Patents by Inventor Sabri A. Mahmoud
Sabri A. Mahmoud has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11216617Abstract: Methods, systems, and computer readable media for machine translation between Arabic language and Arabic Sign Language are described.Type: GrantFiled: December 18, 2018Date of Patent: January 4, 2022Assignee: King Fahd University of Petroleum and MineralsInventors: Hamzah Luqman, Sabri A. Mahmoud
-
Publication number: 20200192982Abstract: Methods, systems, and computer readable media for machine translation between Arabic language and Arabic Sign Language are described.Type: ApplicationFiled: December 18, 2018Publication date: June 18, 2020Applicant: King Fahd University of Petroleum and MineralsInventors: Hamzah LUQMAN, Sabri A. MAHMOUD
-
Patent number: 10515148Abstract: 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.Type: GrantFiled: February 8, 2018Date of Patent: December 24, 2019Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Wasfi G. Al-Khatib, Tamim Alnethary
-
Publication number: 20190188255Abstract: 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.Type: ApplicationFiled: February 8, 2018Publication date: June 20, 2019Applicant: KING FAHD UNIVERSITY OF PETROLEUM AND MINERALSInventors: Sabri A. Mahmoud, Wasfi G. Al-Khatib, Tamim Alnethary
-
Patent number: 10268879Abstract: 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.Type: GrantFiled: September 20, 2018Date of Patent: April 23, 2019Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Ala Addin Sidig
-
Patent number: 10262198Abstract: 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.Type: GrantFiled: September 21, 2018Date of Patent: April 16, 2019Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Ala Addin Sidig
-
Publication number: 20190050637Abstract: 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.Type: ApplicationFiled: June 27, 2018Publication date: February 14, 2019Applicant: King Fahd University of Petroleum and MineralsInventors: Sabri A. MAHMOUD, Ala Addin SIDIG
-
Patent number: 10192105Abstract: 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.Type: GrantFiled: June 27, 2018Date of Patent: January 29, 2019Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Ala Addin Sidig
-
Publication number: 20190026546Abstract: 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.Type: ApplicationFiled: September 21, 2018Publication date: January 24, 2019Applicant: King Fahd University of Petroleum and MineralsInventors: SABRI A. MAHMOUD, Ala Addin SIDIG
-
Publication number: 20190019018Abstract: 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.Type: ApplicationFiled: September 20, 2018Publication date: January 17, 2019Applicant: King Fahd University of Petroleum and MineralsInventors: SABRI A. MAHMOUD, Ala Addin Sidig
-
Patent number: 10176367Abstract: 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.Type: GrantFiled: June 29, 2018Date of Patent: January 8, 2019Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Ala Addin Sidig
-
Patent number: 10176391Abstract: 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.Type: GrantFiled: July 16, 2018Date of Patent: January 8, 2019Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Mohammed O. Assayony
-
Patent number: 10163019Abstract: 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.Type: GrantFiled: July 13, 2018Date of Patent: December 25, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Mohammed O. Assayony
-
Patent number: 10156982Abstract: 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.Type: GrantFiled: July 11, 2018Date of Patent: December 18, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Baligh M. Al-Helali
-
Patent number: 10156983Abstract: 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.Type: GrantFiled: July 11, 2018Date of Patent: December 18, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Baligh M. Al-Helali
-
Publication number: 20180322338Abstract: 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.Type: ApplicationFiled: June 29, 2018Publication date: November 8, 2018Applicant: King Fahd University of Petroleum and MineralsInventors: Sabri A. MAHMOUD, Ala Addin SIDIG
-
Patent number: 10067669Abstract: 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-basal 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.Type: GrantFiled: July 13, 2017Date of Patent: September 4, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Baligh M. Al-Helali
-
Patent number: 10055660Abstract: 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.Type: GrantFiled: March 9, 2018Date of Patent: August 21, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Mohammed O. Assayony
-
Patent number: 10037458Abstract: 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.Type: GrantFiled: May 2, 2017Date of Patent: July 31, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Ala Addin Sidig
-
Patent number: 10002301Abstract: 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.Type: GrantFiled: September 19, 2017Date of Patent: June 19, 2018Assignee: King Fahd University of Petroleum and MineralsInventors: Sabri A. Mahmoud, Mohammed O. Assayony