30029 , G06F17/30038 , G06F17/30056 , G11B27/322
摘要： A method and system for automatically creating an image product based on media assets stored in a database. A number of stored digital media files are analyzed to determine their semantic relationship to an event and are classified according to requirements and semantic rules for generating an image product. Rule sets are applied to assets for finding one or more assets that can be include in a story product. The assets, which best meet the requirements and rules of the image product are included.
摘要翻译：一种基于存储在数据库中的媒体资产自动创建图像产品的方法和系统。分析多个存储的数字媒体文件以确定其与事件的语义关系，并根据要求和用于生成图像产品的语义规则进行分类。规则集适用于资产，用于查找可包含在故事产品中的一个或多个资产。包括最符合图像产品要求和规则的资产。

10. 发明申请

US20080304808A1 AUTOMATIC STORY CREATION USING SEMANTIC CLASSIFIERS FOR DIGITAL ASSETS AND ASSOCIATED METADATA 有权
标题翻译：使用数字资产和相关元数据的语义分类器进行自动创建
公开(公告)号：US20080304808A1
公开(公告)日：2008-12-11
申请号：US11935737
申请日：2007-11-06
申请人： Catherine D. Newell , Mark D. Wood , Kathleen M. Costello , Robert B. Poetker
发明人： Catherine D. Newell , Mark D. Wood , Kathleen M. Costello , Robert B. Poetker
IPC分类号： H04N5/93
CPC分类号： G11B27/034 , G06F17/30029 , G06F17/30038 , G06F17/30056 , G11B27/322
摘要： A method and system for automatically creating an image product based on media assets stored in a database. A number of stored digital media files are analyzed to determine their semantic relationship to an event and are classified according to requirements and semantic rules for generating an image product. Rule sets are applied to assets for finding one or more assets that can be include in a story product. The assets, which best meet the requirements and rules of the image product are included.
摘要翻译：一种基于存储在数据库中的媒体资产自动创建图像产品的方法和系统。分析多个存储的数字媒体文件以确定其与事件的语义关系，并根据要求和用于生成图像产品的语义规则进行分类。规则集适用于资产，用于查找可包含在故事产品中的一个或多个资产。包括最符合图像产品要求和规则的资产。

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