Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696829
Liyou Fang, Xiang Yao
The power industry is an important foundation for the development of the national economy, and a strong and reliable power supply is the basic guarantee for social stability. This research mainly discusses the intelligent diagnosis system of networked substation equipment based on data mining algorithm. First, through various experiments and monitoring methods, the original database of characteristic indicators is obtained, and then the original database is screened, repaired, and quantitatively converted into a form that is convenient for computer processing, providing a data basis for mining status information. Fusion of multi-dimensional information, classification of status levels according to certain standards or models, and further refinement functions such as fault location and division of responsibilities can be realized according to needs. Based on the results of diagnosis and evaluation, considering the actual operation mode of the system and the local human and material resources, a multi-objective optimization function considering effectiveness and safety is established. By solving the objective function, the test items that need to be arranged for a specific transformer can be obtained. Decision-making optimization such as the video frequency of the tour. The highest diagnosis rate under low temperature and overheating state was 93.28%. This research will help improve the reliability of power supply for substation equipment.
{"title":"Intelligent Diagnosis System of Networked Substation Equipment Based on Data Mining Algorithm","authors":"Liyou Fang, Xiang Yao","doi":"10.1109/ICESIT53460.2021.9696829","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696829","url":null,"abstract":"The power industry is an important foundation for the development of the national economy, and a strong and reliable power supply is the basic guarantee for social stability. This research mainly discusses the intelligent diagnosis system of networked substation equipment based on data mining algorithm. First, through various experiments and monitoring methods, the original database of characteristic indicators is obtained, and then the original database is screened, repaired, and quantitatively converted into a form that is convenient for computer processing, providing a data basis for mining status information. Fusion of multi-dimensional information, classification of status levels according to certain standards or models, and further refinement functions such as fault location and division of responsibilities can be realized according to needs. Based on the results of diagnosis and evaluation, considering the actual operation mode of the system and the local human and material resources, a multi-objective optimization function considering effectiveness and safety is established. By solving the objective function, the test items that need to be arranged for a specific transformer can be obtained. Decision-making optimization such as the video frequency of the tour. The highest diagnosis rate under low temperature and overheating state was 93.28%. This research will help improve the reliability of power supply for substation equipment.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131760132","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696731
Xiangren Wang, Jun Peng, Ke Xu, Shangzhu Jin, Ning Chen, Xi Zheng
A color image encryption scheme based on DNA encoding and a hyperchaotic system is proposed. First, the plaintext image is converted into three DNA matrices, and the original image pixels are shuffled by the DNA encoding and chaotic sequence, then the two DNA matrices are separately exchange of DNA fragments in rows and columns. The chaotic sequence determines the matrices and DNA fragments that need to be exchanged, which can resist statistical attacks well, and then the S-box is generated according to the DNA random code and the chaotic sequence, which maps the scrambled matrix and finally recombines the three matrices to obtain the ciphertext. The simulation experiment shows that the image encryption system has good security and can resist various attacks.
{"title":"Hyperchaotic Image Encryption Algorithm Based on Dynamic DNA Coding","authors":"Xiangren Wang, Jun Peng, Ke Xu, Shangzhu Jin, Ning Chen, Xi Zheng","doi":"10.1109/ICESIT53460.2021.9696731","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696731","url":null,"abstract":"A color image encryption scheme based on DNA encoding and a hyperchaotic system is proposed. First, the plaintext image is converted into three DNA matrices, and the original image pixels are shuffled by the DNA encoding and chaotic sequence, then the two DNA matrices are separately exchange of DNA fragments in rows and columns. The chaotic sequence determines the matrices and DNA fragments that need to be exchanged, which can resist statistical attacks well, and then the S-box is generated according to the DNA random code and the chaotic sequence, which maps the scrambled matrix and finally recombines the three matrices to obtain the ciphertext. The simulation experiment shows that the image encryption system has good security and can resist various attacks.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130947729","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9697021
Hao Chen, Zongfeng Li
In this paper, a fluid circuit design scheme based on the new shaftless pump-jet technology is proposed, and its hydraulic performance is analyzed and calculated. This is a brand-new solution to the driving problem of the thermal control fluid circuit. At the same time, based on the shaftless pump-jet technology applied in ships and submarines, this paper abandons the traditional pump drive mode, optimizes the structure design, solves the leakage and hydraulic loss problems, and designs a new type of shaftless pump applied in small fluid circuit. After comparative analysis and comparison, the new shaftless pump has broad prospects in the application of fluid circuits.
{"title":"A new computer assisted design of shaftless pump for small fluid circuit by hydraulic calculation","authors":"Hao Chen, Zongfeng Li","doi":"10.1109/ICESIT53460.2021.9697021","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9697021","url":null,"abstract":"In this paper, a fluid circuit design scheme based on the new shaftless pump-jet technology is proposed, and its hydraulic performance is analyzed and calculated. This is a brand-new solution to the driving problem of the thermal control fluid circuit. At the same time, based on the shaftless pump-jet technology applied in ships and submarines, this paper abandons the traditional pump drive mode, optimizes the structure design, solves the leakage and hydraulic loss problems, and designs a new type of shaftless pump applied in small fluid circuit. After comparative analysis and comparison, the new shaftless pump has broad prospects in the application of fluid circuits.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132847449","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696474
Liang Kaiwu, Zhang Siqi, Wang Lijing
In view of the problems in the classification of high consequence zones of sulphur-bearing collector pipelines, firstly, the factors influencing the classification of high consequence zones of sulphur-bearing collector pipelines were analysed; secondly, the computational fluid dynamics simulation software FLACS was used to simulate the leakage of sulphur-bearing collector pipelines, and a rapid calculation model of the potential influence radius of leakage of sulphur-bearing collector pipelines was proposed; on this basis, a proposal for the classification of high consequence zones of sulphur-bearing collector pipelines was put forward, and an empirical On the basis of this, a high consequence zone classification proposal for sulphur-bearing gathering pipelines was proposed and empirically studied.
{"title":"Exploring the high consequence zone classification of gas gathering pipelines containing hydrogen sulphide","authors":"Liang Kaiwu, Zhang Siqi, Wang Lijing","doi":"10.1109/ICESIT53460.2021.9696474","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696474","url":null,"abstract":"In view of the problems in the classification of high consequence zones of sulphur-bearing collector pipelines, firstly, the factors influencing the classification of high consequence zones of sulphur-bearing collector pipelines were analysed; secondly, the computational fluid dynamics simulation software FLACS was used to simulate the leakage of sulphur-bearing collector pipelines, and a rapid calculation model of the potential influence radius of leakage of sulphur-bearing collector pipelines was proposed; on this basis, a proposal for the classification of high consequence zones of sulphur-bearing collector pipelines was put forward, and an empirical On the basis of this, a high consequence zone classification proposal for sulphur-bearing gathering pipelines was proposed and empirically studied.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133336069","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696558
Wei Yin, Weijie Zhu, Dawei Zhang, Zheng-Yong Hu
The automatic detection system for full-performance detection of measuring instruments mainly solves the problems of the existing detection platform body cannot be applied to the full-performance detection automatic detection line, cannot be compatible with a variety of tested equipment, low automation level, low detection efficiency, and large area. Design a multifunctional automatic detection device suitable for all types of intelligent electric energy meters, type I concentrators and type III special transformer collection terminals. Used in conjunction with the full-performance testing automated assembly line, error testing and functional testing of a variety of metering equipment can be completed without human intervention. It is conducive to the realization of intelligent optimization control of the detection process, and is conducive to the realization of the intelligent collection and management of detection data. Reduce equipment procurement and operation and maintenance costs, and improve resource utilization.
{"title":"Research and Design of Automatic Testing System for Full Performance of Measuring Instruments","authors":"Wei Yin, Weijie Zhu, Dawei Zhang, Zheng-Yong Hu","doi":"10.1109/ICESIT53460.2021.9696558","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696558","url":null,"abstract":"The automatic detection system for full-performance detection of measuring instruments mainly solves the problems of the existing detection platform body cannot be applied to the full-performance detection automatic detection line, cannot be compatible with a variety of tested equipment, low automation level, low detection efficiency, and large area. Design a multifunctional automatic detection device suitable for all types of intelligent electric energy meters, type I concentrators and type III special transformer collection terminals. Used in conjunction with the full-performance testing automated assembly line, error testing and functional testing of a variety of metering equipment can be completed without human intervention. It is conducive to the realization of intelligent optimization control of the detection process, and is conducive to the realization of the intelligent collection and management of detection data. Reduce equipment procurement and operation and maintenance costs, and improve resource utilization.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132727964","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696469
Honghui Zhou, Ruyi Qin, Jian Wu, Ying Qian, Xiaoming Ju
With the continuous development of the state grid, power transmission equipment is also increasing, and how to efficiently inspect and maintain power transmission equipment has become a key concern in the industry. In order to reduce the consumption of manpower in the inspection process, the current method is mainly to send drones to take patrol photos and then use deep learning to identify faulty equipment. However, in the actual process, power transmission equipment is generally built in areas with more natural vegetation, so the pictures obtained from drones have problems such as unclear targets and too many irrelevant areas, which become the main factors affecting the effect of abnormality identification. Based on this, this paper proposes a method of image feature enhancement from the perspective of image processing, which can effectively improve the feature representation in the original image. Experiments are conducted on three datasets constructed by ourselves, and it can be seen that the image processing method proposed in this paper achieves good experimental results, which can effectively improve the detection effect of deep learning models on faulty equipment photos.
{"title":"A New Method for Feature Enhancement of Grid Equipment Images","authors":"Honghui Zhou, Ruyi Qin, Jian Wu, Ying Qian, Xiaoming Ju","doi":"10.1109/ICESIT53460.2021.9696469","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696469","url":null,"abstract":"With the continuous development of the state grid, power transmission equipment is also increasing, and how to efficiently inspect and maintain power transmission equipment has become a key concern in the industry. In order to reduce the consumption of manpower in the inspection process, the current method is mainly to send drones to take patrol photos and then use deep learning to identify faulty equipment. However, in the actual process, power transmission equipment is generally built in areas with more natural vegetation, so the pictures obtained from drones have problems such as unclear targets and too many irrelevant areas, which become the main factors affecting the effect of abnormality identification. Based on this, this paper proposes a method of image feature enhancement from the perspective of image processing, which can effectively improve the feature representation in the original image. Experiments are conducted on three datasets constructed by ourselves, and it can be seen that the image processing method proposed in this paper achieves good experimental results, which can effectively improve the detection effect of deep learning models on faulty equipment photos.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115902120","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696532
Ziqi Zhang
In recent years, generalized linear models have been widely used in auto insurance pricing, and some research results show that machine learning is better than generalized linear models in some aspects, but these results are only based on a single data set. In order to more comprehensively compare the effects of generalized linear models and machine learning methods on the problem of car insurance claim frequency prediction, a comparative test was carried out on 7 car insurance data sets, including deep learning, random forest, support vector machine, XGboost and other machine learning methods; Based on the same training set, establish different generalized linear models to predict the frequency of claims, select the best generalized linear model according to the minimum information criterion (AIC); obtain the best machine learning parameters and models through cross-validation tuning. The research results show that the prediction effect of XGboost on all data sets is consistently better than the generalized linear model; for some data sets with more independent variables and strong correlation between variables, the prediction effects of neural networks, deep learning and random forests Better than generalized linear models.
{"title":"Data Sets Modeling and Frequency Prediction via Machine Learning and Neural Network","authors":"Ziqi Zhang","doi":"10.1109/ICESIT53460.2021.9696532","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696532","url":null,"abstract":"In recent years, generalized linear models have been widely used in auto insurance pricing, and some research results show that machine learning is better than generalized linear models in some aspects, but these results are only based on a single data set. In order to more comprehensively compare the effects of generalized linear models and machine learning methods on the problem of car insurance claim frequency prediction, a comparative test was carried out on 7 car insurance data sets, including deep learning, random forest, support vector machine, XGboost and other machine learning methods; Based on the same training set, establish different generalized linear models to predict the frequency of claims, select the best generalized linear model according to the minimum information criterion (AIC); obtain the best machine learning parameters and models through cross-validation tuning. The research results show that the prediction effect of XGboost on all data sets is consistently better than the generalized linear model; for some data sets with more independent variables and strong correlation between variables, the prediction effects of neural networks, deep learning and random forests Better than generalized linear models.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124275991","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696550
Erxin Sun, Zongjuan Chen, Jianjun Cai
In this paper, the development status of vehicle-road collaboration is discussed in detail, and an intelligent networked vehicle-road collaborative cloud control platform architecture is proposed. Based on big data cluster architecture, vehicle-road collaborative perception and communication, 5G mobile communication, high-precision map, real-time edge computing and other key technologies. The platform realizes the storage, processing, management, analysis and display of the massive data generated by vehicle and road cooperation, it introduces in detail the platform functions such as vehicle intelligent manage and control, V2X comprehensive management, test operation management, data management and system management. Providing reliable basis for the prediction, perception, decision making and control of intelligent networked vehicles. It provides the platform support for the commercialization of the three-level test of intelligent networked vehicles
{"title":"Cloud Control Platform of Vehicle and Road Collaborative and its Implementation on Intelligent Networked Vehicles","authors":"Erxin Sun, Zongjuan Chen, Jianjun Cai","doi":"10.1109/ICESIT53460.2021.9696550","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696550","url":null,"abstract":"In this paper, the development status of vehicle-road collaboration is discussed in detail, and an intelligent networked vehicle-road collaborative cloud control platform architecture is proposed. Based on big data cluster architecture, vehicle-road collaborative perception and communication, 5G mobile communication, high-precision map, real-time edge computing and other key technologies. The platform realizes the storage, processing, management, analysis and display of the massive data generated by vehicle and road cooperation, it introduces in detail the platform functions such as vehicle intelligent manage and control, V2X comprehensive management, test operation management, data management and system management. Providing reliable basis for the prediction, perception, decision making and control of intelligent networked vehicles. It provides the platform support for the commercialization of the three-level test of intelligent networked vehicles","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124522062","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696595
Wu Jianyu, Hongli Zhang, Jianfei Wu
Despite the advantages of a fast switching speed and a low power consumption, intelligent switch chips as a controlled power supply chip need to be electromagnetic compatible due to the complex working environment. Either injection of electromagnetic interference or the transistor's own parasitic capacitance due to the change to the transistor state can result in chip failure. This paper will introduce a novel optimization strategy of reducing (Electromagnetic interference) EMI for an intelligent high side power switch. The proposed circuit is characterized by a differential voltage comparator for a better tolerance of interference and it also exploits the single-term conductivity of the diode to block noise. Experimental results show that the improved method can suppress the electromagnetic interference effectively and improve the anti-jamming ability without increasing the chip die area. It has a wide application potential in improving the reliability of chips.
{"title":"Blocking EMI Optimization of the Drive Circuit for an Intelligent High Side Power Switch","authors":"Wu Jianyu, Hongli Zhang, Jianfei Wu","doi":"10.1109/ICESIT53460.2021.9696595","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696595","url":null,"abstract":"Despite the advantages of a fast switching speed and a low power consumption, intelligent switch chips as a controlled power supply chip need to be electromagnetic compatible due to the complex working environment. Either injection of electromagnetic interference or the transistor's own parasitic capacitance due to the change to the transistor state can result in chip failure. This paper will introduce a novel optimization strategy of reducing (Electromagnetic interference) EMI for an intelligent high side power switch. The proposed circuit is characterized by a differential voltage comparator for a better tolerance of interference and it also exploits the single-term conductivity of the diode to block noise. Experimental results show that the improved method can suppress the electromagnetic interference effectively and improve the anti-jamming ability without increasing the chip die area. It has a wide application potential in improving the reliability of chips.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124559356","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696657
Kai Wu, Dingjiang Yan, Hongcheng Liao, Xiang Zhang, Q. Huang, Qian Zhang, Min Fu
Given the low efficiency of massive image data processing in actual business departments, image character recognition OCR (optical character recognition) based on deep learning neural networks is not high. Based on the above background, a text image data enhancement method based on Font-CycleGan is proposed to improve text recognition accuracy. Our goal is to generate the data of specific fonts for the original hidden word text samples through the font library and then enhance the data of the hidden word text through CycleGan to enrich the database of the hidden word text to improve the performance of the classifier and the accuracy of text recognition. We evaluate and compare the impact of traditional character recognition and font-cyclgan based data to enhance character recognition accuracy. The results show that the improvement effect of this method is more significant.
{"title":"Application of Data Augmentation of Rare Words Based on “Font-CycleGan” in Character Recognition","authors":"Kai Wu, Dingjiang Yan, Hongcheng Liao, Xiang Zhang, Q. Huang, Qian Zhang, Min Fu","doi":"10.1109/ICESIT53460.2021.9696657","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696657","url":null,"abstract":"Given the low efficiency of massive image data processing in actual business departments, image character recognition OCR (optical character recognition) based on deep learning neural networks is not high. Based on the above background, a text image data enhancement method based on Font-CycleGan is proposed to improve text recognition accuracy. Our goal is to generate the data of specific fonts for the original hidden word text samples through the font library and then enhance the data of the hidden word text through CycleGan to enrich the database of the hidden word text to improve the performance of the classifier and the accuracy of text recognition. We evaluate and compare the impact of traditional character recognition and font-cyclgan based data to enhance character recognition accuracy. The results show that the improvement effect of this method is more significant.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"291 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115132457","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：