Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945827
Adil Enaanai, Aziz Sdigui Doukkali, Ichrak Saif, Hicham Moutachaouik, M. Hain
Relevance is one of the most interesting topics in the information retrieval domain. In this paper, we introduce another method of relevance calculation. We propose to use the implicit opinion of users to calculate relevance. The Implicit judgment of users is injected to the documents by calculating different kinds of weighting. These latter touch several criteria like as user's weight in the query's words, user's profile, user's interest, document's content and the document popularity. In this method, each user is an active element of the system, he searches documents and he makes treatments to provide relevant information to other users in the Network. This is similar as the peer-to-peer systems; unlike that, an element (user) have to manage automatically his data by creating a short view model of his most visited documents, and calculates his relative relevance about each one. The relative relevance is variable according each user, so the final relevance is calculated by the averaging of the elementary relevance of all users. Hence, the name of collaborative relevance.
{"title":"The collaborative relevance in the distributed information retrieval","authors":"Adil Enaanai, Aziz Sdigui Doukkali, Ichrak Saif, Hicham Moutachaouik, M. Hain","doi":"10.1109/AICCSA.2016.7945827","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945827","url":null,"abstract":"Relevance is one of the most interesting topics in the information retrieval domain. In this paper, we introduce another method of relevance calculation. We propose to use the implicit opinion of users to calculate relevance. The Implicit judgment of users is injected to the documents by calculating different kinds of weighting. These latter touch several criteria like as user's weight in the query's words, user's profile, user's interest, document's content and the document popularity. In this method, each user is an active element of the system, he searches documents and he makes treatments to provide relevant information to other users in the Network. This is similar as the peer-to-peer systems; unlike that, an element (user) have to manage automatically his data by creating a short view model of his most visited documents, and calculates his relative relevance about each one. The relative relevance is variable according each user, so the final relevance is calculated by the averaging of the elementary relevance of all users. Hence, the name of collaborative relevance.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115028580","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945813
L. Tawalbeh, T. Al-Somani
There are many recent revolutionary advances in information technology that include: wireless communication, the spread of mobile devices, and the Internet-of-Things (IoT). IoT will have an important role in connecting almost everything (mobile devices, cameras, home appliances, healthcare devices, military equipments, …, etc) to the Internet via different communication technologies such as Wi-Fi. This connection will have impact on many sectors of our life such as industry, economy, social life, and ICT sector. Moreover, there will be huge amounts of data (including financial and medical records for example) transmitted between those devices and the non-secure Internet. Some of these data might be very sensitive and their privacy and security must not be compromised. Here comes the need for Cryptographic systems to protect the vital data. There are many hardware and software implementations for the symmetric and asymmetric cryptographic algorithms such as AES, Elliptic Curve Cryptography, and RSA. And since we are talking about protecting physical devices connected to the Internet, we think that the hardware cryptosystems are more useful to be used in this case. In this paper, we introduce the IoT concept, applications, and challenges facing IoT. Then, we present the recent timing and fault Side Channel Attacks on cryptosystem implementations for the most secure encryption algorithms (AES, ECC, and RSA). Also, the countermeasures to protect these cryptosystems from such attacks are also presented.
{"title":"More secure Internet of Things using robust encryption algorithms against side channel attacks","authors":"L. Tawalbeh, T. Al-Somani","doi":"10.1109/AICCSA.2016.7945813","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945813","url":null,"abstract":"There are many recent revolutionary advances in information technology that include: wireless communication, the spread of mobile devices, and the Internet-of-Things (IoT). IoT will have an important role in connecting almost everything (mobile devices, cameras, home appliances, healthcare devices, military equipments, …, etc) to the Internet via different communication technologies such as Wi-Fi. This connection will have impact on many sectors of our life such as industry, economy, social life, and ICT sector. Moreover, there will be huge amounts of data (including financial and medical records for example) transmitted between those devices and the non-secure Internet. Some of these data might be very sensitive and their privacy and security must not be compromised. Here comes the need for Cryptographic systems to protect the vital data. There are many hardware and software implementations for the symmetric and asymmetric cryptographic algorithms such as AES, Elliptic Curve Cryptography, and RSA. And since we are talking about protecting physical devices connected to the Internet, we think that the hardware cryptosystems are more useful to be used in this case. In this paper, we introduce the IoT concept, applications, and challenges facing IoT. Then, we present the recent timing and fault Side Channel Attacks on cryptosystem implementations for the most secure encryption algorithms (AES, ECC, and RSA). Also, the countermeasures to protect these cryptosystems from such attacks are also presented.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114163999","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945726
Hiba Ramadan, H. Tairi
This paper presents a new algorithm for automatic segmentation of moving objects in video based on spatiotemporal saliency and laplacian coordinates (LC). Our algorithm exploits the saliency and the motion information to build a spatio-temporal saliency map, used to extract a moving region of interest (MRI). This region is used to provide automatically the seeds for the segmentation of the moving object using LC. Experiments show a good performance of our algorithm for moving objects segmentation in video without a user interaction, especially on Segtrack dataset.
{"title":"Moving object segmentation in video using spatiotemporal saliency and laplacian coordinates","authors":"Hiba Ramadan, H. Tairi","doi":"10.1109/AICCSA.2016.7945726","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945726","url":null,"abstract":"This paper presents a new algorithm for automatic segmentation of moving objects in video based on spatiotemporal saliency and laplacian coordinates (LC). Our algorithm exploits the saliency and the motion information to build a spatio-temporal saliency map, used to extract a moving region of interest (MRI). This region is used to provide automatically the seeds for the segmentation of the moving object using LC. Experiments show a good performance of our algorithm for moving objects segmentation in video without a user interaction, especially on Segtrack dataset.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"58 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116228625","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945637
Clícia Pinto, Marcos E. Barreto, M. Boratto
The increasing need for computing power today justifies the continuous search for techniques that decrease the time to answer usual computational problems. To take advantage of new hybrid parallel architectures composed by multithreading and multiprocessor hardware, our current efforts involve the design and validation of highly parallel algorithms that efficently explore the characteristics of such architectures. In this paper, we propose an automatic tuning methodology to easily exploit multicore, multi-GPU and coprocessor systems. We present an optimization of an algorithm for solving triangular systems (TRSM), based on block decomposition and asynchronous task assignment, and discuss some results.
{"title":"Auto-tuning TRSM with an asynchronous task assignment model on multicore, multi-GPU and coprocessor systems","authors":"Clícia Pinto, Marcos E. Barreto, M. Boratto","doi":"10.1109/AICCSA.2016.7945637","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945637","url":null,"abstract":"The increasing need for computing power today justifies the continuous search for techniques that decrease the time to answer usual computational problems. To take advantage of new hybrid parallel architectures composed by multithreading and multiprocessor hardware, our current efforts involve the design and validation of highly parallel algorithms that efficently explore the characteristics of such architectures. In this paper, we propose an automatic tuning methodology to easily exploit multicore, multi-GPU and coprocessor systems. We present an optimization of an algorithm for solving triangular systems (TRSM), based on block decomposition and asynchronous task assignment, and discuss some results.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123071645","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945616
Zaki Brahmi, Sahar Mili, Rihab Derouiche
Massive data applications such as E-science applications are characterized by complex treatments on large amounts of data which need to be stored in distributed data centers. In fact, when one task needs several datasets from different data centers, moving these data may cost a lot of time and cause energy's high consumption. Moreover, when the number of the data centers involved in the execution of tasks is high, the total data movement and the execution time increase dramatically and become a bottleneck, since the data centers have a limited bandwidth. Thus, we need a good data placement strategy to minimise the data movement between data centers and reduce the energy consumed. Indeed, many researches are concerned with data placement strategy that distributes data in ways that are advantageous for application execution. In this paper, our data placement strategy aims at grouping the maximum of data and of tasks in a minimal number of data centers. It is based on the Formal Concept Analysis approach (FCA) because its notion of a concept respects our idea since it faithfully represents a group of tasks and data that are required for their execution. It is based on four steps: 1) Hierarchical organization of tasks using Formal Concepts Analysis approach, 2) Selection of candidate concepts, 3) Assigning data in the appropriate data centers and 4) Data replication. Simulations show that our strategy can effectively reduce the data movement and the average query spans compared to the genetic approach.
{"title":"Data placement strategy for massive data applications based on FCA approach","authors":"Zaki Brahmi, Sahar Mili, Rihab Derouiche","doi":"10.1109/AICCSA.2016.7945616","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945616","url":null,"abstract":"Massive data applications such as E-science applications are characterized by complex treatments on large amounts of data which need to be stored in distributed data centers. In fact, when one task needs several datasets from different data centers, moving these data may cost a lot of time and cause energy's high consumption. Moreover, when the number of the data centers involved in the execution of tasks is high, the total data movement and the execution time increase dramatically and become a bottleneck, since the data centers have a limited bandwidth. Thus, we need a good data placement strategy to minimise the data movement between data centers and reduce the energy consumed. Indeed, many researches are concerned with data placement strategy that distributes data in ways that are advantageous for application execution. In this paper, our data placement strategy aims at grouping the maximum of data and of tasks in a minimal number of data centers. It is based on the Formal Concept Analysis approach (FCA) because its notion of a concept respects our idea since it faithfully represents a group of tasks and data that are required for their execution. It is based on four steps: 1) Hierarchical organization of tasks using Formal Concepts Analysis approach, 2) Selection of candidate concepts, 3) Assigning data in the appropriate data centers and 4) Data replication. Simulations show that our strategy can effectively reduce the data movement and the average query spans compared to the genetic approach.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123221622","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945626
Abir Gorrab, Ferihane Kboubi, H. Ghézala, B. L. Grand
The emergence of social networks and the communication facilities they offer have generated an enormous informational mass. This social content is used in several research and industrial works and has had a great impact in different processes. In this paper, we present an overview of social information use in Information Retrieval (IR) and Recommendation systems. We first describe several user profile models using social information. A special attention is given to the following points: the analysis of the different user profiling models incorporating social content in Information Retrieval (IR) and in social recommendation methods. We distinguish between the models using social signals and relations, and the models using temporal information. We also present current and future challenges and research directions to enhance IR and recommendation process. We then describe our proposed model of social polarized and temporal user profile building and use in social recommendation context. Our proposal tries to address open challenges and establish a new model of user profile that fits information needs in recommender systems.
{"title":"Towards a dynamic and polarity-aware social user profile modeling","authors":"Abir Gorrab, Ferihane Kboubi, H. Ghézala, B. L. Grand","doi":"10.1109/AICCSA.2016.7945626","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945626","url":null,"abstract":"The emergence of social networks and the communication facilities they offer have generated an enormous informational mass. This social content is used in several research and industrial works and has had a great impact in different processes. In this paper, we present an overview of social information use in Information Retrieval (IR) and Recommendation systems. We first describe several user profile models using social information. A special attention is given to the following points: the analysis of the different user profiling models incorporating social content in Information Retrieval (IR) and in social recommendation methods. We distinguish between the models using social signals and relations, and the models using temporal information. We also present current and future challenges and research directions to enhance IR and recommendation process. We then describe our proposed model of social polarized and temporal user profile building and use in social recommendation context. Our proposal tries to address open challenges and establish a new model of user profile that fits information needs in recommender systems.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122030605","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945646
Kaoru Uchida
Artifact-metrics technology is gaining more research interests, along with the expansion of its applications. One of its challenges is an efficient image search, in which a match is to be identified in a large multi-scale image database with a given, possibly distorted, query image having unknown location, orientation, and scale. To approach this computational efficiency problem of image database search, we conducted a preliminary feasibility study focused specifically on aerial photo search problem. We propose a highly efficient image search system to find a match in the multi-layered database of images with multiple magnitudes. The system first pre-selects matching candidates based on comparison results of image profiles such as frequency spectra, so that the following matching stages focus on the appropriate scale layer to accelerate search. Then in the coarse matching stage, the down-sampled query image is compared with images in a lower-magnitude layer using a scale-invariant matcher based on local feature descriptors. This paper outlines our interim proposed approach and discusses its feasibility and performance based on the experimental results from our ongoing research work.
{"title":"Efficient image search system with multi-scale database using profile-based pre-selection and coarse matching","authors":"Kaoru Uchida","doi":"10.1109/AICCSA.2016.7945646","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945646","url":null,"abstract":"Artifact-metrics technology is gaining more research interests, along with the expansion of its applications. One of its challenges is an efficient image search, in which a match is to be identified in a large multi-scale image database with a given, possibly distorted, query image having unknown location, orientation, and scale. To approach this computational efficiency problem of image database search, we conducted a preliminary feasibility study focused specifically on aerial photo search problem. We propose a highly efficient image search system to find a match in the multi-layered database of images with multiple magnitudes. The system first pre-selects matching candidates based on comparison results of image profiles such as frequency spectra, so that the following matching stages focus on the appropriate scale layer to accelerate search. Then in the coarse matching stage, the down-sampled query image is compared with images in a lower-magnitude layer using a scale-invariant matcher based on local feature descriptors. This paper outlines our interim proposed approach and discusses its feasibility and performance based on the experimental results from our ongoing research work.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122521483","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945784
S. Guellouz, Adel Benzina, M. Khalgui, Georg Frey
This paper presents an extension to the IEC 61499 standard called Reconfigurable Function Block. The major goal is to optimize the design of a network of Function Blocks by encapsulating several reconfiguration scenarios in one function block. We define the events triggering the reconfiguration and we attach a probability to each event to express its uncertainty. In order to verify the system and to evaluate its performances, we model it with a class of Petri nets. The proposed approach is applied to a medical platform BROS as a case study throughout a developed software tool called ZiZo v3.
{"title":"Reconfigurable function blocks: Extension to the standard IEC 61499","authors":"S. Guellouz, Adel Benzina, M. Khalgui, Georg Frey","doi":"10.1109/AICCSA.2016.7945784","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945784","url":null,"abstract":"This paper presents an extension to the IEC 61499 standard called Reconfigurable Function Block. The major goal is to optimize the design of a network of Function Blocks by encapsulating several reconfiguration scenarios in one function block. We define the events triggering the reconfiguration and we attach a probability to each event to express its uncertainty. In order to verify the system and to evaluate its performances, we model it with a class of Petri nets. The proposed approach is applied to a medical platform BROS as a case study throughout a developed software tool called ZiZo v3.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123860546","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945622
Hassanin M. Al-Barhamtoshy, Maher Khemakhem, K. Jambi, F. Essa, A. Fattouh, A. Al-Ghamdi
Document Analysis and Recognition (DAR) has two main objectives, first the analysis of the physical structure of the input image of the document, which should lead to the correct identification of the corresponding different homogeneous components and their boundaries in terms of XY coordinates. Second, each of these homogeneous components should be recognized in such a way that, if it is a text image, consequently this image should be recognized and translated into an intelligible text. DAR remains one of the most challenging topics in pattern recognition. Indeed, despite the diversity of the proposed approaches, techniques and methods, results remain very weak and away from expectations especially for several categories of documents such as complex, low quality, handwritten and historical documents. The complex structure and/or morphology of such documents are behind the weakness of results of these proposed approaches, techniques and methods. One of the challenging problems related to this topic is the creation of standard datasets that can be used by all stakeholders of this topic such as system developers, expert evaluators, and users. In addition, another challenging problem is how one could take advantages of all existing datasets that unfortunately are dispersed around the world without knowing, most of the times, any information about their locations and the way to reach them. As an attempt to solve the two mentioned above problems, we propose in this paper a Universal Datasets Repository for Document Analysis and Recognition (UMDAR) that has, in fact, a twofold advantage. First, it can help dataset creators to standardize their datasets and making them accessible to the research community once published on the proposed repository. Second, it can be used as a central which bridges in a smart manner between datasets and all DAR stakeholders.
文档分析与识别(Document Analysis and Recognition, DAR)有两个主要目标，首先是对文档输入图像的物理结构进行分析，从而正确识别相应的不同同构分量及其在XY坐标下的边界。其次，每一个同质成分都应该以这样一种方式被识别，如果它是一个文本图像，那么这个图像应该被识别并翻译成可理解的文本。DAR仍然是模式识别中最具挑战性的课题之一。事实上，尽管所提议的方法、技术和方法多种多样，但结果仍然非常薄弱，与预期相差甚远，特别是对于复杂、低质量、手写和历史文件等几类文件。这些文件的复杂结构和/或形态是这些提出的方法、技术和方法的结果薄弱的原因。与该主题相关的一个具有挑战性的问题是创建可由该主题的所有利益相关者(如系统开发人员、专家评估人员和用户)使用的标准数据集。此外，另一个具有挑战性的问题是，人们如何利用所有现有的数据集，不幸的是，这些数据集分散在世界各地，大多数时候，人们不知道它们的位置和到达它们的方式的任何信息。作为解决上述两个问题的尝试，我们在本文中提出了一个用于文档分析和识别的通用数据集存储库(UMDAR)，它实际上具有双重优势。首先，它可以帮助数据集创建者标准化他们的数据集，并且一旦在建议的存储库上发布，研究社区就可以访问它们。其次，它可以作为一个中心，以智能的方式在数据集和所有DAR利益相关者之间架起桥梁。
{"title":"Universal metadata repository for document analysis and recognition","authors":"Hassanin M. Al-Barhamtoshy, Maher Khemakhem, K. Jambi, F. Essa, A. Fattouh, A. Al-Ghamdi","doi":"10.1109/AICCSA.2016.7945622","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945622","url":null,"abstract":"Document Analysis and Recognition (DAR) has two main objectives, first the analysis of the physical structure of the input image of the document, which should lead to the correct identification of the corresponding different homogeneous components and their boundaries in terms of XY coordinates. Second, each of these homogeneous components should be recognized in such a way that, if it is a text image, consequently this image should be recognized and translated into an intelligible text. DAR remains one of the most challenging topics in pattern recognition. Indeed, despite the diversity of the proposed approaches, techniques and methods, results remain very weak and away from expectations especially for several categories of documents such as complex, low quality, handwritten and historical documents. The complex structure and/or morphology of such documents are behind the weakness of results of these proposed approaches, techniques and methods. One of the challenging problems related to this topic is the creation of standard datasets that can be used by all stakeholders of this topic such as system developers, expert evaluators, and users. In addition, another challenging problem is how one could take advantages of all existing datasets that unfortunately are dispersed around the world without knowing, most of the times, any information about their locations and the way to reach them. As an attempt to solve the two mentioned above problems, we propose in this paper a Universal Datasets Repository for Document Analysis and Recognition (UMDAR) that has, in fact, a twofold advantage. First, it can help dataset creators to standardize their datasets and making them accessible to the research community once published on the proposed repository. Second, it can be used as a central which bridges in a smart manner between datasets and all DAR stakeholders.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124147011","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 : 2016-11-01DOI: 10.1109/AICCSA.2016.7945773
M. AMROUCH, M. Rabi, D. Mammass
In this paper we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition.
{"title":"An improved Arabic handwritten recognition system using embedded training based on HMMs","authors":"M. AMROUCH, M. Rabi, D. Mammass","doi":"10.1109/AICCSA.2016.7945773","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945773","url":null,"abstract":"In this paper we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125381388","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：