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
Image Processing Based on Convolution Neural Network
share announcement

Image Processing Based on Convolution Neural Network

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 June 2024 | Viewed by 1757

Special Issue Editors

Prof. Dr. Shaozhang Niu

E-Mail Website
Guest Editor
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China
Interests: multimedia security; image recognition
Dr. Jiwei Zhang

E-Mail Website
Guest Editor
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China
Interests: computer vision; information security
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The advent of Convolutional Neural Networks (CNNs) has revolutionized the realm of image processing, leading to breakthroughs in numerous fields such as facial recognition, autonomous vehicles, and medical imaging. This can be attributed to their capacity for processing large-scale image data both efficiently and dependably. While CNN-based image processing techniques have played a significant role in feature extraction, information fusion, and the processing of static, dynamic, color, and grayscale images, it still holds immense potential for future advancements. Currently, more research is applying CNN-based image processing techniques to fields such as medical imaging, biometric identification, entertainment media, and public safety, presenting a variety of more refined and novel visual capabilities to individuals while simultaneously ensuring greater convenience.

Nevertheless, key challenges arise when CNNs are applied in image processing. These include the difficulty in handling complex and large-scale data, as well as the model's sensitivity to geometric transformations such as image deformation and rotation, which can lead to unstable prediction outcomes. In addition, the black-box nature of CNNs obscures the decision-making process, making it difficult to understand and interpret. Moreover, CNNs require a vast amount of annotated data for training, which can be challenging to obtain in certain fields like medical image processing, thereby limiting their application in these areas. Finally, just as federated learning has enhanced data security in computing networks, similar concerns and solutions are applicable to image processing using CNNs.

This Special Issue aims to provide a platform for researchers to present innovative and effective image processing technologies based on CNNs. This includes addressing the following specific topics:

  • Advancements in CNN-based image processing techniques;
  • Integration of CNNs with other AI techniques for image processing;
  • CNN architecture optimization for image processing;
  • Mathematical models for CNN-based image processing;
  • Security and privacy in image processing;
  • Resource allocation optimization for CNNs in image processing tasks;
  • Modeling, analysis, and measurement of computational and requirements for CNN-based image processing;
  • Interpretable image processing with CNNs.

Prof. Dr. Shaozhang Niu
Dr. Jiwei Zhang
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

  • artificial intelligence
  • convolutional neural networks
  • deep learning
  • image processing
  • machine learning
  • information security
  • privacy-preserving
  • architecture optimization
  • multimedia

Published Papers (2 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

16 pages, 466 KiB  
Article
ESFuzzer: An Efficient Way to Fuzz WebAssembly Interpreter
by Jideng Han, Zhaoxin Zhang, Yuejin Du, Wei Wang and Xiuyuan Chen
Electronics 2024, 13(8), 1498; https://doi.org/10.3390/electronics13081498 - 15 Apr 2024
Viewed by 407
Abstract
WebAssembly code is designed to run in a sandboxed environment, such as a web browser, providing a high level of security and isolation from the underlying operating system and hardware. This enables the execution of untrusted code in a web browser without compromising [...] Read more.
WebAssembly code is designed to run in a sandboxed environment, such as a web browser, providing a high level of security and isolation from the underlying operating system and hardware. This enables the execution of untrusted code in a web browser without compromising the security and integrity of the user’s system. This paper discusses the challenges associated with using fuzzing tools to identify vulnerabilities or bugs in WebAssembly interpreters. Our approach, known as ESFuzzer, introduces an efficient method for fuzzing WebAssembly interpreters using an Equivalent-Statement concept and the Stack Repair Algorithm. The samples generated by our approach successfully passed code validation. In addition, we developed effective mutation strategies to enhance the efficacy of our approach. ESFuzzer has demonstrated its ability to generate code that achieves 100% WebAssembly validation testing and achieves code coverage that is more than twice that of libFuzzer. Furthermore, the 24-h experiment results show that ESFuzzer performs ten times more efficiently than libFuzzer. Full article
(This article belongs to the Special Issue Image Processing Based on Convolution Neural Network)
►▼ Show Figures

Figure 1

0 pages, 4435 KiB  
Article
Feature Reduction Networks: A Convolution Neural Network-Based Approach to Enhance Image Dehazing
by Haoyang Yu, Xiqin Yuan, Ruofei Jiang, Huamin Feng, Jiaxing Liu and Zhongyu Li
Electronics 2023, 12(24), 4984; https://doi.org/10.3390/electronics12244984 - 12 Dec 2023
Viewed by 867
Abstract
Image dehazing represents a dynamic area of research in computer vision. With the exponential development of deep learning, particularly convolutional neural networks (CNNs), innovative and effective image dehazing techniques have surfaced. However, in stark contrast to the majority of computer vision tasks employing [...] Read more.
Image dehazing represents a dynamic area of research in computer vision. With the exponential development of deep learning, particularly convolutional neural networks (CNNs), innovative and effective image dehazing techniques have surfaced. However, in stark contrast to the majority of computer vision tasks employing CNNs, the output from a dehazing model is often treated as uninformative noise, even though the model’s filters are engineered to extract pertinent features from the images. The standard approach of end-to-end models for dehazing involves noise removal from the hazy image to obtain a clear one. Consequently, the model’s dehazing capacity diminishes, as the noise is progressively filtered out throughout the propagation phase. This leads to the conception of the feature reduction network (FRNet), which is a distinctive CNN architecture that incrementally eliminates informative features, thereby resulting in the output of noise. Our experimental results indicate that the CNN-driven FRNet surpasses previous state-of-the-art (SOTA) methods in terms of the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) evaluation metrics. This highlights the effectiveness of the FRNet across various image dehazing datasets. With its reduced overhead, the CNN-based FRNet demonstrates superior performance over current SOTA methods, thereby affirming the efficacy of CNNs in image dehazing tasks. Full article
(This article belongs to the Special Issue Image Processing Based on Convolution Neural Network)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop