Jun-E Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jun-E Liu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Fengping An
School of Physics and Electronic Electrical Engineering, Huaiyin Normal University, Huaian, China
7 shared publications - Lei Bai
Hebei IoT Monitoring Engineering Technology Research Center, North China Institute of Science and Technology, Beijing, China
1 shared publication - Lei Bai
Hebei IoT Monitoring Engineering Technology Research Center, North China Institute of Science and Technology, Langfang, HB 065201, China
1 shared publication
Latest Publications
- 13 August 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (21-23) , 33099-33114
Remote sensing image classification algorithm based on ridge wave sparse collaborative representation convolutional neural network
- 13 August 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (21-23) , 33099-33114
Remote sensing image classification algorithm based on ridge wave sparse collaborative representation convolutional neural network
- 1 February 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (10) , 15017-15039
Medical image segmentation algorithm based on multilayer boundary perception-self attention deep learning model
- 1 February 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (10) , 15017-15039
Medical image segmentation algorithm based on multilayer boundary perception-self attention deep learning model
- Open Access
- 28 January 2021
- Published by Wiley in Journal of Sensors
- Vol. 2021 (1)
Pedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction‐Multilayer Attention Mechanism Convolutional Neural Network
Pedestrian reidentification is a key technology in large‐scale distributed camera systems. It can quickly and efficiently detect and track target people in large‐scale distributed surveillance networks. The existing traditional pedestrian reidentification methods have problems such as low recognition accuracy, low calculation efficiency, and weak adaptive ability. Pedestrian reidentification algorithms based on deep learning have been widely used in the field of pedestrian reidentification due to their strong adaptive ability and high recognition accuracy. However, the pedestrian recognition method based on deep learning has the following problems: first, during the learning process of the deep learning model, the initial value of the convolution kernel is usually randomly assigned, which makes the model learning process easily fall into a local optimum. The second is that the model parameter learning method based on the gradient descent method exhibits gradient dispersion. The third is that the information transfer of pedestrian reidentification sequence images is not considered. In view of these issues, this paper first examines the feature map matrix from the original image through a deconvolution neural network, uses it as a convolution kernel, and then performs layer‐by‐layer convolution and pooling operations. Then, the second derivative information of the error function is directly obtained without calculating the Hessian matrix, and the momentum coefficient is used to improve the convergence of the backpropagation, thereby suppressing the gradient dispersion phenomenon. At the same time, to solve the problem of information transfer of pedestrian reidentification sequence images, this paper proposes a memory network model based on a multilayer attention mechanism, which uses the network to effectively store image visual information and pedestrian behavior information, respectively. It can solve the problem of information transmission. Based on the above ideas, this paper proposes a pedestrian reidentification algorithm based on deconvolution network feature extraction‐multilayer attention mechanism convolutional neural network. Experiments are performed on the related data sets using this algorithm and other major popular human reidentification algorithms. The results show that the pedestrian reidentification method proposed in this paper not only has strong adaptive ability but also has significantly improved average recognition accuracy and rank‐1 matching rate compared with other mainstream methods.
- 28 January 2021
- Published by Wiley in Journal of Sensors
- Vol. 2021 (1)
Open AccessPedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction‐Multilayer Attention Mechanism Convolutional Neural Network
Pedestrian reidentification is a key technology in large‐scale distributed camera systems. It can quickly and efficiently detect and track target people in large‐scale distributed surveillance networks. The existing traditional pedestrian reidentification methods have problems such as low recognition accuracy, low calculation efficiency, and weak adaptive ability. Pedestrian reidentification algorithms based on deep learning have been widely used in the field of pedestrian reidentification due to their strong adaptive ability and high recognition accuracy. However, the pedestrian recognition method based on deep learning has the following problems: first, during the learning process of the deep learning model, the initial value of the convolution kernel is usually randomly assigned, which makes the model learning process easily fall into a local optimum. The second is that the model parameter learning method based on the gradient descent method exhibits gradient dispersion. The third is that the information transfer of pedestrian reidentification sequence images is not considered. In view of these issues, this paper first examines the feature map matrix from the original image through a deconvolution neural network, uses it as a convolution kernel, and then performs layer‐by‐layer convolution and pooling operations. Then, the second derivative information of the error function is directly obtained without calculating the Hessian matrix, and the momentum coefficient is used to improve the convergence of the backpropagation, thereby suppressing the gradient dispersion phenomenon. At the same time, to solve the problem of information transfer of pedestrian reidentification sequence images, this paper proposes a memory network model based on a multilayer attention mechanism, which uses the network to effectively store image visual information and pedestrian behavior information, respectively. It can solve the problem of information transmission. Based on the above ideas, this paper proposes a pedestrian reidentification algorithm based on deconvolution network feature extraction‐multilayer attention mechanism convolutional neural network. Experiments are performed on the related data sets using this algorithm and other major popular human reidentification algorithms. The results show that the pedestrian reidentification method proposed in this paper not only has strong adaptive ability but also has significantly improved average recognition accuracy and rank‐1 matching rate compared with other mainstream methods.
- 3 January 2021
- Published by Springer Nature in The Visual Computer
- Vol. 38 (2) , 541-553
Object recognition algorithm based on optimized nonlinear activation function-global convolutional neural network
- 3 January 2021
- Published by Springer Nature in The Visual Computer
- Vol. 38 (2) , 541-553
Object recognition algorithm based on optimized nonlinear activation function-global convolutional neural network
- Open Access
- 15 May 2020
- Published by Wiley in Complexity
- Vol. 2020, 1-13
Medical Image Segmentation Algorithm Based on Optimized Convolutional Neural Network-Adaptive Dropout Depth Calculation
Medical image segmentation is a key technology for image guidance. Therefore, the advantages and disadvantages of image segmentation play an important role in image-guided surgery. Traditional machine learning methods have achieved certain beneficial effects in medical image segmentation, but they have problems such as low classification accuracy and poor robustness. Deep learning theory has good generalizability and feature extraction ability, which provides a new idea for solving medical image segmentation problems. However, deep learning has problems in terms of its application to medical image segmentation: one is that the deep learning network structure cannot be constructed according to medical image characteristics; the other is that the generalizability y of the deep learning model is weak. To address these issues, this paper first adapts a neural network to medical image features by adding cross-layer connections to a traditional convolutional neural network. In addition, an optimized convolutional neural network model is established. The optimized convolutional neural network model can segment medical images using the features of two scales simultaneously. At the same time, to solve the generalizability problem of the deep learning model, an adaptive distribution function is designed according to the position of the hidden layer, and then the activation probability of each layer of neurons is set. This enhances the generalizability of the dropout model, and an adaptive dropout model is proposed. This model better addresses the problem of the weak generalizability of deep learning models. Based on the above ideas, this paper proposes a medical image segmentation algorithm based on an optimized convolutional neural network with adaptive dropout depth calculation. An ultrasonic tomographic image and lumbar CT medical image were separately segmented by the method of this paper. The experimental results show that not only are the segmentation effects of the proposed method improved compared with those of the traditional machine learning and other deep learning methods but also the method has a high adaptive segmentation ability for various medical images. The research work in this paper provides a new perspective for research on medical image segmentation.
- 15 May 2020
- Published by Wiley in Complexity
- Vol. 2020, 1-13
Open AccessMedical Image Segmentation Algorithm Based on Optimized Convolutional Neural Network-Adaptive Dropout Depth Calculation
Medical image segmentation is a key technology for image guidance. Therefore, the advantages and disadvantages of image segmentation play an important role in image-guided surgery. Traditional machine learning methods have achieved certain beneficial effects in medical image segmentation, but they have problems such as low classification accuracy and poor robustness. Deep learning theory has good generalizability and feature extraction ability, which provides a new idea for solving medical image segmentation problems. However, deep learning has problems in terms of its application to medical image segmentation: one is that the deep learning network structure cannot be constructed according to medical image characteristics; the other is that the generalizability y of the deep learning model is weak. To address these issues, this paper first adapts a neural network to medical image features by adding cross-layer connections to a traditional convolutional neural network. In addition, an optimized convolutional neural network model is established. The optimized convolutional neural network model can segment medical images using the features of two scales simultaneously. At the same time, to solve the generalizability problem of the deep learning model, an adaptive distribution function is designed according to the position of the hidden layer, and then the activation probability of each layer of neurons is set. This enhances the generalizability of the dropout model, and an adaptive dropout model is proposed. This model better addresses the problem of the weak generalizability of deep learning models. Based on the above ideas, this paper proposes a medical image segmentation algorithm based on an optimized convolutional neural network with adaptive dropout depth calculation. An ultrasonic tomographic image and lumbar CT medical image were separately segmented by the method of this paper. The experimental results show that not only are the segmentation effects of the proposed method improved compared with those of the traditional machine learning and other deep learning methods but also the method has a high adaptive segmentation ability for various medical images. The research work in this paper provides a new perspective for research on medical image segmentation.
- Open Access
- 31 January 2020
- Published by Wiley in Scientific Programming
- Vol. 2020, 1-14
Image Classification Algorithm Based on Deep Learning-Kernel Function
Although the existing traditional image classification methods have been widely applied in practical problems, there are some problems in the application process, such as unsatisfactory effects, low classification accuracy, and weak adaptive ability. This method separates image feature extraction and classification into two steps for classification operation. The deep learning model has a powerful learning ability, which integrates the feature extraction and classification process into a whole to complete the image classification test, which can effectively improve the image classification accuracy. However, this method has the following problems in the application process: first, it is impossible to effectively approximate the complex functions in the deep learning model. Second, the deep learning model comes with a low classifier with low accuracy. So, this paper introduces the idea of sparse representation into the architecture of the deep learning network and comprehensively utilizes the sparse representation of well multidimensional data linear decomposition ability and the deep structural advantages of multilayer nonlinear mapping to complete the complex function approximation in the deep learning model. And a sparse representation classification method based on the optimized kernel function is proposed to replace the classifier in the deep learning model, thereby improving the image classification effect. Therefore, this paper proposes an image classification algorithm based on the stacked sparse coding depth learning model-optimized kernel function nonnegative sparse representation. The experimental results show that the proposed method not only has a higher average accuracy than other mainstream methods but also can be good adapted to various image databases. Compared with other deep learning methods, it can better solve the problems of complex function approximation and poor classifier effect, thus further improving image classification accuracy.
- 31 January 2020
- Published by Wiley in Scientific Programming
- Vol. 2020, 1-14
Open AccessImage Classification Algorithm Based on Deep Learning-Kernel Function
Although the existing traditional image classification methods have been widely applied in practical problems, there are some problems in the application process, such as unsatisfactory effects, low classification accuracy, and weak adaptive ability. This method separates image feature extraction and classification into two steps for classification operation. The deep learning model has a powerful learning ability, which integrates the feature extraction and classification process into a whole to complete the image classification test, which can effectively improve the image classification accuracy. However, this method has the following problems in the application process: first, it is impossible to effectively approximate the complex functions in the deep learning model. Second, the deep learning model comes with a low classifier with low accuracy. So, this paper introduces the idea of sparse representation into the architecture of the deep learning network and comprehensively utilizes the sparse representation of well multidimensional data linear decomposition ability and the deep structural advantages of multilayer nonlinear mapping to complete the complex function approximation in the deep learning model. And a sparse representation classification method based on the optimized kernel function is proposed to replace the classifier in the deep learning model, thereby improving the image classification effect. Therefore, this paper proposes an image classification algorithm based on the stacked sparse coding depth learning model-optimized kernel function nonnegative sparse representation. The experimental results show that the proposed method not only has a higher average accuracy than other mainstream methods but also can be good adapted to various image databases. Compared with other deep learning methods, it can better solve the problems of complex function approximation and poor classifier effect, thus further improving image classification accuracy.
- Open Access
- 20 December 2019
- Published by Wiley in Journal of Sensors
- Vol. 2019, 1-12
Image Encryption Algorithm Based on Adaptive Wavelet Chaos
Images, as one of the important carriers for information exchange, play an important role in work and daily life. Image encryption technology has received a lot of attention, and varieties of encryption technologies for images have emerged. Early image encryption technologies have shortcomings such as simple algorithm structure, small key space, and poor resistance to plaintext attacks. These algorithms have been unable to meet the needs of information security at this stage. Based on the wavelet algorithm, chaos algorithm, and cyclic encryption algorithm, combined with frequency domain encryption and spatial domain encryption, a digital image encryption algorithm based on adaptive wavelet is proposed in this paper. In terms of frequency, this paper enhances the adaptive ability of the wavelet algorithm by convex optimization-particle swarm optimization (PSO). At the same time, the chaotic algorithm is used to scramble the low-frequency coefficients. In the aspect of airspace, this paper uses the block-encryption adaptive encryption algorithm to rescramble the wavelet-reconstructed image. And the SHA-1 algorithm is introduced into the plaintext image generation key sequence as a cyclic index value for cyclic encryption. The key composition of the encryption algorithm proposed in this paper is complex, and the idea of a one-time pad is used, which makes the improved algorithm increase the key space and improve the ability to resist the choice of plaintext attack. In each cyclic encryption of the airspace, mutual encryption is performed by image subblocks, and the algorithm adaptability is improved. Through the experimental test of statistical characteristics, key space, and key sensitivity, the encryption performance of the algorithm is verified, and it has strong antiattack and interference ability. It is a relatively secure encryption algorithm.
- 20 December 2019
- Published by Wiley in Journal of Sensors
- Vol. 2019, 1-12
Open AccessImage Encryption Algorithm Based on Adaptive Wavelet Chaos
Images, as one of the important carriers for information exchange, play an important role in work and daily life. Image encryption technology has received a lot of attention, and varieties of encryption technologies for images have emerged. Early image encryption technologies have shortcomings such as simple algorithm structure, small key space, and poor resistance to plaintext attacks. These algorithms have been unable to meet the needs of information security at this stage. Based on the wavelet algorithm, chaos algorithm, and cyclic encryption algorithm, combined with frequency domain encryption and spatial domain encryption, a digital image encryption algorithm based on adaptive wavelet is proposed in this paper. In terms of frequency, this paper enhances the adaptive ability of the wavelet algorithm by convex optimization-particle swarm optimization (PSO). At the same time, the chaotic algorithm is used to scramble the low-frequency coefficients. In the aspect of airspace, this paper uses the block-encryption adaptive encryption algorithm to rescramble the wavelet-reconstructed image. And the SHA-1 algorithm is introduced into the plaintext image generation key sequence as a cyclic index value for cyclic encryption. The key composition of the encryption algorithm proposed in this paper is complex, and the idea of a one-time pad is used, which makes the improved algorithm increase the key space and improve the ability to resist the choice of plaintext attack. In each cyclic encryption of the airspace, mutual encryption is performed by image subblocks, and the algorithm adaptability is improved. Through the experimental test of statistical characteristics, key space, and key sensitivity, the encryption performance of the algorithm is verified, and it has strong antiattack and interference ability. It is a relatively secure encryption algorithm.