Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030954
Shaker El-Sappagh, Mohammed M Elmogy, A. Riad, H. Zaghloul, F. Badria
Domain knowledge ontology supports the implementation of intelligent Case Based Reasoning (CBR) systems. Standardized terminologies support efficient indexing and processing of patient data. It is an essential element for the implementation of knowledge-based clinical decision support by exploiting pre-defined semantic relationships, both hierarchical and non-hierarchical in nature. Systemized Nomenclature of Medicine-Clinical Terms (SNOMED CT) is the most comprehensive and complete terminology. This paper proposes an encoding methodology for clinical data using SNOMED CT. A case study for a diabetes diagnosis data set will be tested where SNOMED CT provides a concept coverage of ~75% for its clinical terms. Custom codes will be provided for uncovered terms. The encoded data set is derived from electronic health record database, and it represents a case base knowledge. The collected concept IDs will be used to build a domain ontology for diabetes diagnosis CBR. This ontology contains 550 concept IDs. The encoded case base and the domain ontology can be used to build a knowledge intensive CBR.
{"title":"A proposed SNOMED CT ontology-based encoding methodology for diabetes diagnosis case-base","authors":"Shaker El-Sappagh, Mohammed M Elmogy, A. Riad, H. Zaghloul, F. Badria","doi":"10.1109/ICCES.2014.7030954","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030954","url":null,"abstract":"Domain knowledge ontology supports the implementation of intelligent Case Based Reasoning (CBR) systems. Standardized terminologies support efficient indexing and processing of patient data. It is an essential element for the implementation of knowledge-based clinical decision support by exploiting pre-defined semantic relationships, both hierarchical and non-hierarchical in nature. Systemized Nomenclature of Medicine-Clinical Terms (SNOMED CT) is the most comprehensive and complete terminology. This paper proposes an encoding methodology for clinical data using SNOMED CT. A case study for a diabetes diagnosis data set will be tested where SNOMED CT provides a concept coverage of ~75% for its clinical terms. Custom codes will be provided for uncovered terms. The encoded data set is derived from electronic health record database, and it represents a case base knowledge. The collected concept IDs will be used to build a domain ontology for diabetes diagnosis CBR. This ontology contains 550 concept IDs. The encoded case base and the domain ontology can be used to build a knowledge intensive CBR.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115883834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030978
Ihab Sbeity, M. Dbouk
In order to allow software designers to determine the performance of software during design, Connie Smith has introduced the concept of Software Performance Engineering (SPE). The idea is to bring performance evaluation into the software design process. Several approaches have been proposed to provide such techniques. Some of them propose to derive from a UML (Unified Modeling Language) model a performance model. UML2SAN is one of the most recent works in SPE, that permits to generate a performance model (SAN: Stochastic Automata Network) from UML specifications. In this paper, we verify the convenience of UML2SAN by predicting deadlock of transfer funds in a banking system during the design phase.
{"title":"Software performance engineering using UML2SAN: Deadlock prediction of funds transfer","authors":"Ihab Sbeity, M. Dbouk","doi":"10.1109/ICCES.2014.7030978","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030978","url":null,"abstract":"In order to allow software designers to determine the performance of software during design, Connie Smith has introduced the concept of Software Performance Engineering (SPE). The idea is to bring performance evaluation into the software design process. Several approaches have been proposed to provide such techniques. Some of them propose to derive from a UML (Unified Modeling Language) model a performance model. UML2SAN is one of the most recent works in SPE, that permits to generate a performance model (SAN: Stochastic Automata Network) from UML specifications. In this paper, we verify the convenience of UML2SAN by predicting deadlock of transfer funds in a banking system during the design phase.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128210266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030987
A. S. Elons, Menna Ahmed, Hwaidaa Shedid, M. Tolba
Researchers in sign language recognition customized different sensors to capture hand signs. Gloves, digital cameras, depth cameras and Kinect were used alternatively in most systems. Due to signs closeness, input accuracy is a very essential constraint to reach a high recognition accuracy. Although previous systems accomplished high recognition accuracy, they suffer from stability in realistic environment due to variance in signing speed, lighting, etc... In this paper, a recognition system for ArSL has been developed based on a new digital sensor called “Leap Motion”. This sensor tackles the major issues in vision-based systems such as skin color, lighting etc... Leap motion captures hands and fingers movements in 3D digital format. The sensor throws 3D digital information in each frame of movement. These temporal and spatial features are fed into a Multi-layer perceptron Neural Network (MLP). The system was tested on 50 different dynamic signs (distinguishable without non-manual features) and the recognition accuracy reached 88% for two different persons. Although Leap motion tracks both hands accurately, unfortunately Leap motion does not track non-manual features. This system can be enhanced by adding other sensors to track other non-manual features such as facial expressions and body poses. The proposed sensor can work simultaneously with leap motion to capture all sign's features.
{"title":"Arabic sign language recognition using leap motion sensor","authors":"A. S. Elons, Menna Ahmed, Hwaidaa Shedid, M. Tolba","doi":"10.1109/ICCES.2014.7030987","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030987","url":null,"abstract":"Researchers in sign language recognition customized different sensors to capture hand signs. Gloves, digital cameras, depth cameras and Kinect were used alternatively in most systems. Due to signs closeness, input accuracy is a very essential constraint to reach a high recognition accuracy. Although previous systems accomplished high recognition accuracy, they suffer from stability in realistic environment due to variance in signing speed, lighting, etc... In this paper, a recognition system for ArSL has been developed based on a new digital sensor called “Leap Motion”. This sensor tackles the major issues in vision-based systems such as skin color, lighting etc... Leap motion captures hands and fingers movements in 3D digital format. The sensor throws 3D digital information in each frame of movement. These temporal and spatial features are fed into a Multi-layer perceptron Neural Network (MLP). The system was tested on 50 different dynamic signs (distinguishable without non-manual features) and the recognition accuracy reached 88% for two different persons. Although Leap motion tracks both hands accurately, unfortunately Leap motion does not track non-manual features. This system can be enhanced by adding other sensors to track other non-manual features such as facial expressions and body poses. The proposed sensor can work simultaneously with leap motion to capture all sign's features.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132469700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030955
Rehab Mahmoud, Nashwa El-Bendary, Hoda M. O. Mokhtar, A. Hassanien
Disabilities, specially the ones caused by injuries of spinal cord, affect both people's behavior and participation in daily activities. Therefore, developing automated systems that monitor and assess the progress of Spinal Cord Injury (SCI) patients represents an accelerated need. In this paper we utilize the framework of the International Classification for Functioning, disability and health (ICF) in order to propose an automatic system for SCI patients progress monitoring and rehabilitation. The ICF is a reference classification system that aims at improving integration of health information and ensuring the collection of accurate health data. The proposed system is divided into three phases; namely (1) ICF code construction, (2) progress monitoring, and (3) progress assessment phases. Comparing the manual expert-based progress assessment to experimental results obtained by the proposed system in this article, an efficiency of 100% has been achieved by the three previously stated phases of the proposed system.
{"title":"ICF based automation system for spinal cord injuries rehabilitation","authors":"Rehab Mahmoud, Nashwa El-Bendary, Hoda M. O. Mokhtar, A. Hassanien","doi":"10.1109/ICCES.2014.7030955","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030955","url":null,"abstract":"Disabilities, specially the ones caused by injuries of spinal cord, affect both people's behavior and participation in daily activities. Therefore, developing automated systems that monitor and assess the progress of Spinal Cord Injury (SCI) patients represents an accelerated need. In this paper we utilize the framework of the International Classification for Functioning, disability and health (ICF) in order to propose an automatic system for SCI patients progress monitoring and rehabilitation. The ICF is a reference classification system that aims at improving integration of health information and ensuring the collection of accurate health data. The proposed system is divided into three phases; namely (1) ICF code construction, (2) progress monitoring, and (3) progress assessment phases. Comparing the manual expert-based progress assessment to experimental results obtained by the proposed system in this article, an efficiency of 100% has been achieved by the three previously stated phases of the proposed system.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130825131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030924
M. Hassaballah, Mourad Ahmed, H. Alshazly
Face detection as one of the most challenging tasks in computer vision has received a lot of attention in recent decades due to its wide range of use in face based image analysis. In this paper, we propose an efficient approach for face detection that efficiently combines generalized Hough transform within random decision forests framework. In this approach, we train random decision forests that directly maps the image patch appearance to the probabilistic vote about the possible location of the face centroid; the detection hypotheses then correspond to the maxima of the Hough image. The random decision forests construction and prediction abilities depend on setting some parameters, which in turns affects the performance of the method. Therefore, the impact of these parameters that most influence the behavior of the forest for detecting faces is studied through experiments on the widely used CMU+MIT database. Moreover, a comparison with some published methods is presented.
{"title":"Effect of hough forests parameters on face detection performance: An empirical analysis","authors":"M. Hassaballah, Mourad Ahmed, H. Alshazly","doi":"10.1109/ICCES.2014.7030924","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030924","url":null,"abstract":"Face detection as one of the most challenging tasks in computer vision has received a lot of attention in recent decades due to its wide range of use in face based image analysis. In this paper, we propose an efficient approach for face detection that efficiently combines generalized Hough transform within random decision forests framework. In this approach, we train random decision forests that directly maps the image patch appearance to the probabilistic vote about the possible location of the face centroid; the detection hypotheses then correspond to the maxima of the Hough image. The random decision forests construction and prediction abilities depend on setting some parameters, which in turns affects the performance of the method. Therefore, the impact of these parameters that most influence the behavior of the forest for detecting faces is studied through experiments on the widely used CMU+MIT database. Moreover, a comparison with some published methods is presented.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121655003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030933
Mohamed A. Meselhi, Hitham M. Abo Bakr, I. Ziedan, K. Shaalan
Most Named Entity Recognition (NER) systems follow either a rule-based approach or machine learning approach. In this paper, we introduce out attempt at developing a hybrid NER system, which combines the rule-based approach with a machine learning approach in order to obtain the advantages of both approaches and overcomes their problems [1]. The system is able to recognize eight types of named entities including Location, Person, Organization, Date, Time, Price, Measurement and Percent. Experimental results on ANERcorp dataset indicated that our hybrid approach outperforms the rule-based approach and the machine learning approach when they are processed separately. Moreover, our hybrid approach outperforms the state-of-the-art of Arabic NER.
{"title":"Hybrid Named Entity Recognition - Application to Arabic Language","authors":"Mohamed A. Meselhi, Hitham M. Abo Bakr, I. Ziedan, K. Shaalan","doi":"10.1109/ICCES.2014.7030933","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030933","url":null,"abstract":"Most Named Entity Recognition (NER) systems follow either a rule-based approach or machine learning approach. In this paper, we introduce out attempt at developing a hybrid NER system, which combines the rule-based approach with a machine learning approach in order to obtain the advantages of both approaches and overcomes their problems [1]. The system is able to recognize eight types of named entities including Location, Person, Organization, Date, Time, Price, Measurement and Percent. Experimental results on ANERcorp dataset indicated that our hybrid approach outperforms the rule-based approach and the machine learning approach when they are processed separately. Moreover, our hybrid approach outperforms the state-of-the-art of Arabic NER.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"65 41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132380446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030944
Sondos M. Fadl, N. Semary, M. Hadhoud
Digital image tampering becomes a common information falsification trend. Copy-Move forgery is one of the tampering types that are used. Image forgery is the science of detecting image tempering whether with a previous knowledge about the source image (active) or without (passive). In this paper, we propose a method which is efficient and fast for detecting Copy-Move regions even when the copied region was undergone rotation modify in spatial domain. The proposed method accelerates blocking matching strategy by parallel comparing between blocks. Firstly, the image is divided into fixed-size overlapping blocks then features are extracted for each block. k-means clustering technique is used to cluster the blocks into different cluster. The feature vectors of each cluster blocks are lexicographically sorted by radix sort, and then a similarity measure is calculated between each nearby blocks to determine their similarity. The experimental results show that the proposed method can detect the duplicated regions efficiently even when an image was modified by jpeg compression, rotation and smoothing conditions. The proposed system reduced processing time up to 75% of other previous works.
{"title":"Copy-rotate-move forgery detection based on spatial domain","authors":"Sondos M. Fadl, N. Semary, M. Hadhoud","doi":"10.1109/ICCES.2014.7030944","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030944","url":null,"abstract":"Digital image tampering becomes a common information falsification trend. Copy-Move forgery is one of the tampering types that are used. Image forgery is the science of detecting image tempering whether with a previous knowledge about the source image (active) or without (passive). In this paper, we propose a method which is efficient and fast for detecting Copy-Move regions even when the copied region was undergone rotation modify in spatial domain. The proposed method accelerates blocking matching strategy by parallel comparing between blocks. Firstly, the image is divided into fixed-size overlapping blocks then features are extracted for each block. k-means clustering technique is used to cluster the blocks into different cluster. The feature vectors of each cluster blocks are lexicographically sorted by radix sort, and then a similarity measure is calculated between each nearby blocks to determine their similarity. The experimental results show that the proposed method can detect the duplicated regions efficiently even when an image was modified by jpeg compression, rotation and smoothing conditions. The proposed system reduced processing time up to 75% of other previous works.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117240571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030940
S. Elgamel
Empirical mode decomposition (EMD) is used as denoising technique to enhance the signal to noise ratio (SNR) for noisy signals. A new EMD denoising algorithm named EMD iterative altering thresholding and denoising (EMD-IATD) based on the traditional EMD thresholding and denoising (EMD-TD) and inspirited Wavelet denoising technique is developed in this paper. The improved SNR of the new EMD-IATD over the traditional EMD-TD algorithm is assessed using range of simulated and real environments.
{"title":"EMD thresholding and denoising inspired by wavelet technique","authors":"S. Elgamel","doi":"10.1109/ICCES.2014.7030940","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030940","url":null,"abstract":"Empirical mode decomposition (EMD) is used as denoising technique to enhance the signal to noise ratio (SNR) for noisy signals. A new EMD denoising algorithm named EMD iterative altering thresholding and denoising (EMD-IATD) based on the traditional EMD thresholding and denoising (EMD-TD) and inspirited Wavelet denoising technique is developed in this paper. The improved SNR of the new EMD-IATD over the traditional EMD-TD algorithm is assessed using range of simulated and real environments.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115213135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030962
DiaaEldin M. Abdalla, A. M. Zaki, Ayman M. Bahaa-Eldin
Several computing systems that use decimal number calculations suffer from the accumulation and propagation of errors. Decimal numbers are represented using specific length floating point formats and hence there will always be a truncation of extra fraction bits causing errors. Several solutions had been proposed for such a problem. Among those accurate calculation systems was the usage of vectors of floating point numbers to represent decimal values with very large accuracy, known as Multi-Number System (MN). Unfortunately, MN calculations are time consuming and are not suitable for real time applications. Several attempts for special architectures had been proposed to speed up those calculations. In this work, the Single Instruction Multiple Data (SIMD) paradigm found in modern CPUs is exploited to accelerate the MN calculations. The basic arithmetic operation algorithms had been modified to utilize the SIMD architecture and a new Square representation of operands had been proposed, this representation was introduced because the MN operations are sequential and iterative, and thus we can't apply the SIMD parallel instructions directly. The proposed architecture has an execution time that is 35% of the original MN execution time for the division, which is the most time consuming operation while preserving the same accuracy.
{"title":"Acceleration of accurate floating point operations using SIMD","authors":"DiaaEldin M. Abdalla, A. M. Zaki, Ayman M. Bahaa-Eldin","doi":"10.1109/ICCES.2014.7030962","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030962","url":null,"abstract":"Several computing systems that use decimal number calculations suffer from the accumulation and propagation of errors. Decimal numbers are represented using specific length floating point formats and hence there will always be a truncation of extra fraction bits causing errors. Several solutions had been proposed for such a problem. Among those accurate calculation systems was the usage of vectors of floating point numbers to represent decimal values with very large accuracy, known as Multi-Number System (MN). Unfortunately, MN calculations are time consuming and are not suitable for real time applications. Several attempts for special architectures had been proposed to speed up those calculations. In this work, the Single Instruction Multiple Data (SIMD) paradigm found in modern CPUs is exploited to accelerate the MN calculations. The basic arithmetic operation algorithms had been modified to utilize the SIMD architecture and a new Square representation of operands had been proposed, this representation was introduced because the MN operations are sequential and iterative, and thus we can't apply the SIMD parallel instructions directly. The proposed architecture has an execution time that is 35% of the original MN execution time for the division, which is the most time consuming operation while preserving the same accuracy.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030943
Doaa A. Altantawy, Marwa Obbaya, S. Kishk
In this paper, a new segment-based stereo matching algorithm (FastNL_Gc) is introduced. FastNL_Gc depends locally on the introduced Non-Local-Mean (NL-Mean) approach that provides a fast denoising technique with an edge preserving property in the initial disparity map estimation and globally on graph cuts for the disparity plane assignment using a new energy formulation of the stereo problem in segment domain. The methodology is tested on Middlebury stereo benchmark and the results indicate that the proposed FastNL_Gc method is compatible with the current state-of-the-art stereo matching algorithms in dealing with the conventionally difficult areas, such as textureless regions, disparity discontinuous boundaries and occluded portions.
{"title":"A fast non-local based stereo matching algorithm using graph cuts","authors":"Doaa A. Altantawy, Marwa Obbaya, S. Kishk","doi":"10.1109/ICCES.2014.7030943","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030943","url":null,"abstract":"In this paper, a new segment-based stereo matching algorithm (FastNL_Gc) is introduced. FastNL_Gc depends locally on the introduced Non-Local-Mean (NL-Mean) approach that provides a fast denoising technique with an edge preserving property in the initial disparity map estimation and globally on graph cuts for the disparity plane assignment using a new energy formulation of the stereo problem in segment domain. The methodology is tested on Middlebury stereo benchmark and the results indicate that the proposed FastNL_Gc method is compatible with the current state-of-the-art stereo matching algorithms in dealing with the conventionally difficult areas, such as textureless regions, disparity discontinuous boundaries and occluded portions.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129233278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：