Magdi Mohamed - Academia.edu (original) (raw)

Papers by Magdi Mohamed

... Pattern Analysis Machine Intelligence, vol. submitted, 1994. MA Mohamed, “Handwritten Word Re... more ... Pattern Analysis Machine Intelligence, vol. submitted, 1994. MA Mohamed, “Handwritten Word Recognition using Generalized Hidden Markov Models,” in Electrical and Computer Engineering. Columbia, MO: University of Missouri - Columbia, 1995. ...

Pattern Recognition Letters, May 1, 1996

... 66). D.-S. Lee and SN Srihari, Handprinted digit recognition: a comparison of algorithms, Pap... more ... 66). D.-S. Lee and SN Srihari, Handprinted digit recognition: a comparison of algorithms, Paper presented at the Third Internat. Workshop Frontiers Handwriting Recognition Buffalo, NY (1993). accepted for publicationM. Mohamed ...

IEEE Transactions on Fuzzy Systems, 1995

IEEE Transactions on Fuzzy Systems, 2000

... Handwritten word recognition using generalized hidden markov models. ... Source, Pages: 161. ... more ... Handwritten word recognition using generalized hidden markov models. ... Source, Pages: 161. Year of Publication: 1995. ISBN:0-591-11995-1, Order Number:AAI9705254. Authors, Magdi Abuelgasim Mohamed, Supervisors, Paul Gader, Publisher, University of Missouri - Columbia ...

Q filter performs a continuum of linear and non-linear filtering operations, a reconfigurable tec... more Q filter performs a continuum of linear and non-linear filtering operations, a reconfigurable technique. Q filter utilizes a function called Q measure is modeled by a unique mathematical structure. Q measure allows for efficient hardware and software implementations of various useful novel filtering operations and conventional filtering operation is defined using a set of adjustable kernel parameters. Q measure is a novel, based on the extension of the well-known Kanno of Q measure.

Abstract: Automatic use (102) of a disjoint probabilistic analysis of captured temporally parsed ... more Abstract: Automatic use (102) of a disjoint probabilistic analysis of captured temporally parsed data (101) regarding at least a first and a second item serves to facilitate disambiguating state information as pertains to the first item from information as pertains to the second item. This can also comprise, for example, using a joint probability as pertains to the temporally parsed data for the first item and the temporally parsed data for the second item, by using, for example, a Bayesian-based probabilistic analysis of the temporally ...

Applications of Fuzzy Logic Technology II, 1995

ABSTRACT Two applications of fuzzy integrals to handwritten word recognition are discribed. Fuzzy... more ABSTRACT Two applications of fuzzy integrals to handwritten word recognition are discribed. Fuzzy integrals are used in a dynamic programming based, offline handwritten word recognition algorithm. This algorithm finds optimal matches between word images and strings in lexicons. Fuzzy integrals are used to compute the match scores. Fuzzy integrals are also used in a hidden Markov model based, offline handwritten word recognition algorithm. In this case, fuzzy measures and integrals are used as alternatives to probabilistic measures and ordinary integrals. Results are presented on standard data sets consisting of real images collected form United States Postal Service mail stream.

SPIE Proceedings of Electronic Imaging: Science and Technology. Conference on Visual Communications and Image Processing (VCIP), Jan 28, 2007

An approach is introduced in this paper to track the object motion and estimate pose jointly with... more An approach is introduced in this paper to track the object motion and estimate pose jointly within the framework of particle filtering, which can directly estimate the 3D poses from 2D points in the images. The Adaptive Block Matching technique (ABM) is firstly used to improve the computational efficiency of particle filtering. Next, Scale-Invariant Feature Transform (SIFT) is applied to extract feature points. We can show that pose estimation from the corresponding points can be concluded as a Sylvester's Equation, and ...

… Processing, 2006 IEEE …, Oct 8, 2006

Particle filters have been introduced as a powerful tool to estimate the posterior density of non... more Particle filters have been introduced as a powerful tool to estimate the posterior density of nonlinear systems. These filters are also capable of processing data online as required in many practical applications. In this paper, we propose a novel technique for video stabilization based on the particle filtering framework. Scale-invariant feature points are extracted to form a rough estimate which is used to model the importance density. We use a constant-velocity Kalman filter model to estimate intentional camera movement. We ...

In this paper, we present a novel decentralized Bayesian framework using multiple collaborative c... more In this paper, we present a novel decentralized Bayesian framework using multiple collaborative cameras for robust and efficient multiple object tracking with significant and persistent occlusion. This approach avoids the common practice of using a complex joint state representation and a centralized processor for multiple camera tracking. When the objects are in close proximity or present multi-object occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multi- ...

Multiple-target tracking has received tremendous attention due to its wide practical applicabilit... more Multiple-target tracking has received tremendous attention due to its wide practical applicability in video processing and analysis applications. Most existing techniques, however, suffer from the well-known “multitarget occlusion ” problem and/or immense computational cost due to its use of high-dimensional joint-state representations. In this paper, we present a distributed Bayesian framework using multiple collaborative cameras for robust and efficient multiple-target tracking in crowded environments with significant and persistent occlusion. When the targets are in close proximity or present multitarget occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multitarget occlusion problem in an innovative way. Specifically, we propose to model the camera collaboration likelihood density by using epipolar geometry with sequential Monte Carlo implementation. Experimental results have been demonstrated for both synthet...

In this paper, we present a novel decentralized Bayesian framework using multiple collaborative c... more In this paper, we present a novel decentralized Bayesian framework using multiple collaborative cameras for robust and efficient multiple object tracking with significant and persistent occlusion. This approach avoids the common practice of using a complex joint state representation and a centralized processor for multiple camera tracking. When the objects are in close proximity or present multi-object occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multi-object occlusion problem. Specifically, we propose to model the camera collaboration likelihood density by using epipolar geometry with particle filter implementation. The performance of our approach has been demonstrated on both synthetic and realworld video data. 1. INTRODUCTION AND RELATED

Experiments involving handwritten word recognition on words taken from images of handwritten addr... more Experiments involving handwritten word recognition on words taken from images of handwritten address blocks from the United States Postal Service mailstream are described. The word recognition algorithm relies on the use of neural networks at the character level. The neural networks were trained using crisp and fuzzy desired outputs. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level. INTRODUCTION Handwritten word recognition by computer is a very difficult task. Although considerable research has been performed in character recognition, not much has been done in word recognition. Interest has picked up lately, as can be seen by viewing the contents of the proceedings of recent conferences in these areas [1,2,3,4]. Even in the machine-printed case, word recognition consists of more than just reading the in...

... Pattern Analysis Machine Intelligence, vol. submitted, 1994. MA Mohamed, “Handwritten Word Re... more ... Pattern Analysis Machine Intelligence, vol. submitted, 1994. MA Mohamed, “Handwritten Word Recognition using Generalized Hidden Markov Models,” in Electrical and Computer Engineering. Columbia, MO: University of Missouri - Columbia, 1995. ...

Pattern Recognition Letters, May 1, 1996

... 66). D.-S. Lee and SN Srihari, Handprinted digit recognition: a comparison of algorithms, Pap... more ... 66). D.-S. Lee and SN Srihari, Handprinted digit recognition: a comparison of algorithms, Paper presented at the Third Internat. Workshop Frontiers Handwriting Recognition Buffalo, NY (1993). accepted for publicationM. Mohamed ...

IEEE Transactions on Fuzzy Systems, 1995

IEEE Transactions on Fuzzy Systems, 2000

... Handwritten word recognition using generalized hidden markov models. ... Source, Pages: 161. ... more ... Handwritten word recognition using generalized hidden markov models. ... Source, Pages: 161. Year of Publication: 1995. ISBN:0-591-11995-1, Order Number:AAI9705254. Authors, Magdi Abuelgasim Mohamed, Supervisors, Paul Gader, Publisher, University of Missouri - Columbia ...

Q filter performs a continuum of linear and non-linear filtering operations, a reconfigurable tec... more Q filter performs a continuum of linear and non-linear filtering operations, a reconfigurable technique. Q filter utilizes a function called Q measure is modeled by a unique mathematical structure. Q measure allows for efficient hardware and software implementations of various useful novel filtering operations and conventional filtering operation is defined using a set of adjustable kernel parameters. Q measure is a novel, based on the extension of the well-known Kanno of Q measure.

Abstract: Automatic use (102) of a disjoint probabilistic analysis of captured temporally parsed ... more Abstract: Automatic use (102) of a disjoint probabilistic analysis of captured temporally parsed data (101) regarding at least a first and a second item serves to facilitate disambiguating state information as pertains to the first item from information as pertains to the second item. This can also comprise, for example, using a joint probability as pertains to the temporally parsed data for the first item and the temporally parsed data for the second item, by using, for example, a Bayesian-based probabilistic analysis of the temporally ...

Applications of Fuzzy Logic Technology II, 1995

ABSTRACT Two applications of fuzzy integrals to handwritten word recognition are discribed. Fuzzy... more ABSTRACT Two applications of fuzzy integrals to handwritten word recognition are discribed. Fuzzy integrals are used in a dynamic programming based, offline handwritten word recognition algorithm. This algorithm finds optimal matches between word images and strings in lexicons. Fuzzy integrals are used to compute the match scores. Fuzzy integrals are also used in a hidden Markov model based, offline handwritten word recognition algorithm. In this case, fuzzy measures and integrals are used as alternatives to probabilistic measures and ordinary integrals. Results are presented on standard data sets consisting of real images collected form United States Postal Service mail stream.

SPIE Proceedings of Electronic Imaging: Science and Technology. Conference on Visual Communications and Image Processing (VCIP), Jan 28, 2007

An approach is introduced in this paper to track the object motion and estimate pose jointly with... more An approach is introduced in this paper to track the object motion and estimate pose jointly within the framework of particle filtering, which can directly estimate the 3D poses from 2D points in the images. The Adaptive Block Matching technique (ABM) is firstly used to improve the computational efficiency of particle filtering. Next, Scale-Invariant Feature Transform (SIFT) is applied to extract feature points. We can show that pose estimation from the corresponding points can be concluded as a Sylvester's Equation, and ...

… Processing, 2006 IEEE …, Oct 8, 2006

Particle filters have been introduced as a powerful tool to estimate the posterior density of non... more Particle filters have been introduced as a powerful tool to estimate the posterior density of nonlinear systems. These filters are also capable of processing data online as required in many practical applications. In this paper, we propose a novel technique for video stabilization based on the particle filtering framework. Scale-invariant feature points are extracted to form a rough estimate which is used to model the importance density. We use a constant-velocity Kalman filter model to estimate intentional camera movement. We ...

In this paper, we present a novel decentralized Bayesian framework using multiple collaborative c... more In this paper, we present a novel decentralized Bayesian framework using multiple collaborative cameras for robust and efficient multiple object tracking with significant and persistent occlusion. This approach avoids the common practice of using a complex joint state representation and a centralized processor for multiple camera tracking. When the objects are in close proximity or present multi-object occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multi- ...

Multiple-target tracking has received tremendous attention due to its wide practical applicabilit... more Multiple-target tracking has received tremendous attention due to its wide practical applicability in video processing and analysis applications. Most existing techniques, however, suffer from the well-known “multitarget occlusion ” problem and/or immense computational cost due to its use of high-dimensional joint-state representations. In this paper, we present a distributed Bayesian framework using multiple collaborative cameras for robust and efficient multiple-target tracking in crowded environments with significant and persistent occlusion. When the targets are in close proximity or present multitarget occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multitarget occlusion problem in an innovative way. Specifically, we propose to model the camera collaboration likelihood density by using epipolar geometry with sequential Monte Carlo implementation. Experimental results have been demonstrated for both synthet...

In this paper, we present a novel decentralized Bayesian framework using multiple collaborative c... more In this paper, we present a novel decentralized Bayesian framework using multiple collaborative cameras for robust and efficient multiple object tracking with significant and persistent occlusion. This approach avoids the common practice of using a complex joint state representation and a centralized processor for multiple camera tracking. When the objects are in close proximity or present multi-object occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multi-object occlusion problem. Specifically, we propose to model the camera collaboration likelihood density by using epipolar geometry with particle filter implementation. The performance of our approach has been demonstrated on both synthetic and realworld video data. 1. INTRODUCTION AND RELATED

Experiments involving handwritten word recognition on words taken from images of handwritten addr... more Experiments involving handwritten word recognition on words taken from images of handwritten address blocks from the United States Postal Service mailstream are described. The word recognition algorithm relies on the use of neural networks at the character level. The neural networks were trained using crisp and fuzzy desired outputs. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level. INTRODUCTION Handwritten word recognition by computer is a very difficult task. Although considerable research has been performed in character recognition, not much has been done in word recognition. Interest has picked up lately, as can be seen by viewing the contents of the proceedings of recent conferences in these areas [1,2,3,4]. Even in the machine-printed case, word recognition consists of more than just reading the in...