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
Advanced Deep Learning and Neural Network Technologies for Image Recognition
share announcement

Advanced Deep Learning and Neural Network Technologies for Image Recognition

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

Deadline for manuscript submissions: closed (28 February 2022) | Viewed by 10872

Special Issue Editors

Dr. Xiaofeng Liu

E-Mail Website
Guest Editor
Harvard Medical School, Harvard University, Boston, MA 02114, USA
Interests: deep learning; machine learning; medical informatics; physics-informed data-driven methods
Special Issues, Collections and Topics in MDPI journals
Dr. Harry Yang

E-Mail Website
Guest Editor
Facebook AI Research (FAIR), Cambridge, MA, USA
Interests: AI and computer vision; DeepFake generation and detection
Dr. Zhenhua Guo

E-Mail Website
Guest Editor
Smart Transportation, Suzhou 215100, China
Interests: pattern recognition; computer vision; biometrics; object detection
Prof. Dr. Jane You

E-Mail Website
Guest Editor
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
Interests: image processing; pattern recognition; computer-aided diagnosis and monitoring

Special Issue Information

Dear Colleagues,

Visual recognition is a fundamental cognitive ability in humans which is essential for identifying objects/people. The in-depth explorations of deep learning and neural networks have facilitated advances in understanding the high-level semantic of visual contents. However, despite these advances, there are still many challenges remaining. For example, modern deep learning systems are data starved and rely greatly on the i.i.d. assumption of training and testing tasks. The common image corruptions and the recent presence of adversarial noise or attacks have raised higher requirements of robustness. In addition, application in biometrics, medical image analysis, and autonomous driving scenes require inducing non-trivial domain knowledge.   

The main aim of this Special Issue is to seek original contributions that address the above challenges or highlight emerging applications in image recognition. The topics of interest include but are not limited to: 

  • Robust recognition with perturbations;
  • Explainable deep learning;
  • Multimodal or multiview recognition;
  • Weakly supervised learning;
  • Self-supervision learning;
  • Privacy-aware recognition;
  • Data augmentation;
  • Transfer learning and domain adaptation;
  • Few/one shot learning;
  • GANs for image recognition;
  • Deepfake detection;
  • Distance metric learning;
  • Uncertainty estimation;
  • Out-of-distribution detection;
  • Activity and online learning;
  • Advanced and novel biometrics systems;
  • Practical and reliable medical image recognition

Dr. Xiaofeng Liu
Dr. Harry Yang
Dr. Zhenhua Guo
Prof. Dr. Jane You
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

  • Robust recognition with perturbations
  • Explainable deep learning
  • Multimodal or multiview recognition
  • Weakly supervised learning
  • Self-supervision learning
  • Privacy-aware recognition
  • Data augmentation
  • Transfer learning and domain adaptation
  • Few/one shot learning
  • GANs for image recognition
  • Deepfake detection
  • Distance metric learning
  • Uncertainty estimation
  • Out-of-distribution detection
  • Activity and online learning
  • Advanced and novel biometrics systems
  • Practical and reliable medical image recognition

Published Papers (5 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, 2823 KiB  
Article
High Edge-Quality Light-Field Salient Object Detection Using Convolutional Neural Network
by Xingzheng Wang, Songwei Chen, Jiehao Liu and Guoyao Wei
Electronics 2022, 11(7), 1054; https://doi.org/10.3390/electronics11071054 - 28 Mar 2022
Cited by 2 | Viewed by 1822
Abstract
The detection result of current light-field salient object detection methods suffers from loss of edge details, which significantly limits the performance of subsequent computer vision tasks. To solve this problem, we propose a novel convolutional neural network to accurately detect salient objects, by [...] Read more.
The detection result of current light-field salient object detection methods suffers from loss of edge details, which significantly limits the performance of subsequent computer vision tasks. To solve this problem, we propose a novel convolutional neural network to accurately detect salient objects, by digging effective edge information from light-field data. In particular, our method is divided into four steps. Firstly, the network extracts multi-level saliency features from light-field data. Secondly, edge features are extracted from low-level saliency features and optimized by ground-truth guidance. Then, to sufficiently leverage high-level saliency features and edge features, the network hierarchically fuses them in a complementary manner. Finally, spatial correlations between different levels of fused features are considered to detect salient objects. Our method can accurately locate salient objects with exquisite edge details, by extracting clear edge information and accurate saliency information and fully fusing them. We conduct extensive evaluations on three widely used benchmark datasets. The experimental results demonstrate the effectiveness of our method, and it is superior to eight state-of-the-art methods. Full article
(This article belongs to the Special Issue Advanced Deep Learning and Neural Network Technologies for Image Recognition)
►▼ Show Figures

Graphical abstract

12 pages, 460 KiB  
Article
Unsupervised Deep Pairwise Hashing
by Ye Ma, Qin Li, Xiaoshuang Shi and Zhenhua Guo
Electronics 2022, 11(5), 744; https://doi.org/10.3390/electronics11050744 - 28 Feb 2022
Cited by 7 | Viewed by 1907
Abstract
Although unsupervised deep hashing is potentially very useful for tackling many large-scale tasks, its performance is still far below satisfactory. Additionally, its performance might be significantly improved by effectively exploiting the pair similarity relationship among training data, but the attained similarity matrix usually [...] Read more.
Although unsupervised deep hashing is potentially very useful for tackling many large-scale tasks, its performance is still far below satisfactory. Additionally, its performance might be significantly improved by effectively exploiting the pair similarity relationship among training data, but the attained similarity matrix usually contains noisy information, which often largely decreases the model performance. To alleviate this issue, in this paper, we propose a novel unsupervised deep pairwise hashing method to effectively and robustly exploit the similarity information between training samples and multiple anchors. We first create an ensemble anchor-based pairwise similarity matrix to enhance the robustness of similarity and dissimilarity relations between training samples and anchors. Afterwards, we propose a novel loss function to directly and robustly take advantage of the similarity and dissimilarity information via a weighted cross-entropy loss, and make use of a square loss to reduce the gap between latent binary vectors and binary codes, and another square loss to form consensus predictions of latent binary vectors. Extensive experiments on large-scale benchmark databases demonstrate the effectiveness of the proposed method, which outperforms recent state-of-the-art unsupervised hashing methods with significantly better ranking performance. Full article
(This article belongs to the Special Issue Advanced Deep Learning and Neural Network Technologies for Image Recognition)
►▼ Show Figures

Graphical abstract

10 pages, 799 KiB  
Article
Palmprint Translation Network for Cross-Spectral Palmprint Recognition
by Ye Ma and Zhenhua Guo
Electronics 2022, 11(5), 736; https://doi.org/10.3390/electronics11050736 - 27 Feb 2022
Cited by 1 | Viewed by 1710
Abstract
Nowadays, palmprint recognition has been well developed since plenty of promising algorithms have emerged. Palmprints have also been applied under various authentication scenarios. However, these approaches are designed and tested only when the registration images and probe images are taken under the same [...] Read more.
Nowadays, palmprint recognition has been well developed since plenty of promising algorithms have emerged. Palmprints have also been applied under various authentication scenarios. However, these approaches are designed and tested only when the registration images and probe images are taken under the same illumination condition; thus, a cross-spectral performance degradation is speculated. Therefore, we test the cross-spectral performance of extended binary orientation co-occurrence vector (E-BOCV), which is unsatisfactory, illustrating the necessity of a specific algorithm. Trying to achieve the cross-spectral palmprint recognition with image-to-image translation, we have made efforts in the following two aspects. First, we introduce a scheme to evaluate the images of different spectra, which is a reliable basis for translation direction determination. Second, in this paper, we propose a palmprint translation convolutional neural network (PT-net) and the performance of translation from NIR to blue is tested on the PolyU multispectral dataset, which achieves a 91% decrease in Top-1 error using E-BOCV as the recognition framework. Full article
(This article belongs to the Special Issue Advanced Deep Learning and Neural Network Technologies for Image Recognition)
►▼ Show Figures

Figure 1

12 pages, 975 KiB  
Article
Image Perturbation-Based Deep Learning for Face Recognition Utilizing Discrete Cosine Transform
by Jaehun Park and Kwangsu Kim
Electronics 2022, 11(1), 25; https://doi.org/10.3390/electronics11010025 - 22 Dec 2021
Cited by 4 | Viewed by 2934
Abstract
Face recognition, including emotion classification and face attribute classification, has seen tremendous progress during the last decade owing to the use of deep learning. Large-scale data collected from numerous users have been the driving force in this growth. However, face images containing the [...] Read more.
Face recognition, including emotion classification and face attribute classification, has seen tremendous progress during the last decade owing to the use of deep learning. Large-scale data collected from numerous users have been the driving force in this growth. However, face images containing the identities of the owner can potentially cause severe privacy leakage if linked to other sensitive biometric information. The novel discrete cosine transform (DCT) coefficient cutting method (DCC) proposed in this study combines DCT and pixelization to protect the privacy of the image. However, privacy is subjective, and it is not guaranteed that the transformed image will preserve privacy. To overcome this, a user study was conducted on whether DCC really preserves privacy. To this end, convolutional neural networks were trained for face recognition and face attribute classification tasks. Our survey and experiments demonstrate that a face recognition deep learning model can be trained with images that most people think preserve privacy at a manageable cost in classification accuracy. Full article
(This article belongs to the Special Issue Advanced Deep Learning and Neural Network Technologies for Image Recognition)
►▼ Show Figures

Figure 1

14 pages, 1428 KiB  
Article
Violence Recognition Based on Auditory-Visual Fusion of Autoencoder Mapping
by Jiu Lou, Decheng Zuo, Zhan Zhang and Hongwei Liu
Electronics 2021, 10(21), 2654; https://doi.org/10.3390/electronics10212654 - 29 Oct 2021
Cited by 9 | Viewed by 1456
Abstract
In the process of violence recognition, accuracy is reduced due to problems related to time axis misalignment and the semantic deviation of multimedia visual auditory information. Therefore, this paper proposes a method for auditory-visual information fusion based on autoencoder mapping. First, a feature [...] Read more.
In the process of violence recognition, accuracy is reduced due to problems related to time axis misalignment and the semantic deviation of multimedia visual auditory information. Therefore, this paper proposes a method for auditory-visual information fusion based on autoencoder mapping. First, a feature extraction model based on the CNN-LSTM framework is established, and multimedia segments are used as whole input to solve the problem of time axis misalignment of visual and auditory information. Then, a shared semantic subspace is constructed based on an autoencoder mapping model and is optimized by semantic correspondence, which solves the problem of audiovisual semantic deviation and realizes the fusion of visual and auditory information on segment level features. Finally, the whole network is used to identify violence. The experimental results show that the method can make good use of the complementarity between modes. Compared with single-mode information, the multimodal method can achieve better results. Full article
(This article belongs to the Special Issue Advanced Deep Learning and Neural Network Technologies for Image Recognition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop