Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Advances in Image Enhancement
share announcement

Advances in Image Enhancement

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (1 March 2023) | Viewed by 43137

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editors

Dr. Chunwei Tian

E-Mail Website
Guest Editor
School of Software, Northwestern Polytechnical University, Xi'an 710072, China
Interests: deep learning; image restoration; video restoration; computer vision
Special Issues, Collections and Topics in MDPI journals
Dr. Wenqi Ren

E-Mail Website
Guest Editor
State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
Interests: computer vision; image processing; deep learning; image deblurring; image dehazing
Dr. Yudong Liang

E-Mail Website
Guest Editor
School of Computer and Information Technology, Shanxi University, Taiyuan, China
Interests: Image restoration; deep learning

Special Issue Information

Dear Colleagues,

In the era of the Internet of Things, images have played important roles in human–computer interactions, and with the arrival of big data technology, people have higher requirements of image qualities, especially ones collected in dark light. This can be addressed through the development of camera hardware quality, i.e., the resolution and exposure time of cameras, which may require high computational costs. As an alternative, image enhancement techniques can exact salient features to improve the quality of captured images according to the differences of diverse features, although they suffer from some challenges, i.e., a low contrast, artifacts and overexposed, thus, making it decidedly necessary to determine how to use advanced image enhancement techniques.

Topics of interest include, but are not limited to, the following:

  • Image enhancement
  • Image restoration
  • Machine learning and deep learning

Dr. Chunwei Tian
Dr. Wenqi Ren
Dr. Yudong Liang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • image enhancement
  • image restoration
  • computer vision
  • pattern recognition
  • machine learning
  • deep learning
  • feature fusion

Published Papers (20 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 7220 KiB  
Article
A Novel Denoising Algorithm Based on Wavelet and Non-Local Moment Mean Filtering
by Caixia Liu and Li Zhang
Electronics 2023, 12(6), 1461; https://doi.org/10.3390/electronics12061461 - 20 Mar 2023
Cited by 3 | Viewed by 2165
Abstract
Denoising is the basis and premise of image processing and an important part of image preprocessing. Denoising can effectively improve image quality, which contributes to subsequent image processing such as image segmentation, feature extraction, and so on. In this paper, we propose a [...] Read more.
Denoising is the basis and premise of image processing and an important part of image preprocessing. Denoising can effectively improve image quality, which contributes to subsequent image processing such as image segmentation, feature extraction, and so on. In this paper, we propose a novel image denoising method based on wavelet transform and nonlocal moment mean filtering approach (NMM). The noisy image is firstly denoised by a wavelet-based soft-thresholding denoising technique and NMM is then utilized to further eliminate the rest noises. Meanwhile, the fusion of moment invariants increases the robustness of our denoising algorithm due to the invariance of image scaling, translation, and rotation of color moments. Experiments show that our algorithm achieves a better denoising effect compared with some other denoising approaches. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

18 pages, 4014 KiB  
Article
Low-Illumination Road Image Enhancement by Fusing Retinex Theory and Histogram Equalization
by Yi Han, Xiangyong Chen, Yi Zhong, Yanqing Huang, Zhuo Li, Ping Han, Qing Li and Zhenhui Yuan
Electronics 2023, 12(4), 990; https://doi.org/10.3390/electronics12040990 - 16 Feb 2023
Cited by 2 | Viewed by 1920
Abstract
Low-illumination image enhancement can provide more information than the original image in low-light scenarios, e.g., nighttime driving. Traditional deep-learning-based image enhancement algorithms struggle to balance the performance between the overall illumination enhancement and local edge details, due to limitations of time and computational [...] Read more.
Low-illumination image enhancement can provide more information than the original image in low-light scenarios, e.g., nighttime driving. Traditional deep-learning-based image enhancement algorithms struggle to balance the performance between the overall illumination enhancement and local edge details, due to limitations of time and computational cost. This paper proposes a histogram equalization–multiscale Retinex combination approach (HE-MSR-COM) that aims at solving the blur edge problem of HE and the uncertainty in selecting parameters for image illumination enhancement in MSR. The enhanced illumination information is extracted from the low-frequency component in the HE-enhanced image, and the enhanced edge information is obtained from the high-frequency component in the MSR-enhanced image. By designing adaptive fusion weights of HE and MSR, the proposed method effectively combines enhanced illumination and edge information. The experimental results show that HE-MSR-COM improves the image quality by 23.95% and 10.6% in two datasets, respectively, compared with HE, contrast-limited adaptive histogram equalization (CLAHE), MSR, and gamma correction (GC). Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

13 pages, 2514 KiB  
Article
An Improved U-Net for Watermark Removal
by Lijun Fu, Bei Shi, Ling Sun, Jiawen Zeng, Deyun Chen, Hongwei Zhao and Chunwei Tian
Electronics 2022, 11(22), 3760; https://doi.org/10.3390/electronics11223760 - 16 Nov 2022
Cited by 5 | Viewed by 2574
Abstract
Convolutional neural networks (CNNs) with different layers have performed with excellent results in watermark removal. However, how to extract robust and effective features via CNNs of black box in watermark removal is very important. In this paper, we propose an improved watermark removal [...] Read more.
Convolutional neural networks (CNNs) with different layers have performed with excellent results in watermark removal. However, how to extract robust and effective features via CNNs of black box in watermark removal is very important. In this paper, we propose an improved watermark removal U-net (IWRU-net). Taking the robustness of obtained information into account, a serial architecture is designed to facilitate useful information for guaranteeing performance in watermark removal. Taking the problem of long-term dependency into account, U-nets based simple components are integrated into the serial architecture to extract more salient hierarchical information for addressing watermark removal problems. To increase the adaptability of IWRU-net to the real world, we use randomly distributed blind watermarks to implement a blind watermark removal model. The experiment results illustrate that the proposed method is superior to other popular watermark removal methods in terms of quantitative and qualitative evaluations. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

13 pages, 8786 KiB  
Article
Nighttime Image Dehazing Based on Multi-Scale Gated Fusion Network
by Bo Zhao, Han Wu, Zhiyang Ma, Huini Fu, Wenqi Ren and Guizhong Liu
Electronics 2022, 11(22), 3723; https://doi.org/10.3390/electronics11223723 - 14 Nov 2022
Cited by 3 | Viewed by 1313
Abstract
In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input, which can be adapted for nighttime image dehazing. The proposed algorithm hinges on a trainable neural network realized in an encoder–decoder architecture. The encoder is [...] Read more.
In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input, which can be adapted for nighttime image dehazing. The proposed algorithm hinges on a trainable neural network realized in an encoder–decoder architecture. The encoder is exploited to capture the context of the derived input images, while the decoder is employed to estimate the contribution of each input to the final dehazed result using the learned representations attributed to the encoder. The constructed network adopts a novel fusion-based strategy which derives three inputs from an original input by applying white balance (WB), contrast enhancing (CE), and gamma correction (GC). We compute pixel-wise confidence maps based on the appearance differences between these different inputs to blend the information of the derived inputs and preserve the regions with pleasant visibility. The final clear image is generated by gating the important features of the derived inputs. To train the network, we introduce a multi-scale approach to avoid the halo artifacts. Extensive experimental results on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against the state-of-the-art dehazing for nighttime images. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

21 pages, 7859 KiB  
Article
Research on Path-Planning Algorithm Integrating Optimization A-Star Algorithm and Artificial Potential Field Method
by Lisang Liu, Bin Wang and Hui Xu
Electronics 2022, 11(22), 3660; https://doi.org/10.3390/electronics11223660 - 09 Nov 2022
Cited by 15 | Viewed by 3451
Abstract
A fusion pathfinding algorithm based on the optimized A-star algorithm, the artificial potential field method and the least squares method is proposed to meet the performance requirements of path smoothing, response speed and computation time for the path planning of home cleaning robots. [...] Read more.
A fusion pathfinding algorithm based on the optimized A-star algorithm, the artificial potential field method and the least squares method is proposed to meet the performance requirements of path smoothing, response speed and computation time for the path planning of home cleaning robots. The fusion algorithm improves the operation rules of the traditional A-star algorithm, enabling global path planning to be completed quickly. At the same time, the operating rules of the artificial potential field method are changed according to the path points found by the optimal A-star algorithm, thus greatly avoiding the dilemma of being trapped in local optima. Finally, the least squares method is applied to fit the complete path to obtain a smooth path trajectory. Experiments show that the fusion algorithm significantly improves pathfinding efficiency and produces smoother and more continuous paths. Through simulation comparison experiments, the optimized A-star algorithm reduced path-planning time by 60% compared to the traditional A-star algorithm and 65.2% compared to the bidirectional A-star algorithm path-planning time. The fusion algorithm reduced the path-planning time by 65.2% compared to the ant colony algorithm and 83.64% compared to the RRT algorithm path-planning time. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

19 pages, 3467 KiB  
Article
The Systems Approach and Design Path of Electronic Bidding Systems Based on Blockchain Technology
by De Xu and Qing Yang
Electronics 2022, 11(21), 3501; https://doi.org/10.3390/electronics11213501 - 28 Oct 2022
Cited by 3 | Viewed by 2379
Abstract
The electronic tendering and bidding system has realized the digitalization, networking, and high integration of the whole process of tendering, bidding, bid evaluation, and contract, which has a wide range of applications. However, the trust degree, cooperation, and transaction efficiency of the parties [...] Read more.
The electronic tendering and bidding system has realized the digitalization, networking, and high integration of the whole process of tendering, bidding, bid evaluation, and contract, which has a wide range of applications. However, the trust degree, cooperation, and transaction efficiency of the parties involved in electronic bidding are low, and bidding fraud and collusion are forbidden repeatedly. Blockchain technology has the characteristics of decentralization, transparent transactions, traceability, non-tampering and forgery detection, and data security. This paper proposes a design path of an electronic bidding system based on blockchain technology, which aims to solve the efficiency, trust, and security of the electronic trading process. By building the underlying architecture platform of blockchain and embedding the business process of electronic bidding, this realizes the transparency, openness, and traceability during the whole process of electronic bidding. This paper uses qualitative and quantitative methods to prove the effectiveness of the system. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

14 pages, 9416 KiB  
Article
Semantic Segmentation of Side-Scan Sonar Images with Few Samples
by Dianyu Yang, Can Wang, Chensheng Cheng, Guang Pan and Feihu Zhang
Electronics 2022, 11(19), 3002; https://doi.org/10.3390/electronics11193002 - 22 Sep 2022
Cited by 4 | Viewed by 1719
Abstract
Underwater sensing and detection still rely heavily on acoustic equipment, known as sonar. As an imaging sonar, side-scan sonar can present a specific underwater situation in images, so the application scenario is comprehensive. However, the definition of side scan sonar is low; many [...] Read more.
Underwater sensing and detection still rely heavily on acoustic equipment, known as sonar. As an imaging sonar, side-scan sonar can present a specific underwater situation in images, so the application scenario is comprehensive. However, the definition of side scan sonar is low; many objects are in the picture, and the scale is enormous. Therefore, the traditional image segmentation method is not practical. In addition, data acquisition is challenging, and the sample size is insufficient. To solve these problems, we design a semantic segmentation model of side-scan sonar images based on a convolutional neural network, which is used to realize the semantic segmentation of side-scan sonar images with few training samples. The model uses a large convolution kernel to extract large-scale features, adds a parallel channel using a small convolution kernel to obtain multi-scale features, and uses SE-block to focus on the weight of different channels. Finally, we verify the effect of the model on the self-collected side-scan sonar dataset. Experimental results show that, compared with the traditional lightweight semantic segmentation network, the model’s performance is improved, and the number of parameters is relatively small, which is easy to transplant to AUV. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

16 pages, 4839 KiB  
Article
YKP-SLAM: A Visual SLAM Based on Static Probability Update Strategy for Dynamic Environments
by Lisang Liu, Jiangfeng Guo and Rongsheng Zhang
Electronics 2022, 11(18), 2872; https://doi.org/10.3390/electronics11182872 - 11 Sep 2022
Cited by 4 | Viewed by 1449
Abstract
Visual simultaneous localization and mapping (SLAM) algorithms in dynamic scenes can incorrectly add moving feature points to the camera pose calculation, which leads to low accuracy and poor robustness of pose estimation. In this paper, we propose a visual SLAM algorithm based on [...] Read more.
Visual simultaneous localization and mapping (SLAM) algorithms in dynamic scenes can incorrectly add moving feature points to the camera pose calculation, which leads to low accuracy and poor robustness of pose estimation. In this paper, we propose a visual SLAM algorithm based on object detection and static probability update strategy for dynamic scenes, named YKP-SLAM. Firstly, we use the YOLOv5 target detection algorithm and the improved K-means clustering algorithm to segment the image into static regions, suspicious static regions, and dynamic regions. Secondly, the static probability of feature points in each region is initialized and used as weights to solve for the initial camera pose. Then, we use the motion constraints and epipolar constraints to update the static probability of the feature points to solve the final pose of the camera. Finally, it is tested on the TUM RGB-D dataset. The results show that the YKP-SLAM algorithm proposed in this paper can effectively improve the pose estimation accuracy. Compared with the ORBSLAM2 algorithm, the absolute pose estimation accuracy is improved by 56.07% and 96.45% in low dynamic scenes and high dynamic scenes, respectively, and the best results are almost obtained compared with other advanced dynamic SLAM algorithms. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

15 pages, 4270 KiB  
Article
Power Line Scene Recognition Based on Convolutional Capsule Network with Image Enhancement
by Kuansheng Zou, Shuaiqiang Zhao and Zhenbang Jiang
Electronics 2022, 11(18), 2834; https://doi.org/10.3390/electronics11182834 - 08 Sep 2022
Cited by 2 | Viewed by 1415
Abstract
With the popularization of unmanned aerial vehicle (UAV) applications and the continuous development of the power grid network, identifying power line scenarios in advance is very important for the safety of low-altitude flight. The power line scene recognition (PLSR) under complex background environments [...] Read more.
With the popularization of unmanned aerial vehicle (UAV) applications and the continuous development of the power grid network, identifying power line scenarios in advance is very important for the safety of low-altitude flight. The power line scene recognition (PLSR) under complex background environments is particularly important. The complex background environment of power lines is usually mixed by forests, rivers, mountains, buildings, and so on. In these environments, the detection of slender power lines is particularly difficult. In this paper, a PLSR method of complex backgrounds based on the convolutional capsule network with image enhancement is proposed. The enhancement edge features of power line scenes based on the guided filter are fused with the convolutional capsule network framework. First, the guided filter is used to enhance the power line features in order to improve the recognition of the power line in the complex background. Second, the convolutional capsule network is used to extract the depth hierarchical features of the scene image of power lines. Finally, the output layer of the convolutional capsule network identifies the power line and non-power line scenes, and through the decoding layer, the power lines are reconstructed in the power line scene. Experimental results show that the accuracy of the proposed method obtains 97.43% on the public dataset. Robustness and generalization test results show that it has a good application prospect. Furthermore, the power lines can be accurately extracted from the complex backgrounds based on the reconstructed module. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

18 pages, 6156 KiB  
Article
An Improved RandLa-Net Algorithm Incorporated with NDT for Automatic Classification and Extraction of Raw Point Cloud Data
by Zhongli Ma, Jiadi Li, Jiajia Liu, Yuehan Zeng, Yi Wan and Jinyu Zhang
Electronics 2022, 11(17), 2795; https://doi.org/10.3390/electronics11172795 - 05 Sep 2022
Cited by 2 | Viewed by 1784
Abstract
A high-definition map of the autonomous driving system was built with the target points of interest, which were extracted from a large amount of unordered raw point cloud data obtained by Lidar. In order to better obtain the target points of interest, this [...] Read more.
A high-definition map of the autonomous driving system was built with the target points of interest, which were extracted from a large amount of unordered raw point cloud data obtained by Lidar. In order to better obtain the target points of interest, this paper proposes an improved RandLa-Net algorithm incorporated with NDT registration, which can be used to automatically classify and extract large-scale raw point clouds. First, based on the NDT registration algorithm, the frame-by-frame raw point cloud data were converted into a point cloud global map; then, the RandLa-Net network combined random sampling with a local feature sampler is used to classify discrete points in the point cloud map point by point. Finally, the corresponding point cloud data were extracted for the labels of interest through numpy indexing. Experiments on public datasets senmatic3D and senmatickitti show that the method has excellent accuracy and processing speed for the classification and extraction of large-scale point cloud data acquired by Lidar. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

14 pages, 2726 KiB  
Article
A More Effective Zero-DCE Variant: Zero-DCE Tiny
by Weiwen Mu, Huixiang Liu, Wenbai Chen and Yiqun Wang
Electronics 2022, 11(17), 2750; https://doi.org/10.3390/electronics11172750 - 01 Sep 2022
Cited by 1 | Viewed by 2788
Abstract
The purpose of Low Illumination Image Enhancement (LLIE) is to improve the perception or interpretability of images taken in low illumination environments. This work inherits the work of Zero-Reference Deep Curve Estimation (Zero-DCE) and proposes a more effective image enhancement model, Zero-DCE Tiny. [...] Read more.
The purpose of Low Illumination Image Enhancement (LLIE) is to improve the perception or interpretability of images taken in low illumination environments. This work inherits the work of Zero-Reference Deep Curve Estimation (Zero-DCE) and proposes a more effective image enhancement model, Zero-DCE Tiny. First, the new model introduces the Cross Stage Partial Network (CSPNet) into the original U-net structure, divides basic feature maps into two parts, and then recombines it through the structure of cross-phase connection to achieve a richer gradient combination with less computation. Second, we replace all the deep separable convolutions except the last layer with Ghost modules, which makes the network lighter. Finally, we introduce the channel consistency loss into the non-reference loss, which further strengthens the constraint on the pixel distribution of the enhanced image and the original image. Experiments show that compared with Zero-DCE++, the network proposed in this work is more lightweight and surpasses the Zero-DCE++ method in some important image enhancement evaluation indexes. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

19 pages, 5708 KiB  
Article
Recognition of Dorsal Hand Vein in Small-Scale Sample Database Based on Fusion of ResNet and HOG Feature
by Jindi Li, Kefeng Li, Guangyuan Zhang, Jiaqi Wang, Keming Li and Yumin Yang
Electronics 2022, 11(17), 2698; https://doi.org/10.3390/electronics11172698 - 28 Aug 2022
Cited by 2 | Viewed by 1641
Abstract
As artificial intelligence develops, deep learning algorithms are increasingly being used in the field of dorsal hand vein (DHV) recognition. However, deep learning has high requirements regarding the number of samples, and current DHV datasets have few images. To solve the above problems, [...] Read more.
As artificial intelligence develops, deep learning algorithms are increasingly being used in the field of dorsal hand vein (DHV) recognition. However, deep learning has high requirements regarding the number of samples, and current DHV datasets have few images. To solve the above problems, we propose a method based on the fusion of ResNet and Histograms of Oriented Gradients (HOG) features, in which the shallow semantic information extracted by primary convolution and HOG features are fed into the residual structure of ResNet for full fusion and, finally, classification. By adding Gaussian noise, the North China University of Technology dataset, the Shandong University of Science and Technology dataset, and the Eastern Mediterranean University dataset are extended and fused to from a fused dataset. Our proposed method is applied to the above datasets, and the experimental results show that our proposed method achieves good recognition rates on each of the datasets. Importantly, we achieved a 93.47% recognition rate on the fused dataset, which was 2.31% and 26.08% higher than using ResNet and HOG alone. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

16 pages, 67752 KiB  
Article
Improvement of Image Stitching Using Binocular Camera Calibration Model
by Mengfan Tang, Qian Zhou, Ming Yang, Yifan Jiang and Boyan Zhao
Electronics 2022, 11(17), 2691; https://doi.org/10.3390/electronics11172691 - 27 Aug 2022
Cited by 3 | Viewed by 1888
Abstract
Image stitching is the process of stitching several images that overlap each other into a single, larger image. The traditional image stitching algorithm searches the feature points of the image, performs alignments, and constructs the projection transformation relationship. The traditional algorithm has a [...] Read more.
Image stitching is the process of stitching several images that overlap each other into a single, larger image. The traditional image stitching algorithm searches the feature points of the image, performs alignments, and constructs the projection transformation relationship. The traditional algorithm has a strong dependence on feature points; as such, if feature points are sparse or unevenly distributed in the scene, the stitching will be misaligned or even fail completely. In scenes with obvious parallaxes, the global homography projection transformation relationship cannot be used for image alignment. To address these problems, this paper proposes a method of image stitching based on fixed camera positions and a hierarchical projection method based on depth information. The method does not depend on the number and distribution of feature points, so it avoids the complexity of feature point detection. Additionally, the effect of parallax on stitching is eliminated to a certain extent. Our experiments showed that the proposed method based on the camera calibration model can achieve more robust stitching results when a scene has few feature points, uneven feature point distribution, or significant parallax. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

14 pages, 3619 KiB  
Article
LSW-Net: A Learning Scattering Wavelet Network for Brain Tumor and Retinal Image Segmentation
by Ruihua Liu, Haoyu Nan, Yangyang Zou, Ting Xie and Zhiyong Ye
Electronics 2022, 11(16), 2616; https://doi.org/10.3390/electronics11162616 - 20 Aug 2022
Cited by 4 | Viewed by 1788
Abstract
Convolutional network models have been widely used in image segmentation. However, there are many types of boundary contour features in medical images which seriously affect the stability and accuracy of image segmentation models, such as the ambiguity of tumors, the variability of lesions, [...] Read more.
Convolutional network models have been widely used in image segmentation. However, there are many types of boundary contour features in medical images which seriously affect the stability and accuracy of image segmentation models, such as the ambiguity of tumors, the variability of lesions, and the weak boundaries of fine blood vessels. In this paper, in order to solve these problems we first introduce the dual-tree complex wavelet scattering transform module, and then innovatively propose a learning scattering wavelet network model. In addition, a new improved active contour loss function is further constructed to deal with complex segmentation. Finally, the equilibrium coefficient of our model is discussed. Experiments on the BraTS2020 dataset show that the LSW-Net model has improved the Dice coefficient, accuracy, and sensitivity of the classic FCN, SegNet, and At-Unet models by at least 3.51%, 2.11%, and 0.46%, respectively. In addition, the LSW-Net model still has an advantage in the average measure of Dice coefficients compared with some advanced segmentation models. Experiments on the DRIVE dataset prove that our model outperforms the other 14 algorithms in both Dice coefficient and specificity measures. In particular, the sensitivity of our model provides a 3.39% improvement when compared with the Unet model, and the model’s effect is obvious. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

12 pages, 3092 KiB  
Article
An Improved YOLOv5s Algorithm for Object Detection with an Attention Mechanism
by Tingyao Jiang, Cheng Li, Ming Yang and Zilong Wang
Electronics 2022, 11(16), 2494; https://doi.org/10.3390/electronics11162494 - 10 Aug 2022
Cited by 13 | Viewed by 2982
Abstract
To improve the accuracy of the You Only Look Once v5s (YOLOv5s) algorithm for object detection, this paper proposes an improved YOLOv5s algorithm, CBAM-YOLOv5s, which introduces an attention mechanism. A convolutional block attention module (CBAM) is incorporated into the YOLOv5s backbone network to [...] Read more.
To improve the accuracy of the You Only Look Once v5s (YOLOv5s) algorithm for object detection, this paper proposes an improved YOLOv5s algorithm, CBAM-YOLOv5s, which introduces an attention mechanism. A convolutional block attention module (CBAM) is incorporated into the YOLOv5s backbone network to improve its feature extraction ability. Furthermore, the complete intersection-over-union (CIoU) loss is used as the object bounding-box regression loss function to accelerate the speed of the regression process. Experiments are carried out on the Pascal Visual Object Classes 2007 (VOC2007) dataset and the Microsoft Common Objects in Context (COCO2014) dataset, which are widely used for object detection evaluations. On the VOC2007 dataset, the experimental results show that compared with those of the original YOLOv5s algorithm, the precision, recall and mean average precision (mAP) of the CBAM-YOLOv5s algorithm are improved by 4.52%, 1.18% and 3.09%, respectively. On the COCO2014 dataset, compared with the original YOLOv5s algorithm, the precision, recall and mAP of the CBAM-YOLOv5s algorithm are increased by 2.21%, 0.88% and 1.39%, respectively. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

12 pages, 2272 KiB  
Article
Image Denoising Based on GAN with Optimization Algorithm
by Min-Ling Zhu, Liang-Liang Zhao and Li Xiao
Electronics 2022, 11(15), 2445; https://doi.org/10.3390/electronics11152445 - 05 Aug 2022
Cited by 4 | Viewed by 2699
Abstract
Image denoising has been a knotty issue in the computer vision field, although the developing deep learning technology has brought remarkable improvements in image denoising. Denoising networks based on deep learning technology still face some problems, such as in their accuracy and robustness. [...] Read more.
Image denoising has been a knotty issue in the computer vision field, although the developing deep learning technology has brought remarkable improvements in image denoising. Denoising networks based on deep learning technology still face some problems, such as in their accuracy and robustness. This paper constructs a robust denoising network based on a generative adversarial network (GAN). Since the neural network has the phenomena of gradient dispersion and feature disappearance, the global residual is added to the autoencoder in the generator network, to extract and learn the features of the input image, so as to ensure the stability of the network. On this basis, we proposed an optimization algorithm (OA), to train and optimize the mean and variance of noise on each node of the generator. Then the robustness of the denoising network was improved through back propagation. Experimental results showed that the model’s denoising effect is remarkable. The accuracy of the proposed model was over 99% in the MNIST data set and over 90% in the CIFAR10 data set. The peak signal to noise ratio (PSNR) and structural similarity (SSIM) values of the proposed model were better than the state-of-the-art models in the BDS500 data set. Moreover, an anti-interference test of the model showed that the defense capacities of both the fast gradient sign method (FGSM) and project gradient descent (PGD) attacks were significantly improved, with PSNR and SSIM values decreased by less than 2%. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

14 pages, 2934 KiB  
Article
A Study on Particle Swarm Algorithm Based on Restart Strategy and Adaptive Dynamic Mechanism
by Lisang Liu, Hui Xu, Bin Wang, Rongsheng Zhang and Jionghui Chen
Electronics 2022, 11(15), 2339; https://doi.org/10.3390/electronics11152339 - 27 Jul 2022
Cited by 1 | Viewed by 1114
Abstract
Aiming at the problems of low path success rate, easy precocious maturity, and easily falling into local extremums in the complex environment of path planning of mobile robots, this paper proposes a new particle swarm algorithm (RDS-PSO) based on restart strategy and adaptive [...] Read more.
Aiming at the problems of low path success rate, easy precocious maturity, and easily falling into local extremums in the complex environment of path planning of mobile robots, this paper proposes a new particle swarm algorithm (RDS-PSO) based on restart strategy and adaptive dynamic adjustment mechanism. When the population falls into local optimal or premature convergence, the restart strategy is activated to expand the search range by re-randomly initializing the group particles. An inverted S-type decreasing inertia weight and adaptive dynamic adjustment learning factor are proposed to balance the ability of local search and global search. Finally, the new RDS-PSO algorithm is combined with cubic spline interpolation to apply to the path planning and smoothing processing of mobile robots, and the coding mode based on the path node as a particle individual is constructed, and the penalty function is selected as the fitness function to solve the shortest collision-free path. The comparative results of simulation experiments show that the RDS-PSO algorithm proposed in this paper solves the problem of falling into local extremums and precocious puberty, significantly improves the optimization, speed, and effectiveness of the path, and the simulation experiments in different environments also show that the algorithm has good robustness and generalization. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

16 pages, 9064 KiB  
Article
An Image Style Diversified Synthesis Method Based on Generative Adversarial Networks
by Zujian Yang and Zhao Qiu
Electronics 2022, 11(14), 2235; https://doi.org/10.3390/electronics11142235 - 17 Jul 2022
Cited by 2 | Viewed by 1532
Abstract
Existing research shows that there are many mature methods for image conversion in different fields. However, when the existing methods deal with images in multiple image domains, the robustness and scalability of images are often limited. We propose a novel and scalable approach, [...] Read more.
Existing research shows that there are many mature methods for image conversion in different fields. However, when the existing methods deal with images in multiple image domains, the robustness and scalability of images are often limited. We propose a novel and scalable approach, using a generative adversarial networks (GANs) model that can transform images across multiple domains, to address the above limitations. Our model can be trained on image datasets with different domains in a single network, with the ability to translate images and the ability to flexibly translate input images to any desired target domain. Our model is mainly composed of a generator, discriminator, style encoder, and a mapping network. The datasets use the celebrity face dataset CelebA-HQ and the animal face dataset AFHQ, and the evaluation criteria use FID and LPIPS to evaluate the images generated by the model. Experiments show that our model can generate a rich variety of high-quality images, and there is still some room for improvement. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

18 pages, 1784 KiB  
Article
Closed-Loop Residual Attention Network for Single Image Super-Resolution
by Meng Zhu and Wenjie Luo
Electronics 2022, 11(7), 1112; https://doi.org/10.3390/electronics11071112 - 31 Mar 2022
Cited by 1 | Viewed by 2136
Abstract
Recent research on single image super-resolution (SISR) using convolutional neural networks (CNNs) with the utilization of residual structures and attention mechanisms to utilize image features has demonstrated excellent performance. However, previous SISR techniques mainly integrated extracted image features within a deep or wide [...] Read more.
Recent research on single image super-resolution (SISR) using convolutional neural networks (CNNs) with the utilization of residual structures and attention mechanisms to utilize image features has demonstrated excellent performance. However, previous SISR techniques mainly integrated extracted image features within a deep or wide network architecture, ignoring the interaction between multiscale features and the diversity of features. At the same time, SISR is also a typical ill-posed problem in that it allows for several predictions for a given LR image. These problems limit the great learning ability of CNNs. To solve these problems, we propose a closed-loop residual attention network (CLRAN) to extract and interact with all the available diversity of features features efficiently and limit the space of possible function solutions. Specifically, we design an enhanced residual attention block (ERA) to extract features, and it dynamically assigns weight to the internal attention branches. The ERA combines multi-scale block (MSB) and enhanced attention mechanism (EAM) base on the residual module. The MSB adaptively detects multiscale image features of different scales by using different 3 × 3 convolution kernels. The EAM combines multi-spectral channel attention (MSCA) and spatial attention (SA). Therefore, the EAM extracts different frequency component information and spatial information to utilize the diversity features. Furthermore, we apply the progressive network architecture and learn an additional map for model monitoring, which forms a closed-loop with the mapping already learned by the LR to HR function. Extensive experiments demonstrate that our CLRAN outperforms the state-of-the-art SISR methods on public datasets for both ×4 and ×8, proving its accuracy and visual perception. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

16 pages, 23214 KiB  
Article
A Dual CNN for Image Super-Resolution
by Jiagang Song, Jingyu Xiao, Chunwei Tian, Yuxuan Hu, Lei You and Shichao Zhang
Electronics 2022, 11(5), 757; https://doi.org/10.3390/electronics11050757 - 01 Mar 2022
Cited by 2 | Viewed by 1948
Abstract
High-quality images have an important effect on high-level tasks. However, due to human factors and camera hardware, digital devices collect low-resolution images. Deep networks can effectively restore these damaged images via their strong learning abilities. However, most of these networks depended on deeper [...] Read more.
High-quality images have an important effect on high-level tasks. However, due to human factors and camera hardware, digital devices collect low-resolution images. Deep networks can effectively restore these damaged images via their strong learning abilities. However, most of these networks depended on deeper architectures to enhance clarities of predicted images, where single features cannot deal well with complex screens. In this paper, we propose a dual super-resolution CNN (DSRCNN) to obtain high-quality images. DSRCNN relies on two sub-networks to extract complementary low-frequency features to enhance the learning ability of the SR network. To prevent a long-term dependency problem, a combination of convolutions and residual learning operation is embedded into dual sub-networks. To prevent information loss of an original image, an enhanced block is used to gather original information and obtained high-frequency information of a deeper layer via sub-pixel convolutions. To obtain more high-frequency features, a feature learning block is used to learn more details of high-frequency information. The proposed method is very suitable for complex scenes for image resolution. Experimental results show that the proposed DSRCNN is superior to other popular in SR networks. For instance, our DSRCNN has obtained improvement of 0.08 dB than that of MemNet on Set5 for ×3. Full article
(This article belongs to the Special Issue Advances in Image Enhancement)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-20
Back to TopTop