Pub Date : 2015-12-01DOI: 10.1109/SPIS.2015.7422331
Mohaddeseh Peyvandi, A. Pouyan
Localization as a fundamental issue has a challenge in wireless sensor networks (WSNs). Many approaches have been proposed to solve the inaccurate node localization. Among range-free algorithms, DV-Hop (Distance Vector-hop) is a well-known localization algorithm that utilizes of hop-distance estimation to locate sensor nodes. This has lead positioning accuracy is limited. In this paper, an improved DV-HOP algorithm based on the hop-size correction and localization optimization is put forward. Firstly, based on difference of actual and estimated distance between reference nodes an effective hop-size is calculated for whole network; secondly, a correction value is added to the hops between unknown nodes and reference nodes while received signal strength indicator (RSSI) value is used to correct the distance of single hop. Finally, the Levenberg-Marquardt algorithm is applied to estimate an optimize position for each sensors. In evaluation step, various factors that affect the localization accuracy of the DV-Hop are investigated. Simulation results show that the proposed algorithm has been significantly improved compared to the basic DV-Hop and some existing improved algorithms.
定位作为无线传感器网络的一个基本问题，在无线传感器网络中面临着挑战。为了解决节点定位不准确的问题，人们提出了许多方法。在无距离定位算法中，DV-Hop (Distance Vector-hop)是一种著名的定位算法，它利用跳距估计来定位传感器节点。这就导致定位精度受到限制。本文提出了一种基于跳数修正和定位优化的改进DV-HOP算法。首先，根据参考节点之间实际距离和估计距离的差异，计算整个网络的有效跳数;其次，对未知节点与参考节点之间的跳数增加一个校正值，并使用接收信号强度指示器(received signal strength indicator, RSSI)值校正单跳距离。最后，应用Levenberg-Marquardt算法估计每个传感器的最优位置。在评价步骤中，研究了影响DV-Hop定位精度的各种因素。仿真结果表明，与基本的DV-Hop和现有的一些改进算法相比，该算法有了明显的改进。
{"title":"An improved DV-Hop localization algorithm in wireless sensor networks","authors":"Mohaddeseh Peyvandi, A. Pouyan","doi":"10.1109/SPIS.2015.7422331","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422331","url":null,"abstract":"Localization as a fundamental issue has a challenge in wireless sensor networks (WSNs). Many approaches have been proposed to solve the inaccurate node localization. Among range-free algorithms, DV-Hop (Distance Vector-hop) is a well-known localization algorithm that utilizes of hop-distance estimation to locate sensor nodes. This has lead positioning accuracy is limited. In this paper, an improved DV-HOP algorithm based on the hop-size correction and localization optimization is put forward. Firstly, based on difference of actual and estimated distance between reference nodes an effective hop-size is calculated for whole network; secondly, a correction value is added to the hops between unknown nodes and reference nodes while received signal strength indicator (RSSI) value is used to correct the distance of single hop. Finally, the Levenberg-Marquardt algorithm is applied to estimate an optimize position for each sensors. In evaluation step, various factors that affect the localization accuracy of the DV-Hop are investigated. Simulation results show that the proposed algorithm has been significantly improved compared to the basic DV-Hop and some existing improved algorithms.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115448426","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422329
Hamzeh Ghasemzadeh, M. Kayvanrad
Echo hiding methods have good perceptual quality and they are robust to intentional and unintentional modifications. Unfortunately these methods are not quite transparent and are not suitable for steganography applications. Specifically, this point became more obvious after a recent steganalysis investigation where both parameters and the hidden message were extracted accurately. This work tries to alleviate this problem by introducing variable parameters into echo hiding methods. The system is tested in both active and passive warden scenarios. Comparing results of conventional and the proposed method shows that for embedding strength of 0.2, the proposed method decreases detection of echo method by 24.2% and increases its robustness to echo attacks by 16.17%.
{"title":"Toward a robust and secure echo steganography method based on parameters hopping","authors":"Hamzeh Ghasemzadeh, M. Kayvanrad","doi":"10.1109/SPIS.2015.7422329","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422329","url":null,"abstract":"Echo hiding methods have good perceptual quality and they are robust to intentional and unintentional modifications. Unfortunately these methods are not quite transparent and are not suitable for steganography applications. Specifically, this point became more obvious after a recent steganalysis investigation where both parameters and the hidden message were extracted accurately. This work tries to alleviate this problem by introducing variable parameters into echo hiding methods. The system is tested in both active and passive warden scenarios. Comparing results of conventional and the proposed method shows that for embedding strength of 0.2, the proposed method decreases detection of echo method by 24.2% and increases its robustness to echo attacks by 16.17%.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116962995","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422305
H. Khastavaneh, H. Ebrahimpour-Komleh
Brain extraction is the task of removing non-brain tissues from brain magnetic resonance images. Brain extraction is a preprocessing step in many applications related to the brain image analysis. Accurate extraction of brain tissue is a laborious task. So, automatic extraction of it is a need in many applications. In this study we propose an automatic region based brain extraction method. In this method histogram of each region is independently analyzed and parameters relating to each tissue type is estimated by employing expectation-maximization algorithm. The estimated parameters of each tissue type including its mean and variance are used to determine tissues of interests. In this study tissues of interest are gray matter and white mater. Eventually a connected component analysis leads to select largest connected components of tissues of interest as brain mask. The proposed method is tested on BrainWeb dataset. Jaccard similarity index (J), Dice similarity coefficient (DSC), Sensitivity (Sen), and Specificity (Spec) are used to measure performance of the proposed method. The results are compared to three popular brain extraction methods namely hybrid watershed algorithm (HWA), brain extraction tools (BET), and brain surface extractor (BSE). The proposed method outperforms mentioned popular methods.
{"title":"Brain extraction: A region based histogram analysis strategy","authors":"H. Khastavaneh, H. Ebrahimpour-Komleh","doi":"10.1109/SPIS.2015.7422305","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422305","url":null,"abstract":"Brain extraction is the task of removing non-brain tissues from brain magnetic resonance images. Brain extraction is a preprocessing step in many applications related to the brain image analysis. Accurate extraction of brain tissue is a laborious task. So, automatic extraction of it is a need in many applications. In this study we propose an automatic region based brain extraction method. In this method histogram of each region is independently analyzed and parameters relating to each tissue type is estimated by employing expectation-maximization algorithm. The estimated parameters of each tissue type including its mean and variance are used to determine tissues of interests. In this study tissues of interest are gray matter and white mater. Eventually a connected component analysis leads to select largest connected components of tissues of interest as brain mask. The proposed method is tested on BrainWeb dataset. Jaccard similarity index (J), Dice similarity coefficient (DSC), Sensitivity (Sen), and Specificity (Spec) are used to measure performance of the proposed method. The results are compared to three popular brain extraction methods namely hybrid watershed algorithm (HWA), brain extraction tools (BET), and brain surface extractor (BSE). The proposed method outperforms mentioned popular methods.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124139088","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422338
Mahsa Mirabdollahi Shams, H. Kaveh, R. Safabakhsh
Traffic sign recognition (TSR) is a major challenging task for intelligent transport systems. In this paper, we present a multiclass traffic sign recognition system based on the Bag-of-Word (BOW) model. Despite huge success of BOW method, ignoring the spatial information is a weakness of this model and affects accuracy of classification. We have proposed a Spatial Histogram for traffic signs that preserves the required spatial information. In addition, we used an extended codebook construction method to extract key features from all of sign categories efficiently and achieved a recognition rate of %88.02 through 62 sign types with a short execution time.
{"title":"Traffic sign recognition using an extended bag-of-features model with spatial histogram","authors":"Mahsa Mirabdollahi Shams, H. Kaveh, R. Safabakhsh","doi":"10.1109/SPIS.2015.7422338","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422338","url":null,"abstract":"Traffic sign recognition (TSR) is a major challenging task for intelligent transport systems. In this paper, we present a multiclass traffic sign recognition system based on the Bag-of-Word (BOW) model. Despite huge success of BOW method, ignoring the spatial information is a weakness of this model and affects accuracy of classification. We have proposed a Spatial Histogram for traffic signs that preserves the required spatial information. In addition, we used an extended codebook construction method to extract key features from all of sign categories efficiently and achieved a recognition rate of %88.02 through 62 sign types with a short execution time.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130127803","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422323
Razie Kaviani, P. Ahmadi, I. Gholampour
Traffic density estimation plays an integral role in intelligent transportation systems (ITS), using which provides important information for signal control and effective traffic management. In this paper, we present a new framework for traffic density estimation based on topic model, which is an unsupervised model. This framework uses a set of visual features without any need to individual vehicle detection and tracking, and discovers the motion patterns automatically in traffic scenes by using topic model. Then, likelihood value allocated to each video clip enables us to estimate its traffic density. Results on a standard dataset show high classification performance of our proposed approach and robustness to typical environmental and illumination conditions.
{"title":"A new method for traffic density estimation based on topic model","authors":"Razie Kaviani, P. Ahmadi, I. Gholampour","doi":"10.1109/SPIS.2015.7422323","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422323","url":null,"abstract":"Traffic density estimation plays an integral role in intelligent transportation systems (ITS), using which provides important information for signal control and effective traffic management. In this paper, we present a new framework for traffic density estimation based on topic model, which is an unsupervised model. This framework uses a set of visual features without any need to individual vehicle detection and tracking, and discovers the motion patterns automatically in traffic scenes by using topic model. Then, likelihood value allocated to each video clip enables us to estimate its traffic density. Results on a standard dataset show high classification performance of our proposed approach and robustness to typical environmental and illumination conditions.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"15 15-16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132879304","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422321
Milad Seddigh, H. Taheri, Saeed Sharifian
Virtual machine (VM) scheduling with load balancing in cloud computing aims to allocate VMs to suitable physical machines (PM) and balance the resource usage among all of the PMs. Correct scheduling of cloud hosts is necessary to develop efficient scheduling strategies to appropriately allocate VMs to physical resources. In this regard the use of dynamic forecast of resource usage in each PM can improve the VM scheduling problem. This paper combines ant colony optimization (ACO) and VM dynamic forecast scheduling (VM_DFS), called virtual machine dynamic prediction scheduling via ant colony optimization (VMDPS-ACO), to solve the VM scheduling problem. In this algorithm through analysis of historical memory consumption in each PM, future memory consumption forecast of VMs on that PM and the efficient allocation of VMs on the cloud infrastructure is performed. We experimented the proposed algorithm using Matlab. The performance of the proposed algorithm is compared with VM_DFS. VM_DFS algorithm exploits first fit decreasing (FFD) scheme using corresponding types (i.e. queuing the list of VMs increasingly, decreasingly or randomly) to schedule VMs and assign them to suitable PMs. We experimented the proposed algorithm in both homogeneous and heterogeneous mode. The results indicate, VMDPS-ACO produces lower resource wastage than VM_DFS in both homogenous and heterogeneous modes and better load balancing among PMs.
{"title":"Dynamic prediction scheduling for virtual machine placement via ant colony optimization","authors":"Milad Seddigh, H. Taheri, Saeed Sharifian","doi":"10.1109/SPIS.2015.7422321","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422321","url":null,"abstract":"Virtual machine (VM) scheduling with load balancing in cloud computing aims to allocate VMs to suitable physical machines (PM) and balance the resource usage among all of the PMs. Correct scheduling of cloud hosts is necessary to develop efficient scheduling strategies to appropriately allocate VMs to physical resources. In this regard the use of dynamic forecast of resource usage in each PM can improve the VM scheduling problem. This paper combines ant colony optimization (ACO) and VM dynamic forecast scheduling (VM_DFS), called virtual machine dynamic prediction scheduling via ant colony optimization (VMDPS-ACO), to solve the VM scheduling problem. In this algorithm through analysis of historical memory consumption in each PM, future memory consumption forecast of VMs on that PM and the efficient allocation of VMs on the cloud infrastructure is performed. We experimented the proposed algorithm using Matlab. The performance of the proposed algorithm is compared with VM_DFS. VM_DFS algorithm exploits first fit decreasing (FFD) scheme using corresponding types (i.e. queuing the list of VMs increasingly, decreasingly or randomly) to schedule VMs and assign them to suitable PMs. We experimented the proposed algorithm in both homogeneous and heterogeneous mode. The results indicate, VMDPS-ACO produces lower resource wastage than VM_DFS in both homogenous and heterogeneous modes and better load balancing among PMs.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126596798","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422337
Negin Massoudian, M. Eshghi
Since unsafe speed and deviation to the left side in road curve with limited Visibility, may cause accidents to happen, a solution to detect and prevent such accidents has been proposed in this paper in order to achieve a safe trip. It is necessary to have the geometric properties of the road, and detect the speed and location of the car. To do this, initially the geometric properties of mountainous roads are extracted and then using inductive loop detectors sensors, and instant speed and location data of vehicles on the road, probability of accident will be predicted. In next step, by warning drivers and reducing the vehicle's speed using automatic physical barriers used along the route, accidents will be prevented. Finally the costs of making the roads intelligent will be investigated. The results show that the designed intelligent system has succeeded to achieve remarkable reduction in probable.
{"title":"Design an intelligent curve to reduce the accident rate","authors":"Negin Massoudian, M. Eshghi","doi":"10.1109/SPIS.2015.7422337","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422337","url":null,"abstract":"Since unsafe speed and deviation to the left side in road curve with limited Visibility, may cause accidents to happen, a solution to detect and prevent such accidents has been proposed in this paper in order to achieve a safe trip. It is necessary to have the geometric properties of the road, and detect the speed and location of the car. To do this, initially the geometric properties of mountainous roads are extracted and then using inductive loop detectors sensors, and instant speed and location data of vehicles on the road, probability of accident will be predicted. In next step, by warning drivers and reducing the vehicle's speed using automatic physical barriers used along the route, accidents will be prevented. Finally the costs of making the roads intelligent will be investigated. The results show that the designed intelligent system has succeeded to achieve remarkable reduction in probable.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134107250","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422312
S. Paknahad, S. A. Hosseini, Mahdi R. Alaghband
A user-friendly visual secret sharing scheme without pixel expansion is presented based on random grids. Since noise like shares are not user-friendly, a meaningful shares producing method would be proposed in order to simplify mass data management. Firstly, black and white pixels distribution in shared images and stack image will be analyzed, then a probability allocation will be proposed which has ability to control the quality of produced shared images and stack image. In former methods there was a quality tradeoff between meaningful shares and stack image, but the proposed method increases tradeoff flexibility. Moreover the inability to adjust the visual quality reduced by the proposed visual secret sharing scheme. The suggested method will be checked and compared to other schemes.
{"title":"User-friendly visual secret sharing based on random grids","authors":"S. Paknahad, S. A. Hosseini, Mahdi R. Alaghband","doi":"10.1109/SPIS.2015.7422312","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422312","url":null,"abstract":"A user-friendly visual secret sharing scheme without pixel expansion is presented based on random grids. Since noise like shares are not user-friendly, a meaningful shares producing method would be proposed in order to simplify mass data management. Firstly, black and white pixels distribution in shared images and stack image will be analyzed, then a probability allocation will be proposed which has ability to control the quality of produced shared images and stack image. In former methods there was a quality tradeoff between meaningful shares and stack image, but the proposed method increases tradeoff flexibility. Moreover the inability to adjust the visual quality reduced by the proposed visual secret sharing scheme. The suggested method will be checked and compared to other schemes.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115253169","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422330
Iman Taghavi, M. Sabahi, F. Parvaresh, M. Mivehchy
In this paper, we address the problem of direction-of-arrival (DOA) estimation using a novel spatial sampling scheme based on difference set (DS) codes, called DS-spatial sampling. It is shown that the proposed DS-spatial sampling scheme can be modeled by a deterministic dictionary with minimum coherence. We also develop a low complexity compressed sensing (CS) model for DOA estimation. The proposed methods can reduce the number of array elements as well as the number of receivers. Compared with the conventional DOA estimation algorithm, the proposed sampling and processing method can achieve significantly higher resolution.
{"title":"A novel compressed sensing DOA estimation using difference set codes","authors":"Iman Taghavi, M. Sabahi, F. Parvaresh, M. Mivehchy","doi":"10.1109/SPIS.2015.7422330","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422330","url":null,"abstract":"In this paper, we address the problem of direction-of-arrival (DOA) estimation using a novel spatial sampling scheme based on difference set (DS) codes, called DS-spatial sampling. It is shown that the proposed DS-spatial sampling scheme can be modeled by a deterministic dictionary with minimum coherence. We also develop a low complexity compressed sensing (CS) model for DOA estimation. The proposed methods can reduce the number of array elements as well as the number of receivers. Compared with the conventional DOA estimation algorithm, the proposed sampling and processing method can achieve significantly higher resolution.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116000948","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 : 2015-12-01DOI: 10.1109/SPIS.2015.7422310
M. Nejati, A. Majidi, Morteza Jalalat
In this paper, a new approach for Iranian vehicle license plate recognition (LPR) is proposed. The proposed algorithm contains four main steps including plate localization, segmentation, recognition, and fusion of multiple recognition results. The license plate localization is begun with some preprocessing for down-sampling, denoising and histogram equalization. Then, histogram of vertical edges is used for detection of candidate lines expected to contain the license plate. In this step, we design a filter in order to reduce the number of false line candidates. The candidate plates are then extracted using vertical projection histogram of edges and aspect ratio characteristic. The binary image of these candidates obtained by locally adaptive thresholding is transmitted to the segmentation and recognition modules. Our recognition method is accomplished using a classifier ensemble with mixture of experts architecture. Using a feedback from the recognition result of candidate plates, the true candidate is detected. To improve the recognition accuracy and robustness, we apply the proposed LPR on three consecutive frames of a vehicle captured by different exposure times and then combine their recognition outputs. The experimental results in practical situations of day and night show that the proposed approach leads to 95.39% accuracy in plate localization and 92.45% overall accuracy after recognition.
{"title":"License plate recognition based on edge histogram analysis and classifier ensemble","authors":"M. Nejati, A. Majidi, Morteza Jalalat","doi":"10.1109/SPIS.2015.7422310","DOIUrl":"https://doi.org/10.1109/SPIS.2015.7422310","url":null,"abstract":"In this paper, a new approach for Iranian vehicle license plate recognition (LPR) is proposed. The proposed algorithm contains four main steps including plate localization, segmentation, recognition, and fusion of multiple recognition results. The license plate localization is begun with some preprocessing for down-sampling, denoising and histogram equalization. Then, histogram of vertical edges is used for detection of candidate lines expected to contain the license plate. In this step, we design a filter in order to reduce the number of false line candidates. The candidate plates are then extracted using vertical projection histogram of edges and aspect ratio characteristic. The binary image of these candidates obtained by locally adaptive thresholding is transmitted to the segmentation and recognition modules. Our recognition method is accomplished using a classifier ensemble with mixture of experts architecture. Using a feedback from the recognition result of candidate plates, the true candidate is detected. To improve the recognition accuracy and robustness, we apply the proposed LPR on three consecutive frames of a vehicle captured by different exposure times and then combine their recognition outputs. The experimental results in practical situations of day and night show that the proposed approach leads to 95.39% accuracy in plate localization and 92.45% overall accuracy after recognition.","PeriodicalId":424434,"journal":{"name":"2015 Signal Processing and Intelligent Systems Conference (SPIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122250098","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：