Palmprint recognition, as a new biometrics technology, has attracted wide attention and research in recent years. Compared with other biometrics, palmprint has many unique advantages, including high recognition rate, low cost of acquisition equipment and good user acceptance. Firstly, this paper introduces the method of extracting the region of interest of palmprint image, the evaluation index of recognition system, the method of obtaining palmprint image by oneself and the commonly used palmprint databases. Then it introduces the method of identifying by extracting single palmprint features, and the method of identifying by fusing palmprint features and other biological features. What's more, it introduces the methods of feature matching, such as Fisher Linear Discriminant and Neural Network. In addition, it also introduces the application of palmprint recognition in life and the Android system developed in this paper. Finally, it makes the summary and prospect.
{"title":"A Summary of Palmprint Recognition Technology","authors":"Jingjing Wang, Xinman Zhang, Weiyong Gong, Xuebin Xu","doi":"10.1109/CRC.2019.00027","DOIUrl":"https://doi.org/10.1109/CRC.2019.00027","url":null,"abstract":"Palmprint recognition, as a new biometrics technology, has attracted wide attention and research in recent years. Compared with other biometrics, palmprint has many unique advantages, including high recognition rate, low cost of acquisition equipment and good user acceptance. Firstly, this paper introduces the method of extracting the region of interest of palmprint image, the evaluation index of recognition system, the method of obtaining palmprint image by oneself and the commonly used palmprint databases. Then it introduces the method of identifying by extracting single palmprint features, and the method of identifying by fusing palmprint features and other biological features. What's more, it introduces the methods of feature matching, such as Fisher Linear Discriminant and Neural Network. In addition, it also introduces the application of palmprint recognition in life and the Android system developed in this paper. Finally, it makes the summary and prospect.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"12 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123801075","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}
With the speech recognition research intensifying gradually in recent years, it is particularly important to grasp the research direction of this filed. This paper summarizes the theoretical algorithms in the development of speech recognition. Firstly, we introduce the specific process of speech recognition, including biometrics acquisition, preprocessing, feature extraction, biometrics pattern matching and recognition results. Besides, we emphatically introduce feature extraction and matching recognition algorithm. We also introduce the application platform, and give the specific application scenarios. Finally, we put forward the shortcomings of the research and prospect the future development trend.
{"title":"An Overview of Speech Recognition Technology","authors":"Xinman Zhang, Yurui Peng, Xuebin Xu","doi":"10.1109/CRC.2019.00025","DOIUrl":"https://doi.org/10.1109/CRC.2019.00025","url":null,"abstract":"With the speech recognition research intensifying gradually in recent years, it is particularly important to grasp the research direction of this filed. This paper summarizes the theoretical algorithms in the development of speech recognition. Firstly, we introduce the specific process of speech recognition, including biometrics acquisition, preprocessing, feature extraction, biometrics pattern matching and recognition results. Besides, we emphatically introduce feature extraction and matching recognition algorithm. We also introduce the application platform, and give the specific application scenarios. Finally, we put forward the shortcomings of the research and prospect the future development trend.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130186911","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}
The first part of this paper firstly theoretically presents first three industrial revolutions, main inventions and their impact on society and industry development. Then, Industry 4.0 is presented with focus on use of collaborative robots and their role is highlighted. Main part of the article focuses on the Laboratory of Industry 4.0 at University of West Bohemia, its key components, use in education and future plans.
{"title":"Role of Collaborative Robots in Industry 4.0 with Target on Education in Industrial Engineering","authors":"P. Poór, Tomáš Broum, J. Basl","doi":"10.1109/CRC.2019.00018","DOIUrl":"https://doi.org/10.1109/CRC.2019.00018","url":null,"abstract":"The first part of this paper firstly theoretically presents first three industrial revolutions, main inventions and their impact on society and industry development. Then, Industry 4.0 is presented with focus on use of collaborative robots and their role is highlighted. Main part of the article focuses on the Laboratory of Industry 4.0 at University of West Bohemia, its key components, use in education and future plans.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128459604","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}
Existing in-vehicle networks have various network systems such as LIN, CAN, FlexRay, and MOST. When new functions are added here, wires and ECUs are increased. Due to the requirements of these changing systems, the cost and complexity of communication efficiency of automotive networks is also increasing. Therefore, Ethernet is an alternative to integrate these complex in-vehicle network systems into one [1]. If the existing Ethernet is applied to the vehicle, various problems may occur. Therefore, the IEEE is standardizing the Ethernet optimized for vehicles. In this paper, we propose a new data transmission method of IEEE 802.3ch which is actively being standardized.
{"title":"Methods for Switching Multiple Speeds on a Single Link","authors":"Taehyoung Kim, Sungkwon Park","doi":"10.1109/CRC.2019.00037","DOIUrl":"https://doi.org/10.1109/CRC.2019.00037","url":null,"abstract":"Existing in-vehicle networks have various network systems such as LIN, CAN, FlexRay, and MOST. When new functions are added here, wires and ECUs are increased. Due to the requirements of these changing systems, the cost and complexity of communication efficiency of automotive networks is also increasing. Therefore, Ethernet is an alternative to integrate these complex in-vehicle network systems into one [1]. If the existing Ethernet is applied to the vehicle, various problems may occur. Therefore, the IEEE is standardizing the Ethernet optimized for vehicles. In this paper, we propose a new data transmission method of IEEE 802.3ch which is actively being standardized.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116237746","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}
Aiming at the problems of unimodal biometric recognition, such as easy interference and low recognition rate in practical application, a multimodal biometric recognition method is proposed in this paper. This method uses the second generation curvelet to extract face features and the 2D Gabor phase method to extract iris features. Then the two features are fused in the feature layer, and the fusion feature vectors are recognized by ELM classification. The experiments are carried out on the YaleB face dataset and CASIA-Iris-Lamp dataset. The experiment results show that the average accuracy of recognition of the algorithm can reach up to 99.74%, which is better than recognition methods of unimodal face and unimodal iris. The rate increases by 3.35%, which provides an effective model for multimodal biometric recognition.
{"title":"A Multimodal Biometric Recognition Algorithm Based on Second Generation Curvelet and 2D Gabor Filter","authors":"Xinman Zhang, Q. Xiong, Xuebin Xu","doi":"10.1109/CRC.2019.00031","DOIUrl":"https://doi.org/10.1109/CRC.2019.00031","url":null,"abstract":"Aiming at the problems of unimodal biometric recognition, such as easy interference and low recognition rate in practical application, a multimodal biometric recognition method is proposed in this paper. This method uses the second generation curvelet to extract face features and the 2D Gabor phase method to extract iris features. Then the two features are fused in the feature layer, and the fusion feature vectors are recognized by ELM classification. The experiments are carried out on the YaleB face dataset and CASIA-Iris-Lamp dataset. The experiment results show that the average accuracy of recognition of the algorithm can reach up to 99.74%, which is better than recognition methods of unimodal face and unimodal iris. The rate increases by 3.35%, which provides an effective model for multimodal biometric recognition.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116484588","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}
With the development of computer technology, sensor technology and information processing technology, image fusion, as a powerful tool of information fusion, has been widely used in automatic target recognition, military and medical image fields. This technology utilizes the complementarity of information advantages contained in each image to obtain a clear, comprehensive and accurate image description of the same scene through a certain algorithm. In this paper, we firstly summarized the research status of image fusion methods comprehensively. Secondly, the existing fusion methods of homogeneity and heterogeneity are summarized. Thirdly, several evaluation indexes are introduced. Finally, this paper points out the current problems of image fusion. In a word, the research of image fusion will still have a great development in the next few years.
{"title":"Research Status of Image Fusion: A Review","authors":"Xinman Zhang, Jiayu Zhang, Jie Kou, Xuebin Xu","doi":"10.1109/CRC.2019.00044","DOIUrl":"https://doi.org/10.1109/CRC.2019.00044","url":null,"abstract":"With the development of computer technology, sensor technology and information processing technology, image fusion, as a powerful tool of information fusion, has been widely used in automatic target recognition, military and medical image fields. This technology utilizes the complementarity of information advantages contained in each image to obtain a clear, comprehensive and accurate image description of the same scene through a certain algorithm. In this paper, we firstly summarized the research status of image fusion methods comprehensively. Secondly, the existing fusion methods of homogeneity and heterogeneity are summarized. Thirdly, several evaluation indexes are introduced. Finally, this paper points out the current problems of image fusion. In a word, the research of image fusion will still have a great development in the next few years.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116366856","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 this paper, an approach to watermarking images by embedding quick response (QR) code in a digital image based on the discrete cosine transform (DCT) is proposed. A block structure for manipulation is formed by partitioning the host image into non-overlapping blocks of 8'8 pixels and applying DCT to each block separately. A single watermark is embedded in different location blocks by quantization index modulation (QIM) to ensure that the watermark can still survive, even if the watermarked image is cropped over a large area. By employing the error correction mechanism of QR code, the information contained within a watermarked image can potentially be decoded. Experiment results indicate that the proposed scheme can withstand a variety of image processing attacks. Compared with the other watermarking scheme, the proposed method exhibits superior robustness and imperceptibility with the same payload capacity.
{"title":"A Blind Robust QR Code Watermarking Approach Based on DCT","authors":"Ling-Yuan Hsu, Hwai-Tsu Hu, Hsien-Hsin Chou","doi":"10.1109/CRC.2019.00043","DOIUrl":"https://doi.org/10.1109/CRC.2019.00043","url":null,"abstract":"In this paper, an approach to watermarking images by embedding quick response (QR) code in a digital image based on the discrete cosine transform (DCT) is proposed. A block structure for manipulation is formed by partitioning the host image into non-overlapping blocks of 8'8 pixels and applying DCT to each block separately. A single watermark is embedded in different location blocks by quantization index modulation (QIM) to ensure that the watermark can still survive, even if the watermarked image is cropped over a large area. By employing the error correction mechanism of QR code, the information contained within a watermarked image can potentially be decoded. Experiment results indicate that the proposed scheme can withstand a variety of image processing attacks. Compared with the other watermarking scheme, the proposed method exhibits superior robustness and imperceptibility with the same payload capacity.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124082696","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}
Extreme Learning Machine (ELM), as a new learning framework of Single Hidden Layer Feedforward Neural Network (SLFN), has become one of the hottest research directions in the field of artificial intelligence in recent years. It has been widely used in multiclass classification, human action recognition and other fields. ELM provides an efficient and unified learning framework for regression, classification, feature learning, and clustering. At the same time, ELM theories and algorithms have been improved for specific applications. This paper aims to provide a comprehensive review of existing research related to ELM. We first give an overview of the standard ELM. Then we discuss and analyze the typical variants of ELM, which are improved from different aspects, including models, strengths and weaknesses. Then we compare ELM with traditional methods in classification field and list the performance comparison between ELM and other deep network algorithms. Furthermore, the latest applications of ELM and its variants are summarized. Last but not least, we conclude the research trends of ELM variants mentioned above.
{"title":"An Overview of Extreme Learning Machine","authors":"Bohua Deng, Xinman Zhang, Weiyong Gong, Dongpeng Shang","doi":"10.1109/CRC.2019.00046","DOIUrl":"https://doi.org/10.1109/CRC.2019.00046","url":null,"abstract":"Extreme Learning Machine (ELM), as a new learning framework of Single Hidden Layer Feedforward Neural Network (SLFN), has become one of the hottest research directions in the field of artificial intelligence in recent years. It has been widely used in multiclass classification, human action recognition and other fields. ELM provides an efficient and unified learning framework for regression, classification, feature learning, and clustering. At the same time, ELM theories and algorithms have been improved for specific applications. This paper aims to provide a comprehensive review of existing research related to ELM. We first give an overview of the standard ELM. Then we discuss and analyze the typical variants of ELM, which are improved from different aspects, including models, strengths and weaknesses. Then we compare ELM with traditional methods in classification field and list the performance comparison between ELM and other deep network algorithms. Furthermore, the latest applications of ELM and its variants are summarized. Last but not least, we conclude the research trends of ELM variants mentioned above.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115509989","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}
With the development of the technology of energy storage system (ESS), the supercapacitors (SCs) are more widely used. The research focusing on the control technology of the state of health (SOH) and the state of charge (SOC) of SCs occupies a critical position. The definition of SOH and SOC and the functional relationship between SOH and SOC are described in this paper. Two commonly used control methods are listed. Then, the SOH control methods and the SOC control strategy of SCs in the last three years are cited and the characteristics of them are explained. At the end of the article, the future control methods of SOH and SOC for SCs are proposed.
{"title":"The Literature Review on Control Methods of SOH and SOC for Supercapacitors","authors":"Shuo Li, Kai Wang","doi":"10.1109/CRC.2019.00013","DOIUrl":"https://doi.org/10.1109/CRC.2019.00013","url":null,"abstract":"With the development of the technology of energy storage system (ESS), the supercapacitors (SCs) are more widely used. The research focusing on the control technology of the state of health (SOH) and the state of charge (SOC) of SCs occupies a critical position. The definition of SOH and SOC and the functional relationship between SOH and SOC are described in this paper. Two commonly used control methods are listed. Then, the SOH control methods and the SOC control strategy of SCs in the last three years are cited and the characteristics of them are explained. At the end of the article, the future control methods of SOH and SOC for SCs are proposed.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114410782","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}
Zhirong Wang, Chentao Mao, Zhang-wei Chen, Yuxiang Wang, Jun Zhou, Zhen Lu
Kinematic calibration plays a significant role in improving the robot positioning accuracy. Due to the mechanical factors such as joint deformation and heavy load, some errors are non-geometrical and nonlinear. In this case, a single kinematic calibration method is difficult to achieve good results especially for robots with heavy load. In this paper, a two-stage parameter identification method is proposed, which also deals with joint deformation and heavy load dependent errors to achieve a higher positioning accuracy. In the first stage, the method builds the kinematic model and identifies the geometric errors using the DH model and the distance model. In the second stage, the stiffness of the joint is analyzed and the positioning accuracy is improved on the robot dynamics. Finally, the experiments are carried out on the 6R robot with heavy load. The experimental results demonstrate the effectiveness and correctness of the method.
{"title":"A Two-Stage Parameter Identification Method and Compensation Verification for Heavy Load Robot","authors":"Zhirong Wang, Chentao Mao, Zhang-wei Chen, Yuxiang Wang, Jun Zhou, Zhen Lu","doi":"10.1109/CRC.2019.00017","DOIUrl":"https://doi.org/10.1109/CRC.2019.00017","url":null,"abstract":"Kinematic calibration plays a significant role in improving the robot positioning accuracy. Due to the mechanical factors such as joint deformation and heavy load, some errors are non-geometrical and nonlinear. In this case, a single kinematic calibration method is difficult to achieve good results especially for robots with heavy load. In this paper, a two-stage parameter identification method is proposed, which also deals with joint deformation and heavy load dependent errors to achieve a higher positioning accuracy. In the first stage, the method builds the kinematic model and identifies the geometric errors using the DH model and the distance model. In the second stage, the stiffness of the joint is analyzed and the positioning accuracy is improved on the robot dynamics. Finally, the experiments are carried out on the 6R robot with heavy load. The experimental results demonstrate the effectiveness and correctness of the method.","PeriodicalId":414946,"journal":{"name":"2019 4th International Conference on Control, Robotics and Cybernetics (CRC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121852047","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：