Pub Date : 2016-04-05DOI: 10.1109/IACS.2016.7476093
A. Haque, Shantanu Kode, A. Razaque, Muder Almiani
Prior to the creation of the internet, data security was the focal point when one wanted to keep electronic data secure from unauthorized agents for whom wanted to view, create, alter, and/or destroy various parts of an electronic file. Mobile security is still at the forefront of cyber warfare however, data security is progressively gaining ground and can arguably be the front runner. Since almost every device is connected to a network nowadays data security awareness has been on a drastic rise. And this has caused both the customers and manufacturers a severe concern. Research has and is currently being conducted to determine new ways to detect if malicious actions are taking place, how to discontinue said actions, and ways to prevent future malicious actions from occurring. Though manufacturers are implementing industry standard security measures, customers are not comfortable using them as they are not user friendly. So it is necessary to implement a security protocol that is well-secure, smart and can act according to the customers' needs. The main goal of this paper is not to find a new encryption protocol rather to implement an existing security protocol in an efficient way, so that customers can easily use it. In this paper we are introducing a context aware system, "ConSec", which encrypts and decrypts the memory according the users' usage.
{"title":"ConSec: An encryption policy for context aware security applications","authors":"A. Haque, Shantanu Kode, A. Razaque, Muder Almiani","doi":"10.1109/IACS.2016.7476093","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476093","url":null,"abstract":"Prior to the creation of the internet, data security was the focal point when one wanted to keep electronic data secure from unauthorized agents for whom wanted to view, create, alter, and/or destroy various parts of an electronic file. Mobile security is still at the forefront of cyber warfare however, data security is progressively gaining ground and can arguably be the front runner. Since almost every device is connected to a network nowadays data security awareness has been on a drastic rise. And this has caused both the customers and manufacturers a severe concern. Research has and is currently being conducted to determine new ways to detect if malicious actions are taking place, how to discontinue said actions, and ways to prevent future malicious actions from occurring. Though manufacturers are implementing industry standard security measures, customers are not comfortable using them as they are not user friendly. So it is necessary to implement a security protocol that is well-secure, smart and can act according to the customers' needs. The main goal of this paper is not to find a new encryption protocol rather to implement an existing security protocol in an efficient way, so that customers can easily use it. In this paper we are introducing a context aware system, \"ConSec\", which encrypts and decrypts the memory according the users' usage.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"145 1","pages":"96-101"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86212477","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476103
Dajin Wang
We propose to use a 2-dimensional (2-D for short) spatial Poisson process to model a WSN with randomly deployed sensors, and use the model to analyze a scheme that subdivides the clusters of a WSN to achieve an overall power savings. We assume no knowledge of how the sensors are spread in the sensing area, and hence need a statistical process to describe the distribution of all sensors. Assuming the 2-D spatial Poisson distribution, a comprehensive analysis is performed to estimate the power savings brought about by the proposed subdivision. Using hexagon as the shape of the cluster, the analysis shows that the subdivision scheme can yield significant savings in overall power consumption of sensors in the cluster.
{"title":"Cluster subdivision towards power savings for randomly deployed WSNs — An analysis using 2-D spatial poisson process","authors":"Dajin Wang","doi":"10.1109/IACS.2016.7476103","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476103","url":null,"abstract":"We propose to use a 2-dimensional (2-D for short) spatial Poisson process to model a WSN with randomly deployed sensors, and use the model to analyze a scheme that subdivides the clusters of a WSN to achieve an overall power savings. We assume no knowledge of how the sensors are spread in the sensing area, and hence need a statistical process to describe the distribution of all sensors. Assuming the 2-D spatial Poisson distribution, a comprehensive analysis is performed to estimate the power savings brought about by the proposed subdivision. Using hexagon as the shape of the cluster, the analysis shows that the subdivision scheme can yield significant savings in overall power consumption of sensors in the cluster.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"39 1","pages":"156-161"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79415779","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476089
Mohammed Tag Elsir Awad Elsoufi, Xiong Ying, Wang Jun, Tang Bin
A new method of Modulation Recognition of communication signals is proposed based on Clustering Validity Indices. These indices provide a good basis for key feature extraction. To distinguish different modulation schemes, a Fuzzy C-mean (FCM) clustering is used to get the membership matrix of different clusters. Then, a clustering validity measure is applied to extract features. To enhance clustering results at low SNR, a neural network with a conjugate gradient learning algorithm is utilized. Fletcher-Reeves learning approach enhances the recognition rate and widely improves the speed and rate of convergence. Simulation results show the validity of proposed approach compared with other approaches using only clustering or using back propagation neural networks. Misclassification rate is less for low order MQAM signals. This algorithm is applicable in high order MQAM signals. In Non-cooperative Communications, the modulated signal parameters are unknown. Some Modulation Recognition algorithms rely on estimating these parameters first, then applying recognition algorithms. Proposed algorithm doesn't need any prior information to achieve modulation recognition.
{"title":"Fletcher-Reeves learning approach for high order MQAM signal modulation recognition","authors":"Mohammed Tag Elsir Awad Elsoufi, Xiong Ying, Wang Jun, Tang Bin","doi":"10.1109/IACS.2016.7476089","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476089","url":null,"abstract":"A new method of Modulation Recognition of communication signals is proposed based on Clustering Validity Indices. These indices provide a good basis for key feature extraction. To distinguish different modulation schemes, a Fuzzy C-mean (FCM) clustering is used to get the membership matrix of different clusters. Then, a clustering validity measure is applied to extract features. To enhance clustering results at low SNR, a neural network with a conjugate gradient learning algorithm is utilized. Fletcher-Reeves learning approach enhances the recognition rate and widely improves the speed and rate of convergence. Simulation results show the validity of proposed approach compared with other approaches using only clustering or using back propagation neural networks. Misclassification rate is less for low order MQAM signals. This algorithm is applicable in high order MQAM signals. In Non-cooperative Communications, the modulated signal parameters are unknown. Some Modulation Recognition algorithms rely on estimating these parameters first, then applying recognition algorithms. Proposed algorithm doesn't need any prior information to achieve modulation recognition.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"19 1","pages":"74-79"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85936532","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476105
Meng Sun, Xinchang Zhang, Lu Wang, Huiling Shi, Wei Zhang
Multiple Multicast Tree (MMT) orchestration optimizes the share of network resources among coexisting MMT. The software defined networking (SDN) technique can conveniently monitor the network traffic and quickly install and change the routes. Based on the SDN environment, considering the dynamic change of the practical network traffic monitored by controller, we model the MMT optimization as a problem with the objective of minimizing the total path length subject to the constraints of bandwidth and MMT's Edge Modification Times (EMT). We propose a two-stage solution to solve the problem. In the first stage, we only consider the optimization objective and the bandwidth constraint to modify the initial MMT and obtain a suboptimal MMT. In the second stage, we continue to modify the suboptimal MMT according to the EMT obtained in the first stage. Experimental results demonstrate that our algorithm have the better performance in terms of the total path length and EMT compared with the existing algorithm of reconstructing a new MMT.
{"title":"A multiple multicast tree optimization solution based on software defined network","authors":"Meng Sun, Xinchang Zhang, Lu Wang, Huiling Shi, Wei Zhang","doi":"10.1109/IACS.2016.7476105","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476105","url":null,"abstract":"Multiple Multicast Tree (MMT) orchestration optimizes the share of network resources among coexisting MMT. The software defined networking (SDN) technique can conveniently monitor the network traffic and quickly install and change the routes. Based on the SDN environment, considering the dynamic change of the practical network traffic monitored by controller, we model the MMT optimization as a problem with the objective of minimizing the total path length subject to the constraints of bandwidth and MMT's Edge Modification Times (EMT). We propose a two-stage solution to solve the problem. In the first stage, we only consider the optimization objective and the bandwidth constraint to modify the initial MMT and obtain a suboptimal MMT. In the second stage, we continue to modify the suboptimal MMT according to the EMT obtained in the first stage. Experimental results demonstrate that our algorithm have the better performance in terms of the total path length and EMT compared with the existing algorithm of reconstructing a new MMT.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"45 1","pages":"168-173"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88050068","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476064
Yahya M. Tashtoush, Ala Darabseh, Huda Al-Sarhan
Nowadays, most people are using the Internet to achieve their daily needs. One of these needs is the ability to access the government websites, to make the necessary transactions and procedures via the internet. Maintaining the transaction over the web arises the needs of building an available and accessible website for all users, even those with special needs. In this paper, we evaluate the accessibility for a set of Arabian E-government websites with two versions, English and Arabic, by using a set of automated tools. The results obtained from the two versions are compared to decide which is the best government website that achieved the least number of errors. The selected accessibility tools are supporting the Web Contents Accessibility Guidelines (WCAG) version 2.0 as an update of the previous version WCAG 1.0.
{"title":"The Arabian E-government websites accessibility: A case study","authors":"Yahya M. Tashtoush, Ala Darabseh, Huda Al-Sarhan","doi":"10.1109/IACS.2016.7476064","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476064","url":null,"abstract":"Nowadays, most people are using the Internet to achieve their daily needs. One of these needs is the ability to access the government websites, to make the necessary transactions and procedures via the internet. Maintaining the transaction over the web arises the needs of building an available and accessible website for all users, even those with special needs. In this paper, we evaluate the accessibility for a set of Arabian E-government websites with two versions, English and Arabic, by using a set of automated tools. The results obtained from the two versions are compared to decide which is the best government website that achieved the least number of errors. The selected accessibility tools are supporting the Web Contents Accessibility Guidelines (WCAG) version 2.0 as an update of the previous version WCAG 1.0.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"16 1","pages":"276-281"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88521971","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476121
Muhammad Syafiq Bin Ab Malek, Mohd Anuaruddin bin Ahmadon, S. Yamaguchi, B. Gupta
Computer-based test (CBT for short) has become a new form of delivering test. This causes a challenge of unethical conduct during examinations such as cheating and accessing test data before the examination. Model checking is a promising approach to analyse the behavior and correctness of secured system. However, if a system has a large-scale behavior, we cannot apply model checking because of state space explosion. In this paper, we gave a security considerations of CBT and proposed a Petri net-based framework of parallel model checking with a Petri net splitting procedure. The proposed framework is useful to reduce the size of the net, thereby increases the applicability of model checking to security protocol verification. It allows us to analyse the property of each splitted nets simultaneously. We illustrated the proposed framework with a product called as E-monitoring with biometric authentication scheme as an application example.
{"title":"Implementation of parallel model checking for computer-based test security design","authors":"Muhammad Syafiq Bin Ab Malek, Mohd Anuaruddin bin Ahmadon, S. Yamaguchi, B. Gupta","doi":"10.1109/IACS.2016.7476121","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476121","url":null,"abstract":"Computer-based test (CBT for short) has become a new form of delivering test. This causes a challenge of unethical conduct during examinations such as cheating and accessing test data before the examination. Model checking is a promising approach to analyse the behavior and correctness of secured system. However, if a system has a large-scale behavior, we cannot apply model checking because of state space explosion. In this paper, we gave a security considerations of CBT and proposed a Petri net-based framework of parallel model checking with a Petri net splitting procedure. The proposed framework is useful to reduce the size of the net, thereby increases the applicability of model checking to security protocol verification. It allows us to analyse the property of each splitted nets simultaneously. We illustrated the proposed framework with a product called as E-monitoring with biometric authentication scheme as an application example.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"28 1","pages":"258-263"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74283791","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476104
Walaa Abd Ellatief, O. Younes, Hatem Ahmed, Mohee Hadhoud
Wireless sensor networks are characterized with large number of nodes deployed randomly over the network area. In many real applications, random deployment process produce non-uniform distribution of nodes. This means that there is no constant density over any unit area and therefore no constant number of neighbours for each node. With non-uniform distribution, network appear as if it divided to a set of sub-regions each with a different density level. Density in these sub-regions ranging from high density areas, medium, and others are empty areas. For this reason, topology extraction techniques is needed for sensors which helps to discover the layout of the network around them. It assists to figure the skeleton of the whole network. It can help in the discovery of holes and used to solve this problem as a guide for redeployment process to produce a full covered area. Our aim is to define a simple distributed technique that allow all sensors in the network to share information between them and extract the layout of the network. This is done by defining the closed boundary of sub-regions of different density levels which form the network. Previous techniques used for topology extraction need networks with very high density and deal with special deployment figures. Many of them requires uniform distribution which is not always applicable in real situations. Our proposed technique is simple, use lower density than other previously proposed techniques, and do not need special deployment figures.
{"title":"Transmission range adaption technique for non-uniform wireless sensor network topology extraction","authors":"Walaa Abd Ellatief, O. Younes, Hatem Ahmed, Mohee Hadhoud","doi":"10.1109/IACS.2016.7476104","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476104","url":null,"abstract":"Wireless sensor networks are characterized with large number of nodes deployed randomly over the network area. In many real applications, random deployment process produce non-uniform distribution of nodes. This means that there is no constant density over any unit area and therefore no constant number of neighbours for each node. With non-uniform distribution, network appear as if it divided to a set of sub-regions each with a different density level. Density in these sub-regions ranging from high density areas, medium, and others are empty areas. For this reason, topology extraction techniques is needed for sensors which helps to discover the layout of the network around them. It assists to figure the skeleton of the whole network. It can help in the discovery of holes and used to solve this problem as a guide for redeployment process to produce a full covered area. Our aim is to define a simple distributed technique that allow all sensors in the network to share information between them and extract the layout of the network. This is done by defining the closed boundary of sub-regions of different density levels which form the network. Previous techniques used for topology extraction need networks with very high density and deal with special deployment figures. Many of them requires uniform distribution which is not always applicable in real situations. Our proposed technique is simple, use lower density than other previously proposed techniques, and do not need special deployment figures.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"17 1","pages":"162-167"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83065505","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476118
M. H. Aldosari, Ahmad A. Al-Daraiseh
CAPTCHA (Completely Automated Public Turing Test to tell Computers and Humans Apart) is a kind of test which is commonly used by different websites on the Internet to differentiate between humans and automated bots. Most websites require the user to pass the CAPTCHA before signing up or filling out most forms. CAPTCHA today is even used on some mobile applications to provide a higher security level that can protect websites and mobile applications against malicious attacks by automated bots and spammers. In this paper, we present an advanced CAPTCHA technique; our technique essentially relies on employing the human recognition ability, which is not available in automated bots or machines, through leveraging the handwriting characteristics in designing CAPTCHA. Moreover, the proposed CAPTCHA technique adopts handwritten characters of four different languages (English, Arabic, Spanish, and French) to generate handwritten multilingual CAPTCHA text using characters from the four adopted languages. Furthermore, the initial experiments' results have shown a promising security level that the proposed CAPTCHA technique can provide.
{"title":"Strong multilingual CAPTCHA based on handwritten characters","authors":"M. H. Aldosari, Ahmad A. Al-Daraiseh","doi":"10.1109/IACS.2016.7476118","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476118","url":null,"abstract":"CAPTCHA (Completely Automated Public Turing Test to tell Computers and Humans Apart) is a kind of test which is commonly used by different websites on the Internet to differentiate between humans and automated bots. Most websites require the user to pass the CAPTCHA before signing up or filling out most forms. CAPTCHA today is even used on some mobile applications to provide a higher security level that can protect websites and mobile applications against malicious attacks by automated bots and spammers. In this paper, we present an advanced CAPTCHA technique; our technique essentially relies on employing the human recognition ability, which is not available in automated bots or machines, through leveraging the handwriting characteristics in designing CAPTCHA. Moreover, the proposed CAPTCHA technique adopts handwritten characters of four different languages (English, Arabic, Spanish, and French) to generate handwritten multilingual CAPTCHA text using characters from the four adopted languages. Furthermore, the initial experiments' results have shown a promising security level that the proposed CAPTCHA technique can provide.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"23 1","pages":"239-245"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86990540","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476074
Omar Al-Qawasmeh, Mohammad Al-Smadi, Nisreen Fraihat
This research aims at tackling the problem of Arabic Named-Entity Disambiguation (ANED) through an enhanced approach of information extraction from Arabic Wikipedia and Linked Open Data (LOD). The approach uses query label expansion and text similarity techniques to disambiguate entities of the types: person, location, and organization. A reference dataset for ANED has been prepared and annotated with over 10K entity mentions. The reference dataset was used in evaluating the proposed ANED approach. Results show that the accuracy of ANED approach is 84% on the overall Dataset. Moreover, the proposed approach was capable to disambiguate location entities with accuracy of 94%, person entities with 76%, and organization entities with 78%.
{"title":"Arabic named entity disambiguation using linked open data","authors":"Omar Al-Qawasmeh, Mohammad Al-Smadi, Nisreen Fraihat","doi":"10.1109/IACS.2016.7476074","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476074","url":null,"abstract":"This research aims at tackling the problem of Arabic Named-Entity Disambiguation (ANED) through an enhanced approach of information extraction from Arabic Wikipedia and Linked Open Data (LOD). The approach uses query label expansion and text similarity techniques to disambiguate entities of the types: person, location, and organization. A reference dataset for ANED has been prepared and annotated with over 10K entity mentions. The reference dataset was used in evaluating the proposed ANED approach. Results show that the accuracy of ANED approach is 84% on the overall Dataset. Moreover, the proposed approach was capable to disambiguate location entities with accuracy of 94%, person entities with 76%, and organization entities with 78%.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"22 1","pages":"333-338"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84251915","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 : 2016-04-05DOI: 10.1109/IACS.2016.7476115
Heba Ghreeb M. Abdel-Aziz, H. M. Ebeid, M. Mostafa
Face recognition is considered one of the most essential applications of Biometrics for personal identification. Face sketch recognition is a special case of face recognition, and it is very important for forensic applications. In this paper, we propose an unsupervised method for face photo-sketch recognition by synthesizing a pseudo-sketch from a single photo. The proposed method is the first unsupervised method that deals with face sketch recognition. The proposed photo-sketch synthesis step consists of two main steps, namely: edge detection and hair detection, which are applied on the grayscale image of the photo image. In the recognition step, the artist sketch is compared with the generated pseudo-sketch. PCA and LDA are used to extract features from the sketch images. The k-nearest neighbor classifier with Euclidean distance is used in the classification step. We use the CUHK database to test the performance of the proposed Method. Results for the synthesized sketches are compared with state-of-the-art methods, e.g., Local Linear Embedding (LLE) and Eigen transformation. The experimental results show that the proposed method generates a clear synthesis sketch and it defines persons more accurate than other methods. Moreover, in the recognition step, the proposed method achieves a recognition rate at the 1-nearest neighbor (rank1: first-match) range from 82% with PCA to 94% with LDA. The highest recognition rate is obtained at the 5-nearest neighbor (rank 5) is 98% that is better than some of the state-of-the-art methods.
{"title":"An unsupervised method for face photo-sketch synthesis and recognition","authors":"Heba Ghreeb M. Abdel-Aziz, H. M. Ebeid, M. Mostafa","doi":"10.1109/IACS.2016.7476115","DOIUrl":"https://doi.org/10.1109/IACS.2016.7476115","url":null,"abstract":"Face recognition is considered one of the most essential applications of Biometrics for personal identification. Face sketch recognition is a special case of face recognition, and it is very important for forensic applications. In this paper, we propose an unsupervised method for face photo-sketch recognition by synthesizing a pseudo-sketch from a single photo. The proposed method is the first unsupervised method that deals with face sketch recognition. The proposed photo-sketch synthesis step consists of two main steps, namely: edge detection and hair detection, which are applied on the grayscale image of the photo image. In the recognition step, the artist sketch is compared with the generated pseudo-sketch. PCA and LDA are used to extract features from the sketch images. The k-nearest neighbor classifier with Euclidean distance is used in the classification step. We use the CUHK database to test the performance of the proposed Method. Results for the synthesized sketches are compared with state-of-the-art methods, e.g., Local Linear Embedding (LLE) and Eigen transformation. The experimental results show that the proposed method generates a clear synthesis sketch and it defines persons more accurate than other methods. Moreover, in the recognition step, the proposed method achieves a recognition rate at the 1-nearest neighbor (rank1: first-match) range from 82% with PCA to 94% with LDA. The highest recognition rate is obtained at the 5-nearest neighbor (rank 5) is 98% that is better than some of the state-of-the-art methods.","PeriodicalId":6579,"journal":{"name":"2016 7th International Conference on Information and Communication Systems (ICICS)","volume":"8 1","pages":"221-226"},"PeriodicalIF":0.0,"publicationDate":"2016-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82151502","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：