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
Selected Papers from Young Researchers in AI for Computer Vision
share announcement

Selected Papers from Young Researchers in AI for Computer Vision

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

Deadline for manuscript submissions: 10 October 2024 | Viewed by 6633

Special Issue Editors

Dr. Moez Bouchouicha

E-Mail Website
Guest Editor
LIS-CNRS, Université de Toulon, Aix-Marseille University, 83041 Toulon, France
Interests: computer vision; AI; deep learning; medical imaging; fire detection
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Eric Moreau

E-Mail
Guest Editor
LIS-CNRS, Université de Toulon, Aix-Marseille University, 83041 Toulon, France
Interests: signal and image processing; independent component analysis; source separation
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence is a research field that has progressed exponentially over the last two decades. Nowadays, AI is used in many fields: health, industry, commerce, finance, etc. Nevertheless, it is important to note that the most spectacular results that have allowed the development of this field have been obtained in computer vision. AI in computer vision has yielded prodigious results in the field of medical imaging, autonomous driving, robotics, etc. We could even say that it has, at times, surpassed human performance—image recognition representing a good example.

The main purpose of this Special Issue is to allow young researchers to communicate and share their achievements in terms of novel theoretical and experimental research methods in the field of AI in computer vision. Moreover, papers are welcome that deal with computer vision applications such facial recognition, human pose estimation and tracking, autonomous vehicles, medical imaging, agriculture, etc.

Dr. Moez Bouchouicha
Prof. Dr. Eric Moreau
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

  • computer vision
  • machine learning
  • deep learning
  • pattern recognition
  • neural network
  • convolutional neural network

Published Papers (6 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

Jump to: Review

23 pages, 11434 KiB  
Article
Noncontact Automatic Water-Level Assessment and Prediction in an Urban Water Stream Channel of a Volcanic Island Using Deep Learning
by Fábio Mendonça, Sheikh Shanawaz Mostafa, Fernando Morgado-Dias, Joaquim Amândio Azevedo, Antonio G. Ravelo-García and Juan L. Navarro-Mesa
Electronics 2024, 13(6), 1145; https://doi.org/10.3390/electronics13061145 - 20 Mar 2024
Viewed by 486
Abstract
Traditional methods for water-level measurement usually employ permanent structures, such as a scale built into the water system, which is costly and laborious and can wash away with water. This research proposes a low-cost, automatic water-level estimator that can appraise the level without [...] Read more.
Traditional methods for water-level measurement usually employ permanent structures, such as a scale built into the water system, which is costly and laborious and can wash away with water. This research proposes a low-cost, automatic water-level estimator that can appraise the level without disturbing water flow or affecting the environment. The estimator was developed for urban areas of a volcanic island water channel, using machine learning to evaluate images captured by a low-cost remote monitoring system. For this purpose, images from over one year were collected. For better performance, captured images were processed by converting them to a proposed color space, named HLE, composed of hue, lightness, and edge. Multiple residual neural network architectures were examined. The best-performing model was ResNeXt, which achieved a mean absolute error of 1.14 cm using squeeze and excitation and data augmentation. An explainability analysis was carried out for transparency and a visual explanation. In addition, models were developed to predict water levels. Three models successfully forecasted the subsequent water levels for 10, 60, and 120 min, with mean absolute errors of 1.76 cm, 2.09 cm, and 2.34 cm, respectively. The models could follow slow and fast transitions, leading to a potential flooding risk-assessment mechanism. Full article
(This article belongs to the Special Issue Selected Papers from Young Researchers in AI for Computer Vision)
►▼ Show Figures

Figure 1

26 pages, 49715 KiB  
Article
Deep Spectral Meshes: Multi-Frequency Facial Mesh Processing with Graph Neural Networks
by Robert Kosk, Richard Southern, Lihua You, Shaojun Bian, Willem Kokke and Greg Maguire
Electronics 2024, 13(4), 720; https://doi.org/10.3390/electronics13040720 - 09 Feb 2024
Viewed by 704
Abstract
With the rising popularity of virtual worlds, the importance of data-driven parametric models of 3D meshes has grown rapidly. Numerous applications, such as computer vision, procedural generation, and mesh editing, vastly rely on these models. However, current approaches do not allow for independent [...] Read more.
With the rising popularity of virtual worlds, the importance of data-driven parametric models of 3D meshes has grown rapidly. Numerous applications, such as computer vision, procedural generation, and mesh editing, vastly rely on these models. However, current approaches do not allow for independent editing of deformations at different frequency levels. They also do not benefit from representing deformations at different frequencies with dedicated representations, which would better expose their properties and improve the generated meshes’ geometric and perceptual quality. In this work, spectral meshes are introduced as a method to decompose mesh deformations into low-frequency and high-frequency deformations. These features of low- and high-frequency deformations are used for representation learning with graph convolutional networks. A parametric model for 3D facial mesh synthesis is built upon the proposed framework, exposing user parameters that control disentangled high- and low-frequency deformations. Independent control of deformations at different frequencies and generation of plausible synthetic examples are mutually exclusive objectives. A Conditioning Factor is introduced to leverage these objectives. Our model takes further advantage of spectral partitioning by representing different frequency levels with disparate, more suitable representations. Low frequencies are represented with standardised Euclidean coordinates, and high frequencies with a normalised deformation representation (DR). This paper investigates applications of our proposed approach in mesh reconstruction, mesh interpolation, and multi-frequency editing. It is demonstrated that our method improves the overall quality of generated meshes on most datasets when considering both the L1 norm and perceptual Dihedral Angle Mesh Error (DAME) metrics. Full article
(This article belongs to the Special Issue Selected Papers from Young Researchers in AI for Computer Vision)
►▼ Show Figures

Figure 1

18 pages, 3905 KiB  
Article
AI-Based Aortic Stenosis Classification in MRI Scans
by Luís B. Elvas, Pedro Águas, Joao C. Ferreira, João Pedro Oliveira, Miguel Sales Dias and Luís Brás Rosário
Electronics 2023, 12(23), 4835; https://doi.org/10.3390/electronics12234835 - 30 Nov 2023
Viewed by 682
Abstract
Aortic stenosis (AS) is a critical cardiovascular condition that necessitates precise diagnosis for effective patient care. Despite a limited dataset comprising only 202 images, our study employs transfer learning to investigate the efficacy of five convolutional neural network (CNN) models, coupled with advanced [...] Read more.
Aortic stenosis (AS) is a critical cardiovascular condition that necessitates precise diagnosis for effective patient care. Despite a limited dataset comprising only 202 images, our study employs transfer learning to investigate the efficacy of five convolutional neural network (CNN) models, coupled with advanced computer vision techniques, in accurately classifying AS. The VGG16 model stands out among the tested models, achieving 95% recall and F1-score. To fortify the model’s robustness and generalization, we implement various data augmentation techniques, including translation, rotation, flip, and brightness adjustment. These techniques aim to capture real-world image variations encountered in clinical settings. Validation, conducted using authentic data from Hospital Santa Maria, not only affirms the clinical applicability of our model but also highlights the potential to develop robust models with a limited number of images. The models undergo training after the images undergo a series of computer vision and data augmentation techniques, as detailed in this paper. These techniques augment the size of our dataset, contributing to improved model performance. In conclusion, our study illuminates the potential of AI-driven AS detection in MRI scans. The integration of transfer learning, CNN models, and data augmentation yields high accuracy rates, even with a small dataset, as validated in real clinical cases. Full article
(This article belongs to the Special Issue Selected Papers from Young Researchers in AI for Computer Vision)
►▼ Show Figures

Figure 1

15 pages, 2458 KiB  
Article
OCR Applied for Identification of Vehicles with Irregular Documentation Using IoT
by Luiz Alfonso Glasenapp, Aurélio Faustino Hoppe, Miguel Alexandre Wisintainer, Andreza Sartori and Stefano Frizzo Stefenon
Electronics 2023, 12(5), 1083; https://doi.org/10.3390/electronics12051083 - 22 Feb 2023
Cited by 10 | Viewed by 2132
Abstract
Given the lack of investments in surveillance in remote places, this paper presents a prototype that identifies vehicles in irregular conditions, notifying a group of people, such as a network of neighbors, through a low-cost embedded system based on the Internet of things [...] Read more.
Given the lack of investments in surveillance in remote places, this paper presents a prototype that identifies vehicles in irregular conditions, notifying a group of people, such as a network of neighbors, through a low-cost embedded system based on the Internet of things (IoT). The developed prototype allows the visualization of the location, date and time of the event, and vehicle information such as license plate, make, model, color, city, state, passenger capacity and restrictions. It also offers a responsive interface in two languages: Portuguese and English. The proposed device addresses technical concepts pertinent to image processing such as binarization, analysis of possible characters on the plate, plate border location, perspective transformation, character segmentation, optical character recognition (OCR) and post-processing. The embedded system is based on a Raspberry having support to GPS, solar panels, communication via 3G modem, wi-fi, camera and motion sensors. Tests were performed regarding the vehicle’s positioning and the percentage of assertiveness in image processing, where the vehicles are at different angles, speeds and distances. The prototype can be a viable alternative because the results were satisfactory concerning the recognition of the license plates, mobility and autonomy. Full article
(This article belongs to the Special Issue Selected Papers from Young Researchers in AI for Computer Vision)
►▼ Show Figures

Figure 1

Review

Jump to: Research

18 pages, 4908 KiB  
Review
A Review of Generative Adversarial Networks for Computer Vision Tasks
by Ana-Maria Simion, Șerban Radu and Adina Magda Florea
Electronics 2024, 13(4), 713; https://doi.org/10.3390/electronics13040713 - 09 Feb 2024
Viewed by 675
Abstract
In recent years, computer vision tasks have gained a lot of popularity, accompanied by the development of numerous powerful architectures consistently delivering outstanding results when applied to well-annotated datasets. However, acquiring a high-quality dataset remains a challenge, particularly in sensitive domains like medical [...] Read more.
In recent years, computer vision tasks have gained a lot of popularity, accompanied by the development of numerous powerful architectures consistently delivering outstanding results when applied to well-annotated datasets. However, acquiring a high-quality dataset remains a challenge, particularly in sensitive domains like medical imaging, where expense and ethical concerns represent a challenge. Generative adversarial networks (GANs) offer a possible solution to artificially expand datasets, providing a basic resource for applications requiring large and diverse data. This work presents a thorough review and comparative analysis of the most promising GAN architectures. This review is intended to serve as a valuable reference for selecting the most suitable architecture for diverse projects, diminishing the challenges posed by limited and constrained datasets. Furthermore, we developed practical experimentation, focusing on the augmentation of a medical dataset derived from a colonoscopy video. We also applied one of the GAN architectures outlined in our work to a dataset consisting of histopathology images. The goal was to illustrate how GANs can enhance and augment datasets, showcasing their potential to improve overall data quality. Through this research, we aim to contribute to the broader understanding and application of GANs in scenarios where dataset scarcity poses a significant obstacle, particularly in medical imaging applications. Full article
(This article belongs to the Special Issue Selected Papers from Young Researchers in AI for Computer Vision)
►▼ Show Figures

Figure 1

41 pages, 1752 KiB  
Review
Beyond Land: A Review of Benchmarking Datasets, Algorithms, and Metrics for Visual-Based Ship Tracking
by Ranyeri do Lago Rocha and Felipe A. P. de Figueiredo
Electronics 2023, 12(13), 2789; https://doi.org/10.3390/electronics12132789 - 24 Jun 2023
Viewed by 968
Abstract
Object tracking has gained much interest in the last few years, especially in the context of multiple object tracking. Many datasets used for tracking provide video sequences of people and objects in very different contexts. Although it has been attracting much attention, no [...] Read more.
Object tracking has gained much interest in the last few years, especially in the context of multiple object tracking. Many datasets used for tracking provide video sequences of people and objects in very different contexts. Although it has been attracting much attention, no dataset or tracking algorithm has been applied to coastal surveillance and ship tracking. Besides image/video-based tracking technologies, other technologies, such as radar and automatic identification systems (AISs), are also used for this task, especially in maritime applications. In the AIS case, commonly known issues, such as information omission, remain to be dealt with. As for radars, the most important issue is the impossibility of identifying the ship type/class and correlating it with AIS information. However, image/video-based solutions can be combined with these technologies to mitigate or even solve these issues. This work aims to review the most recent datasets and state-of-the-art tracking algorithms (also known as trackers) for single or multiple objects tracking for objects in general and its possibilities for maritime scenarios. The goal is to gain insights for developing novel datasets; benchmarking metrics; and mainly, novel ship tracking algorithms. Full article
(This article belongs to the Special Issue Selected Papers from Young Researchers in AI for Computer Vision)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop