发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2020 4th International Conference on Digital Signal Processing最新文献

筛选
英文 中文
Research on Scene Text Recognition Algorithm Basedon Improved CRNN 基于改进CRNN的场景文本识别算法研究
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408166
Yilin Chen, Juan Yang
{"title":"Research on Scene Text Recognition Algorithm Basedon Improved CRNN","authors":"Yilin Chen, Juan Yang","doi":"10.1145/3408127.3408166","DOIUrl":"https://doi.org/10.1145/3408127.3408166","url":null,"abstract":"Image-based sequence recognition has always been a longstanding research topic in computer vision. Scene text recognition is one of the most important and challenging tasks in image-based sequence recognition. End-to-end scene text recognition based on deep learning now mainly transforms text recognition into sequence recognition problems. This paper improves the current advanced end-to-end trainable variable length recognition method CRNN [1]. Adding the IBN-Net [2] structure can improve the accuracy and generalization of the model without increasing the amount of calculation. Experiments in the public datasets ICDAR 2003 [3] and ICDAR 2013 [4] demonstrate the effectiveness of the proposed method. In addition, the proposed algorithm performs well in non-dictionary text recognition tasks, which clearly confirms its generalization.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122378637","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}
引用次数: 4
Research of Channel Estimation Method Based on Integrated Neural Network 基于集成神经网络的信道估计方法研究
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408135
Quan Yuan, Z. Fang
{"title":"Research of Channel Estimation Method Based on Integrated Neural Network","authors":"Quan Yuan, Z. Fang","doi":"10.1145/3408127.3408135","DOIUrl":"https://doi.org/10.1145/3408127.3408135","url":null,"abstract":"In order to solve the problem that noise and signal interference have an effect on the channel estimation of receiver, a channel estimation method based on integrated neural network has been proposed in this paper. Firstly, improved neural network would be used to extract nonlinear relationship between pilot signal with noise and original pilot signal. Secondly, the integrated neural network model would be obtained by selective integrating according to diversity factor, then channel estimation results could be obtained by model. Compared with the traditional methods, not only this method could reduce the computational complexity and obtain more accurate channel estimation results to reduce the bit error rate of communication system, but also reduce the cost of pilot and increase the bandwidth utilization rate. The simulation results show that the mean square error of channel estimation and bit error rate of communication are reduced by about 5% and 3% respectively, when compared with the traditional channel estimation method under the same signal-to-noise ratio.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127846852","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}
引用次数: 0
Deep Learning Achieves Super-resolution in Digital Holography 深度学习实现数字全息的超分辨率
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408195
Z. Zhong, Qi Cong, Mingguang Shan
{"title":"Deep Learning Achieves Super-resolution in Digital Holography","authors":"Z. Zhong, Qi Cong, Mingguang Shan","doi":"10.1145/3408127.3408195","DOIUrl":"https://doi.org/10.1145/3408127.3408195","url":null,"abstract":"Digital holographic microscopy is a non-contact, full-field quantitative measurement and unlabeled fast 3D measurement method. During the recording process of holograms, high frequency information is lost due to interference from external factors and human factors. In this paper, an end-to-end deep learning algorithm is adopted to realize the super-resolution of digital holographic imaging. We can conduct high-resolution reconstruction from a low-resolution hologram without any prior information. This method can not only improve the detail information of the image, but also avoid autofocusing and phase recovery in the process of holographic reconstruction.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131390629","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}
引用次数: 0
Calibration Method of Multi-Channel based on Steepest Descent 基于最陡下降的多通道标定方法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408136
Shuqing Lin, Hongtao Li, Tianhao He
{"title":"Calibration Method of Multi-Channel based on Steepest Descent","authors":"Shuqing Lin, Hongtao Li, Tianhao He","doi":"10.1145/3408127.3408136","DOIUrl":"https://doi.org/10.1145/3408127.3408136","url":null,"abstract":"Inherent amplitude and phase differences between channels can greatly affects the system performance and many methods are proposed to fix this problem. However, the algorithm proposed in this paper ensures higher accuracy, flexibility and a simple structure for implementation. Following the least-mean-square (LMS) algorithm, this method is derived from the steepest descent algorithm to generate coefficients for channel calibration. The channel imbalance due to the circuit character differences can thus be greatly reduced by weighing the coefficient. For radar systems using linear frequency modulation (LFM) or sine wave, the amplitude and phase error can be reduced to 10-13 deg under different circumstances. Meanwhile, this method still has high performance when the signal to noise ratio (SNR) of signals is low. Its implementation in Field Programmable Gate Array (FPGA) also consumes less resources and successfully calibrated the imbalance between channels for a 32-channel radar system.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133982717","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}
引用次数: 0
FPGA Implementation for a Chaotic Digital Receiver Using Duffing Oscillators Array 基于Duffing振荡器阵列的混沌数字接收机的FPGA实现
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408163
Yongqing Fu, M. Hu, Yanan Li
{"title":"FPGA Implementation for a Chaotic Digital Receiver Using Duffing Oscillators Array","authors":"Yongqing Fu, M. Hu, Yanan Li","doi":"10.1145/3408127.3408163","DOIUrl":"https://doi.org/10.1145/3408127.3408163","url":null,"abstract":"Chaotic signal is suitable for secure communication because of its concealment, unpredictability, high complexity and easy implementation. This paper aims for the complete FPGA implementation to enable hardware design of the chaotic digital receiver that using Duffing oscillator's array operating at the same frequency. Taking account the time-domain signal of chaotic Duffing oscillator has concealment and noise-like characteristics; it can be used to construct more secure communication information in signal modulation. During demodulation, we utilized the amplitude sensitivity of the signal and shielded its phase sensitivity by using Duffing oscillators array, so that it can demodulate binary chaotic signal with arbitrary phases. This paper analyzed the response of Duffing oscillator to chaotic signal. A Duffing oscillators array is used to receive chaotic digital signal and the fourth-order Runge-Kutta algorithm is introduced to solve the Duffing equation. Under the condition of conventional receiver, a Duffing oscillator optimization is added to improve the receiver's overall performance. Finally, a chaotic digital receiver of Duffing oscillator based on FPGA was completed, and the result, obtained using the ModelSim simulation platform and SignalTap II tool, indicates the correction of this receiver.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123738076","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}
引用次数: 0
Deep-learning-enhanced Digital Holographic Autofocus Imaging 深度学习增强数字全息自动对焦成像
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408194
Yang Zhang, Hongru Wang, Mingguang Shan
{"title":"Deep-learning-enhanced Digital Holographic Autofocus Imaging","authors":"Yang Zhang, Hongru Wang, Mingguang Shan","doi":"10.1145/3408127.3408194","DOIUrl":"https://doi.org/10.1145/3408127.3408194","url":null,"abstract":"Digital holography can achieve automatic focusing and quantitative imaging in the whole field of view, and has been widely used in imaging measurement tasks. Conventional digital holographic autofocusing algorithms are usually iterative approaches with time-consuming computational process. In recent years, deep learning technology has been applied in digital holography. However, most current findings about this field are deep learning algorithms dealing with partial operations of digital holographic reconstruction, where angular spectrum propagation and background images are still needed in reconstruction. Inspired by U-Net and residual network (ResNet), a new convolutional neural network (CNN) is proposed in this paper to realize digital holographic autofocus imaging. After proper training, the proposed CNN can obtain the focused reconstructed results by performing a feed forward propagation, and no background images are needed in reconstruction process.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130700049","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}
引用次数: 4
An End-to-End Quantization Framework for Fixed Point Fast Fourier Transform Hardware Implementation via Deep Neural Network 基于深度神经网络的定点快速傅立叶变换硬件实现的端到端量化框架
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408187
Wenqian Cui, Shunqing Zhang, Zhiyong Chen, Shan Cao, Shugong Xu
{"title":"An End-to-End Quantization Framework for Fixed Point Fast Fourier Transform Hardware Implementation via Deep Neural Network","authors":"Wenqian Cui, Shunqing Zhang, Zhiyong Chen, Shan Cao, Shugong Xu","doi":"10.1145/3408127.3408187","DOIUrl":"https://doi.org/10.1145/3408127.3408187","url":null,"abstract":"Fast Fourier Transform (FFT) plays an important role in signal processing nowadays. The quantization problem of sensed/sampled information has been revealed recently. In this paper, we present an end-to-end quantization framework via deep neural networks (DNNs). We have jointly optimized the system of signal quantization and de-quantization, and applied this system before fixed point FFT operation. The system can extract the features of the signal and reduce the hardware consumption of signal processing. Through numerous experiment, we find that the FFT calculation error of our quantization system is not smaller than results of uniform quantization and we analyzed underlying reasons. The designs of system brings a lot of new ideas to the future work. Our quantization system based on DNN can be used not only in FFT calculation, but also in other linear/non-linear symmetric operations.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129519765","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}
引用次数: 1
FPGA Implementation of Quaternary Signal Transmitter Based on Duffing Oscillator 基于Duffing振荡器的四元信号发射机的FPGA实现
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408172
Yongqing Fu, Rui Shao, Yanan Li
{"title":"FPGA Implementation of Quaternary Signal Transmitter Based on Duffing Oscillator","authors":"Yongqing Fu, Rui Shao, Yanan Li","doi":"10.1145/3408127.3408172","DOIUrl":"https://doi.org/10.1145/3408127.3408172","url":null,"abstract":"Chaotic communication uses chaotic signals as carrier instead of sine carrier, and the waveform of chaotic signals is similar to noise signals, even if the signals are intercepted, signals usually are treated as noise by some people. The use of chaotic communication can make information more secure. The Duffing system is one of the chaotic systems. The state of the system is extremely sensitive to the outside world. When the external signal changes, its state transition is obvious, and it can be distinguished by the phase trajectory of the state. Paper implements design and realization of quadrature chaotic modulation transmitter of the Duffing oscillator based on FPGA. On the software simulink platform, the theoretical model is validated to determine the value of the relevant parameters. In terms of FPGA, in order to solve the nonlinear Duffing equation, the Fourth-order Runge Kutta method is used.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121730557","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}
引用次数: 0
Target Detection using Polarimetric Distributed MIMO Radar in Heterogeneous Compound-Gaussian Clutter 极化分布MIMO雷达在非均匀复合高斯杂波条件下的目标检测
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408146
Zhiwen Liu, Yang Yang, Yan Xiang, K. Zhao, Shuli Shi, Yougen Xu
{"title":"Target Detection using Polarimetric Distributed MIMO Radar in Heterogeneous Compound-Gaussian Clutter","authors":"Zhiwen Liu, Yang Yang, Yan Xiang, K. Zhao, Shuli Shi, Yougen Xu","doi":"10.1145/3408127.3408146","DOIUrl":"https://doi.org/10.1145/3408127.3408146","url":null,"abstract":"A polarimetric distributed MIMO radar detector in heterogeneous compound Gaussian clutter is proposed. Based on the modified signal model of the polarimetric distributed MIMO radar, the inverse Gamma distribution assumption on the clutter texture and the complex inverse Wishart distribution assumption on the speckle clutter covariance matrix, the secondary data is used to obtain the maximum posteriori estimation of the texture so as to avoid the integral operation in test statistic. The Bayesian knowledge-aided polarimetric generalized likelihood ratio detector is then acquired. Simulation results show that the proposed detector has a better detection performance than the existing detector.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122673975","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}
引用次数: 0
Comparing MAV, Frequency Spectrum, and Wavelet Spectrum of sEMG Signals as Features for Simple CNN in Finger Motion Estimation 比较表面肌电信号的MAV、频谱和小波谱作为简单CNN在手指运动估计中的特征
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408182
K. Asai, Norio Takase
{"title":"Comparing MAV, Frequency Spectrum, and Wavelet Spectrum of sEMG Signals as Features for Simple CNN in Finger Motion Estimation","authors":"K. Asai, Norio Takase","doi":"10.1145/3408127.3408182","DOIUrl":"https://doi.org/10.1145/3408127.3408182","url":null,"abstract":"This paper presents the comparison of image features between the mean absolute values (MAVs) of amplitudes, the frequency spectra of Fourier transform, and the wavelet spectra for classifying surface electromyography (sEMG) signals with a simple convolutional neural network (CNN) in finger motion estimation. By using CNNs in the high-density sEMG method, high accuracy of gesture recognition was achieved; however, prohibitively high cost of sensor devices makes the method too expensive for a widespread use. We used a low-cost commercially available device to estimate finger motion with the sparse multichannel sEMG method. Experiments of classifying sEMG signals into four types, thumb opened, thumb closed, fingers (excluding the thumb) opened, and fingers (excluding the thumb) closed, showed that the frequency spectra and the wavelet spectra used as feature sets improved the accuracy compared to the MAVs under the condition of turning the sensor device gradually around the forearm. It is considered that the wavelet spectrum keeps well the feature information for estimating finger motions with CNNs.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117316101","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}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书