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

US07499916B2 Image retrieval systems and methods with semantic and feature based relevance feedback 有权
公开(公告)号：US07499916B2
公开(公告)日：2009-03-03
申请号：US10969308
申请日：2004-10-20
申请人： Wen-Yin Liu , Hong-Jiang Zhang , Ye Lu
发明人： Wen-Yin Liu , Hong-Jiang Zhang , Ye Lu
IPC分类号： G06F17/30 , G06F7/00
CPC分类号： G06F17/30265 , G06F17/30256 , G06F19/00 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935
摘要： An image retrieval system performs both keyword-based and content-based image retrieval. A user interface allows a user to specify queries using a combination of keywords and examples images. Depending on the input query, the image retrieval system finds images with keywords that match the keywords in the query and/or images with similar low-level features, such as color, texture, and shape. The system ranks the images and returns them to the user. The user interface allows the user to identify images that are more relevant to the query, as well as images that are less or not relevant to the query. The user may alternatively elect to refine the search by selecting one example image from the result set and submitting its low-level features in a new query. The image retrieval system monitors the user feedback and uses it to refine any search efforts and to train itself for future search queries. In the described implementation, the image retrieval system seamlessly integrates feature-based relevance feedback and semantic-based relevance feedback.

2. 发明授权

US07231381B2 Media content search engine incorporating text content and user log mining 失效
标题翻译：包含文本内容和用户日志挖掘的媒体内容搜索引擎
公开(公告)号：US07231381B2
公开(公告)日：2007-06-12
申请号：US09805626
申请日：2001-03-13
申请人： Mingjing Li , Hong-Jiang Zhang , Wen-Yin Liu , Zhen Chen
发明人： Mingjing Li , Hong-Jiang Zhang , Wen-Yin Liu , Zhen Chen
IPC分类号： G06F17/30
CPC分类号： G06F17/30017 , Y10S707/913 , Y10S707/915 , Y10S707/99933 , Y10S707/99935 , Y10S707/99936
摘要： Text features corresponding to pieces of media content (e.g., images, audio, multimedia content, etc.) are extracted from media content sources. One or more text features (e.g., one or more words) for a piece of media content are extracted from text associated with the piece of media content and text feature vectors generated therefrom and used during subsequent searching. Additional low-level feature vectors may also be extracted from the piece of media content and used during the subsequent searching. Relevance feedback can also be received from a user(s) identifying the relevance of pieces of media content rendered to the user in response to his or her search request. The relevance feedback is logged and can be used in determining how to respond to subsequent search requests, such as by modifying feature vectors (e.g., text feature vectors) corresponding to the pieces of media content for which relevance feedback is received.
摘要翻译：从媒体内容源提取对应于媒体内容（例如，图像，音频，多媒体内容等）的文本特征。从与其相关联的文本内容和从其生成的文本特征向量的文本中提取用于一段媒体内容的一个或多个文本特征（例如，一个或多个单词），并在随后的搜索期间使用。还可以从媒体内容中提取附加的低级特征向量，并在随后的搜索期间使用。还可以从用户识别响应于他或她的搜索请求而呈现给用户的媒体内容的相关性的用户接收到相关性反馈。记录相关性反馈，并且可以用于确定如何响应随后的搜索请求，例如通过修改对应于接收到相关性反馈的多条媒体内容的特征向量（例如，文本特征向量）。

3. 发明申请

US20050114325A1 Semi-automatic annotation of multimedia objects 有权
标题翻译：多媒体对象的半自动注释
公开(公告)号：US20050114325A1
公开(公告)日：2005-05-26
申请号：US10969326
申请日：2004-10-20
申请人： Wen-Yin Liu , Hong-Jiang Zhang
发明人： Wen-Yin Liu , Hong-Jiang Zhang
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30265 , G06F17/30247 , Y10S707/99933 , Y10S707/99934
摘要： A multimedia object retrieval and annotation system integrates an annotation process with object retrieval and relevance feedback processes. The annotation process annotates multimedia objects, such as digital images, with semantically relevant keywords. The annotation process is performed in background, hidden from the user, as the user conducts normal searches. The annotation process is “semi-automatic” in that it utilizes both keyword-based information retrieval and content-based image retrieval techniques to automatically search for multimedia objects, and then encourages users to provide feedback on the retrieved objects. The user identifies objects as either relevant or irrelevant to the query keywords and based on this feedback, the system automatically annotates the objects with semantically relevant keywords and/or updates associations between the keywords and objects. As the retrieval-feedback-annotation cycle is repeated, the annotation coverage and accuracy of future searches continues to improve.
摘要翻译：多媒体对象检索和注释系统将注释过程与对象检索和相关性反馈过程相结合。注释过程用语义相关的关键字注释多媒体对象，如数字图像。注释过程在用户进行正常搜索时在后台执行，隐藏在用户身上。注释过程是“半自动的”，它利用基于关键词的信息检索和基于内容的图像检索技术来自动搜索多媒体对象，然后鼓励用户对检索到的对象提供反馈。用户将对象识别为与查询关键字相关或不相关的对象，并且基于该反馈，系统使用语义相关的关键字自动注释对象并且/或更新关键字和对象之间的关联。随着检索反馈注释周期的重复，未来搜索的注释覆盖率和准确性将继续提高。

4. 发明授权

US07349895B2 Semi-automatic annotation of multimedia objects 有权
标题翻译：多媒体对象的半自动注释
公开(公告)号：US07349895B2
公开(公告)日：2008-03-25
申请号：US10969326
申请日：2004-10-20
申请人： Wen-Yin Liu , Hong-Jiang Zhang
发明人： Wen-Yin Liu , Hong-Jiang Zhang
IPC分类号： G06F17/30
CPC分类号： G06F17/30265 , G06F17/30247 , Y10S707/99933 , Y10S707/99934
摘要： A multimedia object retrieval and annotation system integrates an annotation process with object retrieval and relevance feedback processes. The annotation process annotates multimedia objects, such as digital images, with semantically relevant keywords. The annotation process is performed in background, hidden from the user, as the user conducts normal searches. The annotation process is “semi-automatic” in that it utilizes both keyword-based information retrieval and content-based image retrieval techniques to automatically search for multimedia objects, and then encourages users to provide feedback on the retrieved objects. The user identifies objects as either relevant or irrelevant to the query keywords and based on this feedback, the system automatically annotates the objects with semantically relevant keywords and/or updates associations between the keywords and objects. As the retrieval-feedback-annotation cycle is repeated, the annotation coverage and accuracy of future searches continues to improve.
摘要翻译：多媒体对象检索和注释系统将注释过程与对象检索和相关性反馈过程相结合。注释过程用语义相关的关键字注释多媒体对象，如数字图像。注释过程在用户进行正常搜索时在后台执行，隐藏在用户身上。注释过程是“半自动的”，它利用基于关键词的信息检索和基于内容的图像检索技术来自动搜索多媒体对象，然后鼓励用户对检索到的对象提供反馈。用户将对象识别为与查询关键字相关或不相关的对象，并且基于该反馈，系统使用语义相关的关键字自动注释对象并且/或更新关键字和对象之间的关联。随着检索反馈注释周期的重复，未来搜索的注释覆盖率和准确性将继续改善。

5. 发明授权

US06674918B1 Image synthesis by illuminating a virtual deviation-mapped surface 有权
标题翻译：通过照亮虚拟偏差映射表面的图像合成
公开(公告)号：US06674918B1
公开(公告)日：2004-01-06
申请号：US09505227
申请日：2000-02-16
申请人： Wen-Yin Liu , Hua Zhong , Ying-Qing Xu
发明人： Wen-Yin Liu , Hua Zhong , Ying-Qing Xu
IPC分类号： G06K936
CPC分类号： G06T5/50 , G06T15/503 , G06T15/506
摘要： Methods and apparatus for synthesizing images from two or more existing images are described. The described embodiment makes use of an illumination model as a mathematical model to combine the images. A first of the images is utilized as an object color or color source (i.e. the foreground) for a resultant image that is to be formed. A second of the images (utilized as the background or texture) is utilized as a perturbation source. In accordance with the described embodiment, the first image is represented by a plane that has a plurality of surface normal vectors. Aspects of the second image are utilized to perturb or adjust the surface normal vectors of the plane that represents the first image. Perturbation occurs, in the described embodiment, by determining individual intensity values for corresponding pixels of the second image. The intensity values are mapped to corresponding angular displacement values. The angular displacement values are used to angularly adjust or deviate the surface normal vectors for corresponding image pixels of the plane that represents the first image. This yields a virtual surface whose normal vectors are not fully specified, but constrained only by the angles between the original surface normal vectors and the perturbed normal vectors. In the described embodiment, after some assumptions concerning the viewing and lighting source direction, an illumination model is then applied to the virtual surface to yield a resultant synthesized image.
摘要翻译：描述了用于从两个或多个现有图像合成图像的方法和装置。所描述的实施例利用照明模型作为数学模型来组合图像。第一个图像被用作要形成的合成图像的对象颜色或颜色源（即前景）。用作第二个图像（用作背景或纹理）被用作扰动源。根据所描述的实施例，第一图像由具有多个表面法线向量的平面表示。利用第二图像的方面来扰乱或调整表示第一图像的平面的表面法线向量。在所描述的实施例中，通过确定第二图像的相应像素的单独强度值，发生扰动。强度值映射到相应的角位移值。角位移值用于角度地调整或偏离表示第一图像的平面的相应图像像素的表面法向矢量。这产生了一个虚拟表面，其法向矢量未被完全指定，但仅受原始表面法向量和扰动法向矢量之间的角度约束。在所描述的实施例中，在关于观察和照明光源方向的一些假设之后，然后将照明模型应用于虚拟表面以产生合成的合成图像。

6. 发明授权

US07627556B2 Semi-automatic annotation of multimedia objects 失效
标题翻译：多媒体对象的半自动注释
公开(公告)号：US07627556B2
公开(公告)日：2009-12-01
申请号：US10900951
申请日：2004-07-28
申请人： Wen-Yin Liu , Hong-Jiang Zhang
发明人： Wen-Yin Liu , Hong-Jiang Zhang
IPC分类号： G06F17/30
CPC分类号： G06F17/30265 , G06F17/30247 , Y10S707/99933 , Y10S707/99934
摘要： A multimedia object retrieval and annotation system integrates an annotation process with object retrieval and relevance feedback processes. The annotation process annotates multimedia objects, such as digital images, with semantically relevant keywords. The annotation process is performed in background, hidden from the user, as the user conducts normal searches. The annotation process is “semi-automatic” in that it utilizes both keyword-based information retrieval and content-based image retrieval techniques to automatically search for multimedia objects, and then encourages users to provide feedback on the retrieved objects. The user identifies objects as either relevant or irrelevant to the query keywords and based on this feedback, the system automatically annotates the objects with semantically relevant keywords and/or updates associations between the keywords and objects. As the retrieval-feedback-annotation cycle is repeated, the annotation coverage and accuracy of future searches continues to improve.
摘要翻译：多媒体对象检索和注释系统将注释过程与对象检索和相关性反馈过程相结合。注释过程用语义相关的关键字注释多媒体对象，如数字图像。注释过程在用户进行正常搜索时在后台执行，隐藏在用户身上。注释过程是“半自动的”，它利用基于关键词的信息检索和基于内容的图像检索技术来自动搜索多媒体对象，然后鼓励用户对检索到的对象提供反馈。用户将对象识别为与查询关键字相关或不相关的对象，并且基于该反馈，系统使用语义相关的关键字自动注释对象并且/或更新关键字和对象之间的关联。随着检索反馈注释周期的重复，未来搜索的注释覆盖率和准确性将继续改善。

7. 发明授权

US07493312B2 Media agent 有权
标题翻译：媒体代理
公开(公告)号：US07493312B2
公开(公告)日：2009-02-17
申请号：US10853375
申请日：2004-05-24
申请人： Wen-Yin Liu , Hong-Jiang Zhang , Zheng Chen
发明人： Wen-Yin Liu , Hong-Jiang Zhang , Zheng Chen
IPC分类号： G06F17/30
CPC分类号： G06F17/30017 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935 , Y10S707/99936 , Y10S707/99937 , Y10S707/99943
摘要： Systems and methods for a media agent are described. In one aspect, user access of a media content source is detected. Responsive to this detection, a piece of media content and associated text is collected from the media content source. Semantic text features are extracted from the associated text and the piece of media content. The semantic text features are indexed into a media database.
摘要翻译：描述介质代理的系统和方法。在一个方面，检测到媒体内容源的用户访问。响应于这种检测，从媒体内容源收集一段媒体内容和相关文本。从相关文本和媒体内容中提取语义文本特征。语义文本特征被索引到媒体数据库中。

8. 发明授权

US06970860B1 Semi-automatic annotation of multimedia objects 失效
公开(公告)号：US06970860B1
公开(公告)日：2005-11-29
申请号：US09702288
申请日：2000-10-30
申请人： Wen-Yin Liu , Hong-Jiang Zhang
发明人： Wen-Yin Liu , Hong-Jiang Zhang
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30265 , G06F17/30247 , Y10S707/99933 , Y10S707/99934
摘要： A multimedia object retrieval and annotation system integrates an annotation process with object retrieval and relevance feedback processes. The annotation process annotates multimedia objects, such as digital images, with semantically relevant keywords. The annotation process is performed in background, hidden from the user, as the user conducts normal searches. The annotation process is “semi-automatic” in that it utilizes both keyword-based information retrieval and content-based image retrieval techniques to automatically search for multimedia objects, and then encourages users to provide feedback on the retrieved objects. The user identifies objects as either relevant or irrelevant to the query keywords and based on this feedback, the system automatically annotates the objects with semantically relevant keywords and/or updates associations between the keywords and objects. As the retrieval-feedback-annotation cycle is repeated, the annotation coverage and accuracy of future searches continues to improve.

9. 发明申请

US20050055344A1 Image retrieval systems and methods with semantic and feature based relevance feedback 有权
标题翻译：图像检索系统和方法具有基于语义和特征的相关性反馈
公开(公告)号：US20050055344A1
公开(公告)日：2005-03-10
申请号：US10969308
申请日：2004-10-20
申请人： Wen-Yin Liu , Hong-Jiang Zhang , Ye Lu
发明人： Wen-Yin Liu , Hong-Jiang Zhang , Ye Lu
IPC分类号： G06T1/00 , G06F17/30
CPC分类号： G06F17/30265 , G06F17/30256 , G06F19/00 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935
摘要： An image retrieval system performs both keyword-based and content-based image retrieval. A user interface allows a user to specify queries using a combination of keywords and examples images. Depending on the input query, the image retrieval system finds images with keywords that match the keywords in the query and/or images with similar low-level features, such as color, texture, and shape. The system ranks the images and returns them to the user. The user interface allows the user to identify images that are more relevant to the query, as well as images that are less or not relevant to the query. The user may alternatively elect to refine the search by selecting one example image from the result set and submitting its low-level features in a new query. The image retrieval system monitors the user feedback and uses it to refine any search efforts and to train itself for future search queries. In the described implementation, the image retrieval system seamlessly integrates feature-based relevance feedback and semantic-based relevance feedback.
摘要翻译：图像检索系统执行基于关键词和基于内容的图像检索。用户界面允许用户使用关键字和示例图像的组合来指定查询。根据输入查询，图像检索系统查找与查询中的关键字匹配的关键字和/或具有类似低级特征（如颜色，纹理和形状）的图像。系统对图像进行排序并将其返回给用户。用户界面允许用户识别与查询更相关的图像，以及与查询较少或不相关的图像。用户可以选择通过从结果集中选择一个示例图像并在新查询中提交其低级特征来优化搜索。图像检索系统监视用户反馈，并使用它来优化任何搜索工作，并训练自己以用于将来的搜索查询。在所描述的实现中，图像检索系统将基于特征的相关性反馈和基于语义的相关性反馈无缝集成。

10. 发明授权

US07099860B1 Image retrieval systems and methods with semantic and feature based relevance feedback 有权
公开(公告)号：US07099860B1
公开(公告)日：2006-08-29
申请号：US09702292
申请日：2000-10-30
申请人： Wen-Yin Liu , Hong-Jiang Zhang , Ye Lu
发明人： Wen-Yin Liu , Hong-Jiang Zhang , Ye Lu
IPC分类号： G06F17/30
CPC分类号： G06F17/30265 , G06F17/30256 , G06F19/00 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935
摘要： An image retrieval system performs both keyword-based and content-based image retrieval. A user interface allows a user to specify queries using a combination of keywords and examples images. Depending on the input query, the image retrieval system finds images with keywords that match the keywords in the query and/or images with similar low-level features, such as color, texture, and shape. The system ranks the images and returns them to the user. The user interface allows the user to identify images that are more relevant to the query, as well as images that are less or not relevant to the query. The user may alternatively elect to refine the search by selecting one example image from the result set and submitting its low-level features in a new query. The image retrieval system monitors the user feedback and uses it to refine any search efforts and to train itself for future search queries. In the described implementation, the image retrieval system seamlessly integrates feature-based relevance feedback and semantic-based relevance feedback.

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