Pub Date : 2021-11-25DOI: 10.1109/icicn52636.2021.9673839
Y. Zhong, L. Wan
Aiming at the optimal adjustment of unmanned communication relay nodes (UCRNs) problem in manned/ unmanned aerial vehicle cooperative engagement system, this paper established a two–layer mathematical model to describe it and solved it through a greedy distributed model predictive control (GDMPC) and multi–objective artificial bee colony (MOABC) method. Problem description and element definition, kinematic model of unmanned communication relay nodes, modeling of the problem, GDMPC framework and subsystem optimization solution based on MOABC were in sequence presented, and finally, simulation experiments were carried on to verify the correctness of the model and the effectiveness of the algorithm.
{"title":"Optimal Adjustment of UCRNs in Cooperative Engagement System Based on GDMPC-MOABC","authors":"Y. Zhong, L. Wan","doi":"10.1109/icicn52636.2021.9673839","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673839","url":null,"abstract":"Aiming at the optimal adjustment of unmanned communication relay nodes (UCRNs) problem in manned/ unmanned aerial vehicle cooperative engagement system, this paper established a two–layer mathematical model to describe it and solved it through a greedy distributed model predictive control (GDMPC) and multi–objective artificial bee colony (MOABC) method. Problem description and element definition, kinematic model of unmanned communication relay nodes, modeling of the problem, GDMPC framework and subsystem optimization solution based on MOABC were in sequence presented, and finally, simulation experiments were carried on to verify the correctness of the model and the effectiveness of the algorithm.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128842067","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673926
Lijia Xie, X. Xiao, Yiming Shi, Cheng Zhang, Jie Jiang
Wireless Sensor Network (WSN) has covered broad areas as a promising networking technique. The sensor nodes are facing multiple menaces, especially Distributed Denial of Attack (DDoS). Yet, existing DDoS mitigations are inadequate to be applied in WSNs due to the constrained resources. In this paper, we propose an activatable DDoS defense which is adaptable for WSNs. We design an activation mechanism to achieve the state transition of nodes with adjustable overhead. Furthermore, a probabilistic bootstrap percolation in connected Random Geometric Graph (RGG) is utilized to model the dynamic activation process. We analyze the critical threshold of phase transition theoretically and provide the proof. Finally, we numerically analyze the process and verify the theoretical results by comprehensive simulations.
{"title":"An Activatable DDoS Defense for Wireless Sensor Networks","authors":"Lijia Xie, X. Xiao, Yiming Shi, Cheng Zhang, Jie Jiang","doi":"10.1109/icicn52636.2021.9673926","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673926","url":null,"abstract":"Wireless Sensor Network (WSN) has covered broad areas as a promising networking technique. The sensor nodes are facing multiple menaces, especially Distributed Denial of Attack (DDoS). Yet, existing DDoS mitigations are inadequate to be applied in WSNs due to the constrained resources. In this paper, we propose an activatable DDoS defense which is adaptable for WSNs. We design an activation mechanism to achieve the state transition of nodes with adjustable overhead. Furthermore, a probabilistic bootstrap percolation in connected Random Geometric Graph (RGG) is utilized to model the dynamic activation process. We analyze the critical threshold of phase transition theoretically and provide the proof. Finally, we numerically analyze the process and verify the theoretical results by comprehensive simulations.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125353681","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673880
Jie Yang, Yufeng Shao, An-rong Wang, Zhuang Wang, Qinzheng Hu, Qiming Yang, N. Yu
A 40Gbit/s Free Space Optical (FSO) communication system using Alternate Mark Inversion (AMI) encoded signals is designed in this scheme. It uses Dense Wavelength Division Multiplexing (DWDM) multiplexer to complete the simultaneous multiplexing of 16-channel AMI encoded signals, realizing the transceiver and transmission of 40Gbit/s optical signal. Modeled analysis the system, numerical simulation tested the time domain diagram, spectrum diagram, eye diagrams, bit error rate (BER) and other indicators of the DWDM-AMI signal before and after transmission through the 1km FSO channel. The results show that the 192.4THz AMI signal best decoding decision point is 0.593, Q factor is 15.9; The 193.1THz AMI signal best decoding decision point is 0.597, Q factor is 15.1.
{"title":"A 40Gbit/s Alternate Mark Inversion Encoded Free Space Optical System","authors":"Jie Yang, Yufeng Shao, An-rong Wang, Zhuang Wang, Qinzheng Hu, Qiming Yang, N. Yu","doi":"10.1109/icicn52636.2021.9673880","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673880","url":null,"abstract":"A 40Gbit/s Free Space Optical (FSO) communication system using Alternate Mark Inversion (AMI) encoded signals is designed in this scheme. It uses Dense Wavelength Division Multiplexing (DWDM) multiplexer to complete the simultaneous multiplexing of 16-channel AMI encoded signals, realizing the transceiver and transmission of 40Gbit/s optical signal. Modeled analysis the system, numerical simulation tested the time domain diagram, spectrum diagram, eye diagrams, bit error rate (BER) and other indicators of the DWDM-AMI signal before and after transmission through the 1km FSO channel. The results show that the 192.4THz AMI signal best decoding decision point is 0.593, Q factor is 15.9; The 193.1THz AMI signal best decoding decision point is 0.597, Q factor is 15.1.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122184332","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673895
I. Gueye, I. Diop, I. Dioum, Papis Ndiaye
This article focuses on the performance analysis of cooperative systems hybridizing MIMO-RF/MIMO-FSO and error correcting codes including GC-LDPC codes in FSOs. In this double-hop relay system composed of links with several inputs and multiple outputs at radio frequency and with multiple inputs and multiple outputs in FSO. In this system the source transmits the information to the relay by RF links, the relay processes the information received from the source and retransmits it to the destination by FSO links. To decode the data we used two-phase local-global decoding and to eliminate interference between source-relay links and relay-destination links we use interference alignment (IA) technique. It is also assumed that the source-relay link undergoes Rayleigh fading, while the relay-destination links undergo Gamma-Gamma model fading. Using DF relay technology, hybrid MIMO-RF/MIMO-FSO systems combine the advantages of RF and FSO communication technologies. The use of hybrid MIMO- RF/MIMO-FSO cooperative transmission systems improves network reliability and transmission. In this work, we carried out a simulation study on the distribution of the total transmission power at the source and the relay level to understand the best allocations between the source and the relay in order to guarantee a good quality of reception of the data transmitted to the destination. This work also presents studies on the different combimaision techniques. The results of our simulations show that the MIMO-RF/MIMO-FSO system based on GC-LDPC codes gives better performance compared to MIMO-RF/FSO and RF/FSO systems based on the same codes but also with conventional systems without the use of codes.
{"title":"Performance Analysis of Mixed MIMO-RF/MIMO-FSO DF Relaying Using Globally Coupled Low Density Parity Check (GC-LDPC) Codes and Diversity Techniques","authors":"I. Gueye, I. Diop, I. Dioum, Papis Ndiaye","doi":"10.1109/icicn52636.2021.9673895","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673895","url":null,"abstract":"This article focuses on the performance analysis of cooperative systems hybridizing MIMO-RF/MIMO-FSO and error correcting codes including GC-LDPC codes in FSOs. In this double-hop relay system composed of links with several inputs and multiple outputs at radio frequency and with multiple inputs and multiple outputs in FSO. In this system the source transmits the information to the relay by RF links, the relay processes the information received from the source and retransmits it to the destination by FSO links. To decode the data we used two-phase local-global decoding and to eliminate interference between source-relay links and relay-destination links we use interference alignment (IA) technique. It is also assumed that the source-relay link undergoes Rayleigh fading, while the relay-destination links undergo Gamma-Gamma model fading. Using DF relay technology, hybrid MIMO-RF/MIMO-FSO systems combine the advantages of RF and FSO communication technologies. The use of hybrid MIMO- RF/MIMO-FSO cooperative transmission systems improves network reliability and transmission. In this work, we carried out a simulation study on the distribution of the total transmission power at the source and the relay level to understand the best allocations between the source and the relay in order to guarantee a good quality of reception of the data transmitted to the destination. This work also presents studies on the different combimaision techniques. The results of our simulations show that the MIMO-RF/MIMO-FSO system based on GC-LDPC codes gives better performance compared to MIMO-RF/FSO and RF/FSO systems based on the same codes but also with conventional systems without the use of codes.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116867795","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}
In networked systems, traffic is one of the most fundamental dynamical processes. Since the betweenness of nodes in complex networks can theoretically represent the traffic load of nodes, a routing strategy for two-layer complex networks is proposed based on the betweenness centrality. With the routing strategy, the packets are set to bypass the nodes with large betweenness in the logical layer network and the physical layer network. The traffic loads can be redistributed from the central nodes to the noncentral nodes efficiently. The routing strategy can alleviate the congestion and promote the traffic capacity of multilayers complex networks. Compared to the shortest path routing (SPR) and improved active routing (IAR) strategy, simulation results show that the two-layer complex networks capacity is considerably enhanced when $beta$=0.75..
{"title":"A Routing Strategy Based on the betweenness Centrality for Multi-layers Complex Networks","authors":"Yue Zhuo, Yu Liang, Yu Huang, Yixiao Cao, Jinfeng Nie, Yu Qi","doi":"10.1109/icicn52636.2021.9674025","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9674025","url":null,"abstract":"In networked systems, traffic is one of the most fundamental dynamical processes. Since the betweenness of nodes in complex networks can theoretically represent the traffic load of nodes, a routing strategy for two-layer complex networks is proposed based on the betweenness centrality. With the routing strategy, the packets are set to bypass the nodes with large betweenness in the logical layer network and the physical layer network. The traffic loads can be redistributed from the central nodes to the noncentral nodes efficiently. The routing strategy can alleviate the congestion and promote the traffic capacity of multilayers complex networks. Compared to the shortest path routing (SPR) and improved active routing (IAR) strategy, simulation results show that the two-layer complex networks capacity is considerably enhanced when $beta$=0.75..","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134428731","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673978
Lixia Xi, Jiacheng Wei, Wenbo Zhang
Nonlinear frequency division multiplexing system becomes one of the promising candidates for overcoming the fiber’s nonlinearity limitations. To improve the system’s performance, machine learning was introduced to the NFDM systems in the past few years. In this paper, an overview on the applications of machine learning in the NFDM systems is presented.
{"title":"Applications of Machine Learning on Nonlinear Frequency Division Multiplexing Optic-Fiber Communication Systems","authors":"Lixia Xi, Jiacheng Wei, Wenbo Zhang","doi":"10.1109/icicn52636.2021.9673978","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673978","url":null,"abstract":"Nonlinear frequency division multiplexing system becomes one of the promising candidates for overcoming the fiber’s nonlinearity limitations. To improve the system’s performance, machine learning was introduced to the NFDM systems in the past few years. In this paper, an overview on the applications of machine learning in the NFDM systems is presented.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129283783","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673844
Xiaozhong Tong, Zhen Zuo, Bei Sun, Junyu Wei
Detecting infrared small target that lack texture features and shape information in cluttered environments is a challenging task. In this paper, we propose a novel feature fusion approach of feature pyramid networks (FPN) for effective detection of infrared small target. To extract the feature maps of infrared small target in different layers of the network and to fuse them effectively, we propose a multi-scale feature fusion module. Experimental results show that our proposed method performs much better than traditional approaches for infrared small target detection. In particular, our proposed method still achieves satisfactory results compared to other deep learning-based methods. In addition, we conducted ablation study of the network structure and the experimental results demonstrate the effectiveness of our proposed novel FPN.
{"title":"Novel Feature Fusion for Infrared Small Target Detection Feature Pyramid Networks","authors":"Xiaozhong Tong, Zhen Zuo, Bei Sun, Junyu Wei","doi":"10.1109/icicn52636.2021.9673844","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673844","url":null,"abstract":"Detecting infrared small target that lack texture features and shape information in cluttered environments is a challenging task. In this paper, we propose a novel feature fusion approach of feature pyramid networks (FPN) for effective detection of infrared small target. To extract the feature maps of infrared small target in different layers of the network and to fuse them effectively, we propose a multi-scale feature fusion module. Experimental results show that our proposed method performs much better than traditional approaches for infrared small target detection. In particular, our proposed method still achieves satisfactory results compared to other deep learning-based methods. In addition, we conducted ablation study of the network structure and the experimental results demonstrate the effectiveness of our proposed novel FPN.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125332458","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673969
Lu Li, Zhanjun Jiang, Yanneng Li
There are some problems in the surface defect detection of industrial aluminum products, such as small defect samples, extreme length-to-width ratio of defect, low precision of small defect detection, etc. To solve these problems, an aluminum surface defect detection algorithm is proposed based on improved Faster RCNN. The number of defect samples is increased by data augmentation, and the residual network ResNet50 is employed as the backbone feature extraction network to extract aluminum defect features. Then the path enhancement feature pyramid network (PAFPN) is added to the backbone feature extraction network to form a multi-scale feature map which strengthens the utilization of feature information from the lower layers. Soft non-maximum suppression (Soft-NMS) is used to further improve the detection performance of the algorithm. Results show that the mean average accuracy (mAP) of the proposed algorithm is 78.8%, which is 2.2% higher than the original algorithm.
{"title":"Surface Defect Detection Algorithm of Aluminum Based on Improved Faster RCNN","authors":"Lu Li, Zhanjun Jiang, Yanneng Li","doi":"10.1109/icicn52636.2021.9673969","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673969","url":null,"abstract":"There are some problems in the surface defect detection of industrial aluminum products, such as small defect samples, extreme length-to-width ratio of defect, low precision of small defect detection, etc. To solve these problems, an aluminum surface defect detection algorithm is proposed based on improved Faster RCNN. The number of defect samples is increased by data augmentation, and the residual network ResNet50 is employed as the backbone feature extraction network to extract aluminum defect features. Then the path enhancement feature pyramid network (PAFPN) is added to the backbone feature extraction network to form a multi-scale feature map which strengthens the utilization of feature information from the lower layers. Soft non-maximum suppression (Soft-NMS) is used to further improve the detection performance of the algorithm. Results show that the mean average accuracy (mAP) of the proposed algorithm is 78.8%, which is 2.2% higher than the original algorithm.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115615687","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9673921
Mohammad Nizamul Haque
Underwater wireless sensor networks (UWSNs) face new threats and prospects as a result of recent technological advances. Providing large-scale, and high spatial-temporal resolution of ocean exploration data is highly crucial in environmental monitoring, ocean energy production, and marine science research. Underwater wireless communications, however, face many challenges, including bandwidth constraints, multipath propagation, and fading, long end-to-end propagation latency, and limited power supply with batteries. Underwater monitoring tasks are seriously hampered by data losses due to low link qualities and collisions. Therefore, in UWSN, the design and implementation of an energy-aware, secure, and less propagation delay concern MAC protocol is important. This paper presents a simulation-based performance analysis for a multi-directional data access control system using UAN-CW, UAN-RC, and UANALOHA MAC protocols in an underwater wireless network. A two-way half-duplex acoustic modem has been implemented to analyze the consumed and remaining energy of the network. To assess MAC protocols evaluation, we compared three MAC protocols focusing on throughput, delay, packet delivery ratio, and energy consumption. Simulations were carried out by using the ns3 simulation tool. The simulation results show that UAN-CW MAC protocol outperforms two protocols in respect of throughput, delay, packet delivery ratio, and energy consumption. However, the remaining energy for UAN-RC-MAC is higher than others.
{"title":"Analysis of a Multi-directional Data Access Control System for Underwater Wireless Network using UAN MAC Protocols","authors":"Mohammad Nizamul Haque","doi":"10.1109/icicn52636.2021.9673921","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673921","url":null,"abstract":"Underwater wireless sensor networks (UWSNs) face new threats and prospects as a result of recent technological advances. Providing large-scale, and high spatial-temporal resolution of ocean exploration data is highly crucial in environmental monitoring, ocean energy production, and marine science research. Underwater wireless communications, however, face many challenges, including bandwidth constraints, multipath propagation, and fading, long end-to-end propagation latency, and limited power supply with batteries. Underwater monitoring tasks are seriously hampered by data losses due to low link qualities and collisions. Therefore, in UWSN, the design and implementation of an energy-aware, secure, and less propagation delay concern MAC protocol is important. This paper presents a simulation-based performance analysis for a multi-directional data access control system using UAN-CW, UAN-RC, and UANALOHA MAC protocols in an underwater wireless network. A two-way half-duplex acoustic modem has been implemented to analyze the consumed and remaining energy of the network. To assess MAC protocols evaluation, we compared three MAC protocols focusing on throughput, delay, packet delivery ratio, and energy consumption. Simulations were carried out by using the ns3 simulation tool. The simulation results show that UAN-CW MAC protocol outperforms two protocols in respect of throughput, delay, packet delivery ratio, and energy consumption. However, the remaining energy for UAN-RC-MAC is higher than others.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128932811","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 : 2021-11-25DOI: 10.1109/icicn52636.2021.9674011
Xingxin Yang, Y. Wan
Good binarization result is of great help to the afterwords document image analysis and optical character recognition(OCR). However, non-uniform illumination document image binarization is a very challenging task due to high variation between the document background and foreground. This paper describes a new K-Means clustering based algorithm for non-uniform illumination document image binarization to solve this problem. In the proposed technique, we firstly obtain the combined edge map by take intersection of Canny’s edge map and local image contrast. Then divide the document image into small blocks, each block is classified as text and non-text block using our proposed algorithm. Finally, binarize the text block using K-Means clustering centroids. The proposed technique has been evaluated over nine Non-uniform illumination document images extracted from DIBCO datasets and one scene light reflection document image. Experimental results show that our proposed method achieves competitive performance among other six state-of-the-art binarization algorithm.
{"title":"Non-uniform Illumination Document Image Binarization Using K-Means Clustering Algorithm","authors":"Xingxin Yang, Y. Wan","doi":"10.1109/icicn52636.2021.9674011","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9674011","url":null,"abstract":"Good binarization result is of great help to the afterwords document image analysis and optical character recognition(OCR). However, non-uniform illumination document image binarization is a very challenging task due to high variation between the document background and foreground. This paper describes a new K-Means clustering based algorithm for non-uniform illumination document image binarization to solve this problem. In the proposed technique, we firstly obtain the combined edge map by take intersection of Canny’s edge map and local image contrast. Then divide the document image into small blocks, each block is classified as text and non-text block using our proposed algorithm. Finally, binarize the text block using K-Means clustering centroids. The proposed technique has been evaluated over nine Non-uniform illumination document images extracted from DIBCO datasets and one scene light reflection document image. Experimental results show that our proposed method achieves competitive performance among other six state-of-the-art binarization algorithm.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121449966","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：