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

US10268879B2 Sign language method using clustering 有权
公开(公告)号：US10268879B2
公开(公告)日：2019-04-23
申请号：US16137025
申请日：2018-09-20
申请人： King Fahd University of Petroleum and Minerals
发明人： Sabri A. Mahmoud , Ala Addin Sidig
IPC分类号： G10L21/06 , G06K9/00 , G06F3/01
摘要： A sign language recognizer is configured to detect interest points in an extracted sign language feature, wherein the interest points are localized in space and time in each image acquired from a plurality of frames of a sign language video; apply a filter to determine one or more extrema of a central region of the interest points; associate features with each interest point using a neighboring pixel function; cluster a group of extracted sign language features from the images based on a similarity between the extracted sign language features; represent each image by a histogram of visual words corresponding to the respective image to generate a code book; train a classifier to classify each extracted sign language feature using the code book; detect a posture in each frame of the sign language video using the trained classifier; and construct a sign gesture based on the detected postures.

2. 发明授权

US10262198B2 Automated sign language recognition method 有权
公开(公告)号：US10262198B2
公开(公告)日：2019-04-16
申请号：US16138392
申请日：2018-09-21
申请人： King Fahd University of Petroleum and Minerals
发明人： Sabri A. Mahmoud , Ala Addin Sidig
IPC分类号： G10L21/06 , G06K9/00 , G06F3/01 , G06K9/46
摘要： A sign language recognizer is configured to detect interest points in an extracted sign language feature, wherein the interest points are localized in space and time in each image acquired from a plurality of frames of a sign language video; apply a filter to determine one or more extrema of a central region of the interest points; associate features with each interest point using a neighboring pixel function; cluster a group of extracted sign language features from the images based on a similarity between the extracted sign language features; represent each image by a histogram of visual words corresponding to the respective image to generate a code book; train a classifier to classify each extracted sign language feature using the code book; detect a posture in each frame of the sign language video using the trained classifier; and construct a sign gesture based on the detected postures.

3. 发明授权

US10037458B1 Automated sign language recognition 有权
公开(公告)号：US10037458B1
公开(公告)日：2018-07-31
申请号：US15584361
申请日：2017-05-02
申请人： King Fahd University of Petroleum and Minerals
发明人： Sabri A. Mahmoud , Ala Addin Sidig
IPC分类号： G10L21/00 , G06K9/00 , G06F3/01
CPC分类号： G06K9/00355 , G06F3/017 , G06K9/00389 , G06K9/4676
摘要： A sign language recognizer is configured to detect interest points in an extracted sign language feature, wherein the interest points are localized in space and time in each image acquired from a plurality of frames of a sign language video; apply a filter to determine one or more extrema of a central region of the interest points; associate features with each interest point using a neighboring pixel function; cluster a group of extracted sign language features from the images based on a similarity between the extracted sign language features; represent each image by a histogram of visual words corresponding to the respective image to generate a code book; train a classifier to classify each extracted sign language feature using the code book; detect a posture in each frame of the sign language video using the trained classifier; and construct a sign gesture based on the detected postures.

4. 发明申请

US20190188255A1 NOVEL ARABIC SPELL CHECKING ERROR MODEL 审中-公开
公开(公告)号：US20190188255A1
公开(公告)日：2019-06-20
申请号：US15891563
申请日：2018-02-08
申请人： KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS
发明人： Sabri A. Mahmoud , Wasfi G. Al-Khatib , Tamim Alnethary
IPC分类号： G06F17/27 , G06F17/22
CPC分类号： G06F17/273 , G06F17/2217 , G06F17/2223 , G06F17/2755 , G06F17/2863
摘要： Disclosed is a data driven error model that is based on error patterns found at the morphemes level. A model is generated by error-correct patterns generator and is stored in an error-correct patterns database (ECPD). The ECPD is used in conjunction with a correction candidates' generator (CCG) to provide a list of correction candidates for a given error word. The error model can learn the types and forms of the language patterns from an annotated corpus. The error model can be used to analyze the type of error and can provide candidates corrections for wide ranges of Arabic spelling errors.

5. 发明授权

US10156983B1 Method using statistical features for character recognition 有权
公开(公告)号：US10156983B1
公开(公告)日：2018-12-18
申请号：US16032853
申请日：2018-07-11
申请人： King Fahd University of Petroleum and Minerals
发明人： Sabri A. Mahmoud , Baligh M. Al-Helali
IPC分类号： G06K9/00 , G06F3/0488 , G06K9/34 , G06K9/22
摘要： A character recognition device includes circuitry that is configured to remove duplicate successive points of a plurality of points in a handwritten stroke to form an enhanced handwritten stroke; space the plurality of points a uniform distance apart; detect primary strokes and secondary strokes of the enhanced handwritten stroke; merge the primary strokes; generate a primary merged stroke; extract raw point-based features from local features of the primary merged stroke; extract statistical features from computed statistics associated with the raw point-based features to form primary merged stroke features; train and classify data from the primary merged stroke features and secondary stroke features to form stroke models; determine a plurality of primary merged stroke model candidates from the stroke models; compute a likelihood value for a combined set of primary stroke candidates and a set of secondary stroke candidates; and determine the handwritten stroke from the computing.

6. 发明授权

US09501708B1 Adaptive sliding windows for text recognition 有权
标题翻译：用于文本识别的自适应滑动窗口
公开(公告)号：US09501708B1
公开(公告)日：2016-11-22
申请号：US14850406
申请日：2015-09-10
申请人： King Fahd University of Petroleum and Minerals
发明人： Irfan Ahmad , Sabri A. Mahmoud
IPC分类号： G06K9/62 , G06K9/34 , G06K9/00
CPC分类号： G06K9/6828 , G06K9/00879 , G06K2209/013
摘要： A text-recognition system and method include a trained classifier configured to identify a font of a frame of text line image. The system also includes an adaptive sliding window configured to divide the frame into a plurality of cells. A first cell is located around a prominent writing line of the text line image. Additional cells are located above the prominent writing line and below the prominent writing line, such that each of the additional cells above the prominent writing line has a same percentage of ink-pixels and each of the additional cells below the prominent writing line has a same percentage of ink-pixels. The system also includes a font-specific feature parameters database configured for extraction of text features from each of the cells. The system also includes one or more trained font-specific recognizers configured to recognize the extracted text features using an associated font-specific recognizer for the identified font.
摘要翻译：文本识别系统和方法包括被配置为识别文本行图像的帧的字体的训练分类器。该系统还包括被配置为将帧划分成多个单元的自适应滑动窗口。第一个单元格位于文本行图像的突出写入行周围。附加单元位于突出书写线之上并在突出书写线下方，使得突出书写线之上的每个附加单元具有相同百分比的墨像，并且突出书写线以下的每个附加单元具有相同的墨像的百分比。该系统还包括配置用于从每个单元提取文本特征的字体专用特征参数数据库。该系统还包括一个或多个经过训练的字体特定识别器，其被配置为使用用于识别的字体的相关联的字体特定识别器来识别所提取的文本特征。

7. 发明授权

US10515148B2 Arabic spell checking error model 有权
公开(公告)号：US10515148B2
公开(公告)日：2019-12-24
申请号：US15891563
申请日：2018-02-08
申请人： KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS
发明人： Sabri A. Mahmoud , Wasfi G. Al-Khatib , Tamim Alnethary
IPC分类号： G06F17/00 , G06F17/27 , G06F17/22 , G06F17/28
摘要： Disclosed is a data driven error model that is based on error patterns found at the morphemes level. A model is generated by error-correct patterns generator and is stored in an error-correct patterns database (ECPD). The ECPD is used in conjunction with a correction candidates' generator (CCG) to provide a list of correction candidates for a given error word. The error model can learn the types and forms of the language patterns from an annotated corpus. The error model can be used to analyze the type of error and can provide candidates corrections for wide ranges of Arabic spelling errors.

8. 发明授权

US10156982B1 Writing direction extraction for character recognition 有权
公开(公告)号：US10156982B1
公开(公告)日：2018-12-18
申请号：US16032809
申请日：2018-07-11
申请人： King Fahd University of Petroleum and Minerals
发明人： Sabri A. Mahmoud , Baligh M. Al-Helali
IPC分类号： G06K9/00 , G06F3/0488 , G06K9/34 , G06K9/22
摘要： A character recognition device includes circuitry that is configured to remove duplicate successive points of a plurality of points in a handwritten stroke to form an enhanced handwritten stroke; space the plurality of points a uniform distance apart; detect primary strokes and secondary strokes of the enhanced handwritten stroke; merge the primary strokes; generate a primary merged stroke; extract raw point-based features from local features of the primary merged stroke; extract statistical features from computed statistics associated with the raw point-based features to form primary merged stroke features; train and classify data from the primary merged stroke features and secondary stroke features to form stroke models; determine a plurality of primary merged stroke model candidates from the stroke models; compute a likelihood value for a combined set of primary stroke candidates and a set of secondary stroke candidates; and determine the handwritten stroke from the computing.

9. 发明授权

US10176391B1 Discrete hidden markov model basis for arabic handwriting recognition 有权
公开(公告)号：US10176391B1
公开(公告)日：2019-01-08
申请号：US16036481
申请日：2018-07-16
申请人： KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS
发明人： Sabri A. Mahmoud , Mohammed O. Assayony
IPC分类号： G06K9/00 , G06T7/11 , G06F17/24 , G06K9/46 , G06F3/01
摘要： A system, a non-transitory computer readable medium, and a method for Arabic handwriting recognition are provided. The method includes acquiring an input image representative of a handwritten Arabic text from a user, partitioning the input image into a plurality of regions, determining a bag of features representation for each region of the plurality of regions, modeling each region independently by multi stream discrete Hidden Markov Model (HMM), and identifying a text based on the HMM models.

10. 发明授权

US10163019B1 Arabic handwriting recognition system and method 有权
公开(公告)号：US10163019B1
公开(公告)日：2018-12-25
申请号：US16035257
申请日：2018-07-13
申请人： KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS
发明人： Sabri A. Mahmoud , Mohammed O. Assayony
IPC分类号： G06K9/00 , G06T7/11 , G06F17/24 , G06K9/46 , G06F3/01
摘要： A system, a non-transitory computer readable medium, and a method for Arabic handwriting recognition are provided. The method includes acquiring an input image representative of a handwritten Arabic text from a user, partitioning the input image into a plurality of regions, determining a bag of features representation for each region of the plurality of regions, modeling each region independently by multi stream discrete Hidden Markov Model (HMM), and identifying a text based on the HMM models.

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