-
公开(公告)号：US07974476B2
公开(公告)日：2011-07-05
申请号：US11755195
申请日：2007-05-30
申请人： Qi Zhang , Michael T. Black , Wei Yu
发明人： Qi Zhang , Michael T. Black , Wei Yu
CPC分类号： G06K9/6287 , G06K9/6232
摘要： A memory footprint of an Modified Quadratic Discriminant Function (MQDF) pattern recognition classifier is reduced without resulting in unacceptable classification accuracy degradation. Covariance matrices for multiple classes are clustered into a smaller number of matrices where different classes share the same set of eigenvectors. According to another approach, different numbers of principal components are stored for different classes based on criteria such as class usage frequency, larger variation in writing, and the like, resulting in fewer principal components to be stored in memory.
摘要翻译： 改进的二次判别函数（MQDF）模式识别分类器的存储器占用减少，而不会导致不可接受的分类精度降级。 多个类的协方差矩阵被聚类成较少数量的矩阵，其中不同的类共享同一组特征向量。 根据另一种方法，基于诸如类使用频率，较大的书写变化等等的标准，针对不同类别存储不同数量的主要组件，导致存储在存储器中的较少的主要组件。
-
公开(公告)号：US07620245B2
公开(公告)日：2009-11-17
申请号：US11442799
申请日：2006-05-30
申请人： Qi Zhang , Michael T. Black
发明人： Qi Zhang , Michael T. Black
CPC分类号： G06K9/00422 , G06K9/6807 , G06K2209/011
摘要： Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.
摘要翻译： 公开了改进草书手写识别的各种技术和技术。 从用户接收草写手写输入。 系统执行分层原型搜索作为识别操作的一部分。 对具有打印和草书样本的混合数据库执行相同的空间搜索。 对仅具有草书样本的草书数据库也执行相同的空间搜索。 这两个相同的空间搜索的结果被合并到组合的替代列表中。 然后，组合的替代列表用作对混合和草书数据库执行的动态时间扭曲搜索的约束。 动态时间扭曲搜索的结果也被合并到最终组合的替代列表中，组合的替代列表用于对用户的手写输入进行识别决定。
-
公开(公告)号：US08326040B2
公开(公告)日：2012-12-04
申请号：US12880121
申请日：2010-09-12
申请人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
发明人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
CPC分类号： G06K9/00422 , G06K9/6256 , G06K9/6292
摘要： Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.
摘要翻译： 公开了改进手写识别操作的各种技术和技术。 手写输入以训练模式接收，并通过几个基本识别器生成多个替代列表。 备用列表一起组合成组合的备用列表。 如果正确的结果在组合列表中，则使用每个正确/不正确的备用对来生成训练模式。 存储与替代对相关联的权重。 在运行时，组合的备用列表就像培训时间一样生成。 训练后的比较网可用于比较组合列表中的任何两个替代项。 与一个或多个神经网络基础识别器一起使用模板匹配基础识别器来改善识别操作。 该系统提供了对打印和草书数据进行培训的比较器网络和重新排序网络过程，以及已经对草书数据进行了培训的系统。 相应地使用相应的比较器网络和重新排序网络进程。
-
公开(公告)号：US20070280535A1
公开(公告)日：2007-12-06
申请号：US11442799
申请日：2006-05-30
申请人： Qi Zhang , Michael T. Black
发明人： Qi Zhang , Michael T. Black
IPC分类号： G06K9/18
CPC分类号： G06K9/00422 , G06K9/6807 , G06K2209/011
摘要： Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.
摘要翻译： 公开了改进草书手写识别的各种技术和技术。 从用户接收草写手写输入。 系统执行分层原型搜索作为识别操作的一部分。 对具有打印和草书样本的混合数据库执行相同的空间搜索。 对仅具有草书样本的草书数据库也执行相同的空间搜索。 这两个相同的空间搜索的结果被合并到组合的替代列表中。 然后，组合的替代列表用作对混合和草书数据库执行的动态时间扭曲搜索的约束。 动态时间扭曲搜索的结果也被合并到最终组合的替代列表中，组合的替代列表用于对用户的手写输入进行识别决定。
-
公开(公告)号：US08265377B2
公开(公告)日：2012-09-11
申请号：US13073359
申请日：2011-03-28
申请人： Qi Zhang , Michael T. Black
发明人： Qi Zhang , Michael T. Black
CPC分类号： G06K9/00422 , G06K9/6807 , G06K2209/011
摘要： Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.
摘要翻译： 公开了改进草书手写识别的各种技术和技术。 从用户接收草写手写输入。 系统执行分层原型搜索作为识别操作的一部分。 对具有打印和草书样本的混合数据库执行相同的空间搜索。 对仅具有草书样本的草书数据库也执行相同的空间搜索。 这两个相同的空间搜索的结果被合并到组合的替代列表中。 然后，组合的替代列表用作对混合和草书数据库执行的动态时间扭曲搜索的约束。 动态时间扭曲搜索的结果也被合并到最终组合的替代列表中，组合的替代列表用于对用户的手写输入进行识别决定。
-
公开(公告)号：US07929768B2
公开(公告)日：2011-04-19
申请号：US12576137
申请日：2009-10-08
申请人： Qi Zhang , Michael T. Black
发明人： Qi Zhang , Michael T. Black
CPC分类号： G06K9/00422 , G06K9/6807 , G06K2209/011
摘要： Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.
摘要翻译： 公开了改进草书手写识别的各种技术和技术。 从用户接收草写手写输入。 系统执行分层原型搜索作为识别操作的一部分。 对具有打印和草书样本的混合数据库执行相同的空间搜索。 对仅具有草书样本的草书数据库也执行相同的空间搜索。 这两个相同的空间搜索的结果被合并到组合的替代列表中。 然后，组合的替代列表用作对混合和草书数据库执行的动态时间扭曲搜索的约束。 动态时间扭曲搜索的结果也被合并到最终组合的替代列表中，组合的替代列表用于对用户的手写输入进行识别决定。
-
公开(公告)号：US20110007963A1
公开(公告)日：2011-01-13
申请号：US12880121
申请日：2010-09-12
申请人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
发明人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
IPC分类号： G06K9/62
CPC分类号： G06K9/00422 , G06K9/6256 , G06K9/6292
摘要： Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.
摘要翻译： 公开了改进手写识别操作的各种技术和技术。 手写输入以训练模式接收，并通过几个基本识别器生成多个替代列表。 备用列表一起组合成组合的备用列表。 如果正确的结果在组合列表中，则使用每个正确/不正确的备用对来生成训练模式。 存储与替代对相关联的权重。 在运行时，组合的备用列表就像培训时间一样生成。 训练后的比较网可用于比较组合列表中的任何两个替代项。 与一个或多个神经网络基础识别器一起使用模板匹配基础识别器来改善识别操作。 该系统提供了对打印和草书数据进行培训的比较器网络和重新排序网络过程，以及已经对草书数据进行了培训的系统。 相应地使用相应的比较器网络和重新排序网络进程。
-
公开(公告)号：US07817857B2
公开(公告)日：2010-10-19
申请号：US11443762
申请日：2006-05-31
申请人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
发明人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
CPC分类号： G06K9/00422 , G06K9/6256 , G06K9/6292
摘要： Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.
摘要翻译： 公开了改进手写识别操作的各种技术和技术。 手写输入以训练模式接收，并通过几个基本识别器生成多个替代列表。 备用列表一起组合成组合的备用列表。 如果正确的结果在组合列表中，则使用每个正确/不正确的备用对来生成训练模式。 存储与替代对相关联的权重。 在运行时，组合的备用列表就像培训时间一样生成。 训练后的比较网可用于比较组合列表中的任何两个替代项。 与一个或多个神经网络基础识别器一起使用模板匹配基础识别器来改善识别操作。 该系统提供了对打印和草书数据进行培训的比较器网络和重新排序网络过程，以及已经对草书数据进行了培训的系统。 相应地使用相应的比较器网络和重新排序网络进程。
-
公开(公告)号：US20100027889A1
公开(公告)日：2010-02-04
申请号：US12576137
申请日：2009-10-08
申请人： Qi Zhang , Michael T. Black
发明人： Qi Zhang , Michael T. Black
IPC分类号： G06K9/18
CPC分类号： G06K9/00422 , G06K9/6807 , G06K2209/011
摘要： Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.
摘要翻译： 公开了改进草书手写识别的各种技术和技术。 从用户接收草写手写输入。 系统执行分层原型搜索作为识别操作的一部分。 对具有打印和草书样本的混合数据库执行相同的空间搜索。 对仅具有草书样本的草书数据库也执行相同的空间搜索。 这两个相同的空间搜索的结果被合并到组合的替代列表中。 然后，组合的替代列表用作对混合和草书数据库执行的动态时间扭曲搜索的约束。 动态时间扭曲搜索的结果也被合并到最终组合的替代列表中，组合的替代列表用于对用户的手写输入进行识别决定。
-
公开(公告)号：US20070280536A1
公开(公告)日：2007-12-06
申请号：US11443762
申请日：2006-05-31
申请人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
发明人： Qi Zhang , Ahmad A. Abdulkader , Michael T. Black
CPC分类号： G06K9/00422 , G06K9/6256 , G06K9/6292
摘要： Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.
摘要翻译： 公开了改进手写识别操作的各种技术和技术。 手写输入以训练模式接收，并通过几个基本识别器生成多个替代列表。 备用列表一起组合成组合的备用列表。 如果正确的结果在组合列表中，则使用每个正确/不正确的备用对来生成训练模式。 存储与替代对相关联的权重。 在运行时，组合的备用列表就像培训时间一样生成。 训练后的比较网可用于比较组合列表中的任何两个替代项。 与一个或多个神经网络基础识别器一起使用模板匹配基础识别器来改善识别操作。 该系统提供了对打印和草书数据进行培训的比较器网络和重新排序网络过程，以及已经对草书数据进行了培训的系统。 相应地使用相应的比较器网络和重新排序网络进程。
-
-
-
-
-
-
-
-
-
搜索结果
254 条记录 (耗时 0.021 秒)
