公开(公告)号：US07936906B2

公开(公告)日：2011-05-03

申请号：US11763909

申请日：2007-06-15

申请人： Gang Hua ,  Paul A Viola ,  Steven M. Drucker ,  Michael Revow

发明人： Gang Hua ,  Paul A Viola ,  Steven M. Drucker ,  Michael Revow

IPC分类号： G06K9/00

CPC分类号： G06K9/00288 ,  G06K9/6232

摘要： Systems and methods are described for face recognition using discriminatively trained orthogonal rank one tensor projections. In an exemplary system, images are treated as tensors, rather than as conventional vectors of pixels. During runtime, the system designs visual features—embodied as tensor projections—that minimize intraclass differences between instances of the same face while maximizing interclass differences between the face and faces of different people. Tensor projections are pursued sequentially over a training set of images and take the form of a rank one tensor, i.e., the outer product of a set of vectors. An exemplary technique ensures that the tensor projections are orthogonal to one another, thereby increasing ability to generalize and discriminate image features over conventional techniques. Orthogonality among tensor projections is maintained by iteratively solving an ortho-constrained eigenvalue problem in one dimension of a tensor while solving unconstrained eigenvalue problems in additional dimensions of the tensor.

摘要翻译： 使用区分训练的正交秩一张量投影描述用于人脸识别的系统和方法。 在示例性系统中，图像被视为张量，而不是像传统的像素矢量。 在运行期间，系统设计视觉特征 - 体现为张量投影 - 最大限度地减少不同人脸部和脸部之间的类间差异，从而最大限度地减少同一脸部实例之间的差异。 张量投影在训练图像集上顺序追溯，并采取一级张量的形式，即一组向量的外积。 示例性技术确保张量投影彼此正交，从而增加了与常规技术相比的概括和区分图像特征的能力。 通过迭代求解张量的一维中的邻域约束特征值问题，同时解决张量的附加维度中的无约束特征值问题，维持张量投影中的正交性。

公开(公告)号：US20080226174A1

公开(公告)日：2008-09-18

申请号：US11725129

申请日：2007-03-15

申请人： Gang Hua ,  Steven M. Drucker ,  Michael Revow ,  Paul A. Viola ,  Richard Zemel

发明人： Gang Hua ,  Steven M. Drucker ,  Michael Revow ,  Paul A. Viola ,  Richard Zemel

IPC分类号： G06K9/68 ,  G06K9/46

CPC分类号： G06K9/00228 ,  G06K9/6251

摘要： A system for organizing images includes an extraction component that extracts visual information (e.g., faces, scenes, etc.) from the images. The extracted visual information is provided to a comparison component which computes similarity confidence data between the extracted visual information. The similarity confidence data is an indication of the likelihood that items of extracted visual information are similar. The comparison component then generates a visual distribution of the extracted visual information based upon the similarity confidence data. The visual distribution can include groupings of the extracted visual information based on computed similarity confidence data. For example, the visual distribution can be a two-dimensional layout of faces organized based on the computed similarity confidence data—with faces in closer proximity faces computed to have a greater probability of representing the same person. The visual distribution can then be utilized by a user to sort, organize and/or tag images.

摘要翻译： 用于组织图像的系统包括从图像中提取视觉信息（例如，面部，场景等）的提取组件。 提取的视觉信息被提供给计算提取的视觉信息之间的相似性置信度数据的比较部件。 相似性置信度数据是提取的视觉信息的项目相似的可能性的指示。 然后，比较组件基于相似性置信度数据生成所提取的视觉信息的视觉分布。 视觉分布可以包括基于计算的相似性置信度数据提取的视觉信息的分组。 例如，视觉分布可以是基于所计算的相似性置信度数据组织的面部的二维布局，其中更接近的面中的面被计算为具有更大的代表同一人的概率。 然后用户可以利用视觉分布来对图像进行分类，组织和/或标记。

公开(公告)号：US08027541B2

公开(公告)日：2011-09-27

申请号：US11725129

申请日：2007-03-15

申请人： Gang Hua ,  Steven M. Drucker ,  Michael Revow ,  Paul A. Viola ,  Richard Zemel

发明人： Gang Hua ,  Steven M. Drucker ,  Michael Revow ,  Paul A. Viola ,  Richard Zemel

IPC分类号： G06K9/46

CPC分类号： G06K9/00228 ,  G06K9/6251

摘要： A system for organizing images includes an extraction component that extracts visual information (e.g., faces, scenes, etc.) from the images. The extracted visual information is provided to a comparison component which computes similarity confidence data between the extracted visual information. The similarity confidence data is an indication of the likelihood that items of extracted visual information are similar. The comparison component then generates a visual distribution of the extracted visual information based upon the similarity confidence data. The visual distribution can include groupings of the extracted visual information based on computed similarity confidence data. For example, the visual distribution can be a two-dimensional layout of faces organized based on the computed similarity confidence data—with faces in closer proximity faces computed to have a greater probability of representing the same person. The visual distribution can then be utilized by a user to sort, organize and/or tag images.

摘要翻译： 用于组织图像的系统包括从图像中提取视觉信息（例如，面部，场景等）的提取组件。 提取的视觉信息被提供给计算提取的视觉信息之间的相似性置信度数据的比较部件。 相似性置信度数据是提取的视觉信息的项目相似的可能性的指示。 然后，比较组件基于相似性置信度数据生成所提取的视觉信息的视觉分布。 视觉分布可以包括基于计算的相似性置信度数据提取的视觉信息的分组。 例如，视觉分布可以是基于所计算的相似性置信度数据组织的面部的二维布局，其中更接近的面中的面被计算为具有更大的代表同一人的概率。 然后用户可以利用视觉分布来对图像进行分类，组织和/或标记。

公开(公告)号：US20080310687A1

公开(公告)日：2008-12-18

申请号：US11763909

申请日：2007-06-15

申请人： Gang Hua ,  Paul A. Viola ,  Steven M. Drucker ,  Michael Revow

发明人： Gang Hua ,  Paul A. Viola ,  Steven M. Drucker ,  Michael Revow

IPC分类号： G06K9/00

CPC分类号： G06K9/00288 ,  G06K9/6232

摘要： Systems and methods are described for face recognition using discriminatively trained orthogonal rank one tensor projections. In an exemplary system, images are treated as tensors, rather than as conventional vectors of pixels. During runtime, the system designs visual features—embodied as tensor projections—that minimize intraclass differences between instances of the same face while maximizing interclass differences between the face and faces of different people. Tensor projections are pursued sequentially over a training set of images and take the form of a rank one tensor, i.e., the outer product of a set of vectors. An exemplary technique ensures that the tensor projections are orthogonal to one another, thereby increasing ability to generalize and discriminate image features over conventional techniques. Orthogonality among tensor projections is maintained by iteratively solving an ortho-constrained eigenvalue problem in one dimension of a tensor while solving unconstrained eigenvalue problems in additional dimensions of the tensor.

摘要翻译： 使用区分训练的正交秩一张量投影描述用于人脸识别的系统和方法。 在示例性系统中，图像被视为张量，而不是像传统的像素矢量。 在运行期间，系统设计视觉特征 - 体现为张量投影 - 最大限度地减少不同人脸部和脸部之间的类间差异，从而最大限度地减少同一脸部实例之间的差异。 张量投影在训练图像集上顺序追溯，并采取一级张量的形式，即一组向量的外积。 示例性技术确保张量投影彼此正交，从而增加了与常规技术相比的概括和区分图像特征的能力。 通过迭代求解张量的一维中的邻域约束特征值问题，同时解决张量的附加维度中的无约束特征值问题，维持张量投影中的正交性。

公开(公告)号：US07813920B2

公开(公告)日：2010-10-12

申请号：US11771018

申请日：2007-06-29

申请人： Brian Leung ,  Michael Revow

发明人： Brian Leung ,  Michael Revow

IPC分类号： G06F17/21

CPC分类号： G06K9/222 ,  G06K9/6255

摘要： Learning to reorder alternates based on a user's personalized vocabulary may be provided. An alternate list provided to a user for replacing words input by the user via a character recognition application may be reordered based on data previously viewed or input by the user (personal data). The alternate list may contain generic data, for example, words for possible substitution with one or more words input by the user. By using the user's personal data and statistical learning methodologies in conjunction with generic data in the alternate list, the alternate list can be reordered to present a top alternate that more closely reflect the user's vocabulary. Accordingly, the user is presented with a top alternate that is more likely to be used by the user to replace data incorrectly input.

摘要翻译： 可以提供基于用户的个性化词汇来学习重新排序交替。 提供给用户的用于替换由用户经由字符识别应用输入的字的替代列表可以基于用户先前查看或输入的数据（个人数据）重新排序。 备用列表可以包含通用数据，例如，用于用户输入的一个或多个单词的可能替换的单词。 通过将用户的个人数据和统计学习方法与备用列表中的通用数据结合使用，备用列表可以重新排序，以呈现更加反映用户词汇表的顶级替代。 因此，向用户呈现更可能被用户用来替换不正确输入的数据的顶替代。

公开(公告)号：US20050089227A1

公开(公告)日：2005-04-28

申请号：US10693259

申请日：2003-10-24

申请人： Patrick Haluptzok ,  Ross Luengen ,  Benoit Jurion ,  Michael Revow ,  Richard Sailor

发明人： Patrick Haluptzok ,  Ross Luengen ,  Benoit Jurion ,  Michael Revow ,  Richard Sailor

IPC分类号： G06F20060101 ,  G06K9/18 ,  G06K9/22 ,  G06K9/62

CPC分类号： G06K9/222 ,  G06K9/6256

摘要： An improved system and method for personalizing recognition of an input method is provided. A trainable handwriting recognizer may be personalized by using ink written by the user and text authored by the user. The system includes a personalization service engine and a framework with interfaces for collecting, storing, and accessing user ink and authored information for training recognizers. The trainers of the system may include a text trainer for augmenting a recognizer's dictionary using text content and a shape trainer for tuning generic recognizer components using ink data supplied by a user. The trainers may load multiple trainer clients, each capable of training one or more specific recognizers. Furthermore, a framework is provided for supporting pluggable trainers. Any trainable recognizer may be dynamically personalized using the harvested information authored by the user and ink written by the user.

摘要翻译： 提供了一种用于个性化输入方法的识别的改进的系统和方法。 可以通过使用用户书写的墨水和使用者编写的文字来个性化可训练的手写识别器。 该系统包括个性化服务引擎和具有用于收集，存储和访问用户墨水和用于训练识别器的创作信息的界面的框架。 系统的训练者可以包括用于使用文本内容增强识别器字典的文本训练器，以及使用由用户提供的墨水数据来调整通用识别器组件的形状训练器。 培训师可以加载多个培训师客户，每个客户能够训练一个或多个特定识别器。 此外，还提供了一个用于支持可插拔教练的框架。 任何可训练的识别器可以使用用户编写的收获信息和由用户书写的墨水来动态地个性化。

公开(公告)号：US07702145B2

公开(公告)日：2010-04-20

申请号：US11477332

申请日：2006-06-28

申请人： Michael Revow ,  Manish Goval

发明人： Michael Revow ,  Manish Goval

IPC分类号： G06K9/62

CPC分类号： G06K9/6255 ,  G06K9/00422

摘要： Various technologies and techniques are disclosed for improving handwriting recognition using a neural network by allowing a user to provide samples. A recognition operation is performed on the user's handwritten input, and the user is not satisfied with the recognition result. The user selects an option to train the neural network on one or more characters to improve the recognition results. The user is prompted to specify samples for the certain character, word, or phrase, and the neural network is adjusted for the certain character, word, or phrase. Handwritten input is later received from the user. A recognition operation is performed on the handwritten input using the neural network that was adjusted for the certain character or characters.

摘要翻译： 公开了各种技术和技术，用于通过允许用户提供样本来改进使用神经网络的手写识别。 对用户的手写输入执行识别操作，并且用户对识别结果不满意。 用户选择一个或多个字符来训练神经网络以提高识别结果的选项。 提示用户为特定字符，单词或短语指定样本，并为特定字符，单词或短语调整神经网络。 手写输入稍后从用户接收。 使用针对特定字符或字符调整的神经网络对手写输入执行识别操作。

公开(公告)号：US07881534B2

公开(公告)日：2011-02-01

申请号：US11455874

申请日：2006-06-19

申请人： Brian Leung ,  Michael Revow ,  Richard K. Sailor

发明人： Brian Leung ,  Michael Revow ,  Richard K. Sailor

IPC分类号： G06K9/18 ,  G06K9/00 ,  G06K9/72 ,  G10L15/00

CPC分类号： G06K9/00436

摘要： Various technologies and techniques are disclosed for using user corrections to help improve handwriting recognition operations. The system tracks user corrections to recognition results. The system receives handwritten input from the user and performs a recognition operation to determine a top recognized word. The prior corrections made by the user are analyzed to calculate a ratio of times the user has corrected the top recognized word to a particular other word as opposed to correcting the particular other word to the top recognized word. If the ratio meets or exceeds a required minimum, then at least one secondary source is optionally analyzed to determine if the particular other word is used a certain number of times more frequently than the top recognized word in the secondary source. The system performs a swap of the top recognized word with the particular other word when the required criteria are met.

摘要翻译： 公开了各种技术和技术来使用用户校正来帮助改进手写识别操作。 系统跟踪用户对识别结果的更正。 该系统从用户接收手写输入并执行识别操作以确定顶部识别的字。 对用户进行的先前校正进行分析，以计算用户将顶部识别的单词修正为特定其他单词的次数的比例，而不是将特定的其他单词校正为顶部识别的单词。 如果该比率满足或超过所需的最小值，则可选地分析至少一个次级源以确定该特定的其他单词是否比次要源中的顶部识别的单词频繁使用一定次数。 当满足所需的标准时，系统将使用特定的其他单词执行顶部识别的字的交换。

公开(公告)号：US07734094B2

公开(公告)日：2010-06-08

申请号：US11478500

申请日：2006-06-28

申请人： Michael Revow

发明人： Michael Revow

IPC分类号： G06K9/00 ,  G06K9/18 ,  G06F17/21

CPC分类号： G06K9/00422 ,  G06K9/03 ,  G06K9/222

摘要： Various technologies and techniques are disclosed that identify possible incorrect recognition results. Handwritten input is received from a user. A recognition operation is performed on the handwritten input to produce an initial recognition result. A possible incorrect recognition is identified using the self-consistency process that identifies the possible incorrect recognition when the initial recognition result is not consistent with a normal writing style of the user. The self-consistency process performs a comparison of the initial recognition result with at least one sample previously provided by the user. If the comparison reveals that the initial recognition result is not consistent with the at least one sample, then the result is identified as possibly incorrect. A classifier confidence process can be alternatively or additionally used to identify a possible incorrect recognition result. The user interface for displaying the final result can be modified as appropriate given the possible incorrect recognition result.

摘要翻译： 公开了识别可能的错误识别结果的各种技术和技术。 从用户接收到手写输入。 对手写输入执行识别操作以产生初始识别结果。 当初始识别结果与用户的正常书写风格不一致时，使用识别可能的不正确识别的自我一致性过程来识别可能的错误识别。 自我一致性过程将初始识别结果与先前由用户提供的至少一个样本进行比较。 如果比较显示初始识别结果与至少一个样本不一致，则将结果识别为可能不正确。 可以替代地或附加地使用分类器置信过程来识别可能的不正确识别结果。 用于显示最终结果的用户界面可以根据可能的不正确识别结果进行适当修改。

公开(公告)号：US20080002886A1

公开(公告)日：2008-01-03

申请号：US11477332

申请日：2006-06-28

申请人： Michael Revow ,  Manish Boval

发明人： Michael Revow ,  Manish Boval

IPC分类号： G06K9/62 ,  G06K9/00

CPC分类号： G06K9/6255 ,  G06K9/00422

摘要： Various technologies and techniques are disclosed for improving handwriting recognition using a neural network by allowing a user to provide samples. A recognition operation is performed on the user's handwritten input, and the user is not satisfied with the recognition result. The user selects an option to train the neural network on one or more characters to improve the recognition results. The user is prompted to specify samples for the certain character, word, or phrase, and the neural network is adjusted for the certain character, word, or phrase. Handwritten input is later received from the user. A recognition operation is performed on the handwritten input using the neural network that was adjusted for the certain character or characters.

摘要翻译： 公开了各种技术和技术，用于通过允许用户提供样本来改进使用神经网络的手写识别。 对用户的手写输入执行识别操作，并且用户对识别结果不满意。 用户选择一个或多个字符来训练神经网络以提高识别结果的选项。 提示用户为特定字符，单词或短语指定样本，并为特定字符，单词或短语调整神经网络。 手写输入稍后从用户接收。 使用针对特定字符或字符调整的神经网络对手写输入执行识别操作。