Traffic signs are road facilities that use words or symbols to guide, restrict, warn or indicate information. Traffic signs are characterized by safety, striking setting, clear and bright. Setting traffic signs is an important measure to implement traffic management and ensure road traffic safety and smoothness. Drivers can know the road condition in front of them through traffic signs, so as to make adjustments. However, drivers often neglect traffic signs and misjudge traffic signs information because of their tired spirit, spiritual fluctuation, answering mobile phones during driving and bad weather, which will lead to serious traffic safety accidents. The purpose of the driver assistance system based on image recognition is to alert drivers through voice broadcasting and interface to avoid serious traffic accidents caused by ignoring traffic signs. After the driver opens the system, the system captures the road scene in front of him through the camera, and detects every frame of the image to determine whether there are traffic signs and what the content of the traffic signs are, and then alerts the driver through voice and image.
{"title":"Vehicle Auxiliary Driving System Based on Image Processing","authors":"Peng Li, Wentao Cheng, Ying Ding, Rong Wu, Zhengping Liu, Jinqing Zhan","doi":"10.1109/ICCC51575.2020.9345002","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345002","url":null,"abstract":"Traffic signs are road facilities that use words or symbols to guide, restrict, warn or indicate information. Traffic signs are characterized by safety, striking setting, clear and bright. Setting traffic signs is an important measure to implement traffic management and ensure road traffic safety and smoothness. Drivers can know the road condition in front of them through traffic signs, so as to make adjustments. However, drivers often neglect traffic signs and misjudge traffic signs information because of their tired spirit, spiritual fluctuation, answering mobile phones during driving and bad weather, which will lead to serious traffic safety accidents. The purpose of the driver assistance system based on image recognition is to alert drivers through voice broadcasting and interface to avoid serious traffic accidents caused by ignoring traffic signs. After the driver opens the system, the system captures the road scene in front of him through the camera, and detects every frame of the image to determine whether there are traffic signs and what the content of the traffic signs are, and then alerts the driver through voice and image.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133908769","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344945
Shihang Lu, Ling Qiu, Xiao Liang
This paper investigates a downlink unmanned aerial vehicle (UAV)-enabled simultaneous wireless information and power transfer (SWIPT) system, in which a rotary-wing UAV is leveraged to charge distributed sensor nodes (SNs) and support information transmission simultaneously. Due to the practical hardware limitation, the dynamic power splitting (DPS) scheme is considered. We aim to maximize the UAV energy efficiency (EE) over a finite mission/communication period, by jointly optimizing the UAV trajectory, transmit power, and the power splitting ratio at the SNs. However, the optimization problem is formulated as non-linear fractional programming and thus difficult to be solved directly. To tackle this problem, we propose an iterative algorithm based on Dinkelbach method and successive convex approximation (SCA) techniques. Numerical results show that the proposed design significantly outperforms the other benchmark schemes.
{"title":"Energy Efficient Trajectory and Communication Co-Design in UAV-enabled SWIPT Systems","authors":"Shihang Lu, Ling Qiu, Xiao Liang","doi":"10.1109/ICCC51575.2020.9344945","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344945","url":null,"abstract":"This paper investigates a downlink unmanned aerial vehicle (UAV)-enabled simultaneous wireless information and power transfer (SWIPT) system, in which a rotary-wing UAV is leveraged to charge distributed sensor nodes (SNs) and support information transmission simultaneously. Due to the practical hardware limitation, the dynamic power splitting (DPS) scheme is considered. We aim to maximize the UAV energy efficiency (EE) over a finite mission/communication period, by jointly optimizing the UAV trajectory, transmit power, and the power splitting ratio at the SNs. However, the optimization problem is formulated as non-linear fractional programming and thus difficult to be solved directly. To tackle this problem, we propose an iterative algorithm based on Dinkelbach method and successive convex approximation (SCA) techniques. Numerical results show that the proposed design significantly outperforms the other benchmark schemes.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134156422","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344905
Rongrong He, Yuping Gong, Wei Bai, Yangyang Li, Ximing Wang
When deploying communication systems, an accurate wireless propagation model is important to ensure the quality of service covering the region. Due to the complex radio environment, the traditional wireless propagation models need massive data for correction and calculation. To address this issue, this paper proposes a wireless propagation method to predict path loss. We use the random forest network structure to fit the complex model, accurately predicting the received signal power in the target area. To improve the training efficiency of the model, we construct the preliminary features according to the previous knowledge. A filtering feature selection method is adopted to select features as input of model. Evaluating the model on four typical terrains, the experiment results show that the proposed model outperforms the four existing models in all types of terrains.
{"title":"Random Forests Based Path Loss Prediction in Mobile Communication Systems","authors":"Rongrong He, Yuping Gong, Wei Bai, Yangyang Li, Ximing Wang","doi":"10.1109/ICCC51575.2020.9344905","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344905","url":null,"abstract":"When deploying communication systems, an accurate wireless propagation model is important to ensure the quality of service covering the region. Due to the complex radio environment, the traditional wireless propagation models need massive data for correction and calculation. To address this issue, this paper proposes a wireless propagation method to predict path loss. We use the random forest network structure to fit the complex model, accurately predicting the received signal power in the target area. To improve the training efficiency of the model, we construct the preliminary features according to the previous knowledge. A filtering feature selection method is adopted to select features as input of model. Evaluating the model on four typical terrains, the experiment results show that the proposed model outperforms the four existing models in all types of terrains.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131587949","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345291
Tongxin Wei, Qingbao Li, Jinjin Liu
2D face images represent faces with incomplete information. 3D face reconstruction from a single 2D image is a challenging problem with application value. The single feature extraction method distorts the generated 3D face image. In this paper, we use contour-based face segmentation method to reconstruct 3D face image. We focus on the edge and contour information of the face when using contour lines to segment the face. Different from the global 3D face reconstruction method, we combine the global and local face information to carry out 3D face reconstruction. Our method: First of all, we do contour segmentation for human faces and extract the features of the segmented images. Second, we learn the local binary features of each keypoint in a complete face image, then combine the features and use linear regression to detect the keypoints. Thirdly, we use Convolutional Neural Networks to learn the regression 3D Morphable Model coefficient and significantly improve the quality and efficiency of reconstruction. We regressed the coefficients of the 3D deformable model from 2D images to present face alignment for 3D face reconstruction. We carry out feature mapping between 2D face and 3D face image, and monitor and verify 3D face model through mapping relationship. Our method can not only reconstruct face images from all angles, but also reduce face deformities. We made face images fit better under different expressions and postures.
{"title":"CRNet:3D Face Reconstruction with Contour Map Regression Network","authors":"Tongxin Wei, Qingbao Li, Jinjin Liu","doi":"10.1109/ICCC51575.2020.9345291","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345291","url":null,"abstract":"2D face images represent faces with incomplete information. 3D face reconstruction from a single 2D image is a challenging problem with application value. The single feature extraction method distorts the generated 3D face image. In this paper, we use contour-based face segmentation method to reconstruct 3D face image. We focus on the edge and contour information of the face when using contour lines to segment the face. Different from the global 3D face reconstruction method, we combine the global and local face information to carry out 3D face reconstruction. Our method: First of all, we do contour segmentation for human faces and extract the features of the segmented images. Second, we learn the local binary features of each keypoint in a complete face image, then combine the features and use linear regression to detect the keypoints. Thirdly, we use Convolutional Neural Networks to learn the regression 3D Morphable Model coefficient and significantly improve the quality and efficiency of reconstruction. We regressed the coefficients of the 3D deformable model from 2D images to present face alignment for 3D face reconstruction. We carry out feature mapping between 2D face and 3D face image, and monitor and verify 3D face model through mapping relationship. Our method can not only reconstruct face images from all angles, but also reduce face deformities. We made face images fit better under different expressions and postures.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131628199","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345198
Zhe Li, Yusheng Yang
Differential frequency hopping (DFH) communication system is widely used in the field of confidential communication with strong anti-jamming ability. Linear frequency modulation (LFM) signal with a broadband non-stationary characteristic can cause a great influence on the DFH communication system. In order to solve the problem of anti LFM interference in DFH system, this paper proposal a LFM interference suppression algorithm which is based on FrFT(Fractional Fourier Transform). By combining different order in FrFT, the optimal order is extracted and the LFM interference signal is identified. Further LFM interference suppression is realized. The simulation results show that the algorithm can effectively mitigate LFM interference in DFH communication system to improve the SNR.
{"title":"LFM Interference Suppression Algorithm Based on FrFT","authors":"Zhe Li, Yusheng Yang","doi":"10.1109/ICCC51575.2020.9345198","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345198","url":null,"abstract":"Differential frequency hopping (DFH) communication system is widely used in the field of confidential communication with strong anti-jamming ability. Linear frequency modulation (LFM) signal with a broadband non-stationary characteristic can cause a great influence on the DFH communication system. In order to solve the problem of anti LFM interference in DFH system, this paper proposal a LFM interference suppression algorithm which is based on FrFT(Fractional Fourier Transform). By combining different order in FrFT, the optimal order is extracted and the LFM interference signal is identified. Further LFM interference suppression is realized. The simulation results show that the algorithm can effectively mitigate LFM interference in DFH communication system to improve the SNR.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128815009","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}
Task matching is an important part to realize task assignment in crowdsourcing computing. However, privacy of tasks and workers is usually ignored in most of exiting task matching schemes. To solve this issue, recently, Shu et al. proposed a privacy-preserving task matching with efficient revocation in Crowdsourcing (IEEE Transactions on Dependable and Secure Computing DOI 10.1109/TDSC.2018.2875682) to ensure privacy protection of tasks and workers and achieve the worker revocation. Their scheme had claimed to be selective IND-CKA secure, and realized efficient revocation of the worker. Unfortunately, in this work, by analyzing the security of Shu et al. scheme, we show that their scheme is insecure. It cannot really provide IND-CKA security and realize the revocation of the worker. This is to say, their scheme does not satisfy the confidentiality of keyword since an adversary can distinguish the ciphertexts of arbitrary keywords without trapdoor information. Finally, after the corresponding attacks are given, we analyze the reason to produce such attacks.
任务匹配是众包计算中实现任务分配的重要环节。然而，在现有的大多数任务匹配方案中，任务和工作者的隐私性往往被忽略。为了解决这一问题，最近Shu等人提出了一种Crowdsourcing中具有高效撤销的隐私保护任务匹配(IEEE Transactions on reliable and Secure Computing DOI 10.1109/TDSC.2018.2875682)，以确保任务和工作人员的隐私保护，实现工作人员的撤销。他们的方案声称是选择性IND-CKA安全的，并实现了工人的有效撤销。不幸的是，在这项工作中，通过分析Shu等人方案的安全性，我们表明他们的方案是不安全的。它不能真正提供IND-CKA安全性和实现工作者的撤销。也就是说，他们的方案不满足关键字的机密性，因为攻击者可以在没有陷阱门信息的情况下区分任意关键字的密文。最后，在给出了相应的攻击后，分析了产生这些攻击的原因。
{"title":"On the Security of a Proxy-free Privacy-preserving Task Matching with Efficient Revocation","authors":"Jianhong Zhang, Zian Yan, Zhaorui Deng, Haoting Han, Jing Cao, Zhengtao Jiang","doi":"10.1109/ICCC51575.2020.9344933","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344933","url":null,"abstract":"Task matching is an important part to realize task assignment in crowdsourcing computing. However, privacy of tasks and workers is usually ignored in most of exiting task matching schemes. To solve this issue, recently, Shu et al. proposed a privacy-preserving task matching with efficient revocation in Crowdsourcing (IEEE Transactions on Dependable and Secure Computing DOI 10.1109/TDSC.2018.2875682) to ensure privacy protection of tasks and workers and achieve the worker revocation. Their scheme had claimed to be selective IND-CKA secure, and realized efficient revocation of the worker. Unfortunately, in this work, by analyzing the security of Shu et al. scheme, we show that their scheme is insecure. It cannot really provide IND-CKA security and realize the revocation of the worker. This is to say, their scheme does not satisfy the confidentiality of keyword since an adversary can distinguish the ciphertexts of arbitrary keywords without trapdoor information. Finally, after the corresponding attacks are given, we analyze the reason to produce such attacks.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134641658","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345127
Quan Zhou, Yonggui Li, Yingtao Niu, Zichao Qin, Long Zhao, Junwei Wang
In this paper, we investigate the problem of anti-jamming communication in multi-user scenarios. The Markov game framework is introduced to model and analyze the anti-jamming problem, and a joint multi-agent anti-jamming algorithm (JMAA) is proposed to obtain the optimal anti-jamming strategy. In intelligent dynamic jamming environment, the JMAA adopts multi-agent reinforcement learning (MARL) to make on-line channel selection, which can effectively tackle the external malicious jamming and avoid the internal mutual interference among users. The simulation results show that the proposed JMAA is superior to the frequency-hopping based method, the sensing-based method and the independent Q-learning method.
{"title":"“One Plus One is Greater Than Two”: Defeating Intelligent Dynamic Jamming with Collaborative Multi-agent Reinforcement Learning","authors":"Quan Zhou, Yonggui Li, Yingtao Niu, Zichao Qin, Long Zhao, Junwei Wang","doi":"10.1109/ICCC51575.2020.9345127","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345127","url":null,"abstract":"In this paper, we investigate the problem of anti-jamming communication in multi-user scenarios. The Markov game framework is introduced to model and analyze the anti-jamming problem, and a joint multi-agent anti-jamming algorithm (JMAA) is proposed to obtain the optimal anti-jamming strategy. In intelligent dynamic jamming environment, the JMAA adopts multi-agent reinforcement learning (MARL) to make on-line channel selection, which can effectively tackle the external malicious jamming and avoid the internal mutual interference among users. The simulation results show that the proposed JMAA is superior to the frequency-hopping based method, the sensing-based method and the independent Q-learning method.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131669454","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344987
Jingyi Xu
In the innovative method teaching courses of engineering colleges and universities, the application of UCD-based (User-Centered Design) design thinking methodology is becoming more extensive, and related research is booming. This research uses a self-developed online design thinking tool based on group collaboration to establish an analysis model of collaborative design in the tool. Through the analysis and research on the behavior data collected by the tool, the consensus of views, behavior patterns, and social relations are analyzed. Analysis examples and visual presentations are provided in these three dimensions. This shows that the application of design thinking collaborative online tools helps to establish a deeper understanding of group collaborative design and provides corresponding inspiration for teachers.
{"title":"Research and Applications of Classroom Group Collaboration in the Design Thinking Online Tool","authors":"Jingyi Xu","doi":"10.1109/ICCC51575.2020.9344987","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344987","url":null,"abstract":"In the innovative method teaching courses of engineering colleges and universities, the application of UCD-based (User-Centered Design) design thinking methodology is becoming more extensive, and related research is booming. This research uses a self-developed online design thinking tool based on group collaboration to establish an analysis model of collaborative design in the tool. Through the analysis and research on the behavior data collected by the tool, the consensus of views, behavior patterns, and social relations are analyzed. Analysis examples and visual presentations are provided in these three dimensions. This shows that the application of design thinking collaborative online tools helps to establish a deeper understanding of group collaborative design and provides corresponding inspiration for teachers.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131857518","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345194
Yipeng Du, Mingxi Yin, B. Jiao
This paper presents a deep learningbased classification model, referred to as InceptionSSVEP, for the steady-state visual evoked potential (SSVEP) based braincomputer interface (BCI). InceptionSSVEP adopts the main concept of Inception network, which is a deep learning model performing well in image classification tasks, to improve the performance of SSVEP classification. A multi-scale convolution structure is utilized in InceptionSSVEP to extract both long-term and short-term features of SSVEP signals, for the purpose of ensuring the comprehensiveness of high-dimensional features in extracted SSVEPs. Moreover, a data enhancement scheme is proposed to overcome the impact of SSVEP data amount limitation on classifier training. Results show that the proposed InceptionSSVEP outperforms other existing methods significantly, and validate that Inception networks have good transferability on SSVEP signals. Reasons for the good performance of InceptionSSVEP are analyzed using deep learning interpretability tools.
{"title":"InceptionSSVEP: A Multi-Scale Convolutional Neural Network for Steady-State Visual Evoked Potential Classification","authors":"Yipeng Du, Mingxi Yin, B. Jiao","doi":"10.1109/ICCC51575.2020.9345194","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345194","url":null,"abstract":"This paper presents a deep learningbased classification model, referred to as InceptionSSVEP, for the steady-state visual evoked potential (SSVEP) based braincomputer interface (BCI). InceptionSSVEP adopts the main concept of Inception network, which is a deep learning model performing well in image classification tasks, to improve the performance of SSVEP classification. A multi-scale convolution structure is utilized in InceptionSSVEP to extract both long-term and short-term features of SSVEP signals, for the purpose of ensuring the comprehensiveness of high-dimensional features in extracted SSVEPs. Moreover, a data enhancement scheme is proposed to overcome the impact of SSVEP data amount limitation on classifier training. Results show that the proposed InceptionSSVEP outperforms other existing methods significantly, and validate that Inception networks have good transferability on SSVEP signals. Reasons for the good performance of InceptionSSVEP are analyzed using deep learning interpretability tools.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115881355","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}
A novel filtering algorithm is proposed based on level set method (LSM) and linear time Euclidean distance transform (LET) algorithm in this paper, which has the property of shape retention and thus is suitable for post-processing of the initial contours for contacting instances in digital Pap image. As one of our contributions, we propose two new metrics based on the pixel-level average false positive rate and false negative rate that used by baseline method. A significant decrease in pixel-level average false positive rate (FP) by 62% can obtain by our proposed method. The result of quantitative and qualitative evaluation shows that our proposed shape retentive filtering algorithm (SRFA) can effectively filter out the false positive fragments of the initial instance contour of cervical cells from the ISBI-2014 dataset.
{"title":"A Shape Retentive Filtering Algorithm for Post-processing of Instance Contour of Cervical Cell Based on Level Set Method","authors":"Guangqi Liu, Qinghai Ding, Moran Ju, Haibo Luo, Tianming Jin, Miao He","doi":"10.1109/ICCC51575.2020.9345156","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345156","url":null,"abstract":"A novel filtering algorithm is proposed based on level set method (LSM) and linear time Euclidean distance transform (LET) algorithm in this paper, which has the property of shape retention and thus is suitable for post-processing of the initial contours for contacting instances in digital Pap image. As one of our contributions, we propose two new metrics based on the pixel-level average false positive rate and false negative rate that used by baseline method. A significant decrease in pixel-level average false positive rate (FP) by 62% can obtain by our proposed method. The result of quantitative and qualitative evaluation shows that our proposed shape retentive filtering algorithm (SRFA) can effectively filter out the false positive fragments of the initial instance contour of cervical cells from the ISBI-2014 dataset.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124094234","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：