Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Deep Learning towards Robot Vision
share announcement

Deep Learning towards Robot Vision

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 June 2021) | Viewed by 7253

Special Issue Editor

Dr. Takashi Kuremoto

E-Mail Website
Guest Editor
Department of Information Science and Engineering, Yamaguchi University, Yamaguchi 753-8511, Japan
Interests: neural networks; fuzzy systems; deep learning; swarm intelligence; evolutionary computation; dynamical associative memory; chaotic dynamics; reinforcement learning; human–machine interaction; brain–computer interface; time series forecasting; computer vision

Special Issue Information

Dear Colleagues,

Deep learning (DL) has attracted researchers in many scientific fields as an advanced artificial intelligent (AI) technology in recent years. The success of DL comes from its data-driven feature extraction for the high dimensional data, which is a bottle-neck problem conventionally using hand-crafted features for pattern recognition, classification, robot vision, etc. Many kinds of deep neural networks have been developed, such as AlexNet, VGG, R-CNN, GoogleNet, ResNet, DenseNet, DarkNet, etc. for image processing; however, the development of DL is still ongoing. This Special Issue, “Deep Learning towards Robot Vision”, will publish full papers including survey, theory, and applications of DL for the advanced studies of robot vision. Original papers, as well as papers that have been presented at domestic and international workshops, symposiums, and conferences, will be welcomed.

Dr. Takashi Kuremoto
Guest Editor

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. Applied Sciences 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

  • deep learning
  • deep neural networks
  • image processing
  • robot vision
  • pattern recognition
  • video signal processing

Published Papers (3 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

12 pages, 5349 KiB  
Article
Multi-Fusion Approach for Wood Microscopic Images Identification Based on Deep Transfer Learning
by Meng Zhu, Jincong Wang, Achuan Wang, Honge Ren and Mahmoud Emam
Appl. Sci. 2021, 11(16), 7639; https://0-doi-org.brum.beds.ac.uk/10.3390/app11167639 - 20 Aug 2021
Cited by 3 | Viewed by 2222
Abstract
With the wide increase in global forestry resources trade, the demand for wood is increasing day by day, especially rare wood. Finding a computer-based method that can identify wood species has strong practical value and very important significance for regulating the wood trade [...] Read more.
With the wide increase in global forestry resources trade, the demand for wood is increasing day by day, especially rare wood. Finding a computer-based method that can identify wood species has strong practical value and very important significance for regulating the wood trade market and protecting the interests of all parties, which is one of the important problems to be solved by the wood industry. This article firstly studies the establishment of wood microscopic images dataset through a combination of traditional image amplification technology and Mix-up technology expansion strategy. Then with the traditional Faster Region-based Convolutional Neural Networks (Faster RCNN) model, the receptive field enhancement Spatial Pyramid Pooling (SPP) module and the multi-scale feature fusion of Feature Pyramid Networks (FPN) module are introduced to construct a microscopic image identification model based on the migration learning fusion model and analyzes the three factors (Mix-up, Enhanced SPP and FPN modules) affecting the wood microscopic image detection model. The experimental results show that the proposed approach can identify 10 kinds of wood microscopic images, and the accuracy rate has increased from 77.8% to 83.8%, which provides convenient conditions for further in-depth study of the microscopic characteristics of wood cells and is of great significance to the field of wood science. Full article
(This article belongs to the Special Issue Deep Learning towards Robot Vision)
►▼ Show Figures

Figure 1

12 pages, 4576 KiB  
Article
Say What You Are Looking At: An Attention-Based Interactive System for Autistic Children
by Furong Deng, Yu Zhou, Sifan Song, Zijian Jiang, Lifu Chen, Jionglong Su, Zhenglong Sun and Jiaming Zhang
Appl. Sci. 2021, 11(16), 7426; https://0-doi-org.brum.beds.ac.uk/10.3390/app11167426 - 12 Aug 2021
Cited by 1 | Viewed by 1505
Abstract
Gaze-following is an effective way for intention understanding in human–robot interaction, which aims to follow the gaze of humans to estimate what object is being observed. Most of the existing methods require people and objects to appear in the same image. Due to [...] Read more.
Gaze-following is an effective way for intention understanding in human–robot interaction, which aims to follow the gaze of humans to estimate what object is being observed. Most of the existing methods require people and objects to appear in the same image. Due to the limitation in the view of the camera, these methods are not applicable in practice. To address this problem, we propose a method of gaze following that utilizes a geometric map for better estimation. With the help of the map, this method is competitive for cross-frame estimation. On the basis of this method, we propose a novel gaze-based image caption system, which has been studied for the first time. Our experiments demonstrate that the system follows the gaze and describes objects accurately. We believe that this system is competent for autistic children’s rehabilitation training, pension service robots, and other applications. Full article
(This article belongs to the Special Issue Deep Learning towards Robot Vision)
►▼ Show Figures

Figure 1

16 pages, 898 KiB  
Article
Face Gender Recognition in the Wild: An Extensive Performance Comparison of Deep-Learned, Hand-Crafted, and Fused Features with Deep and Traditional Models
by Alhanoof Althnian, Nourah Aloboud, Norah Alkharashi, Faten Alduwaish, Mead Alrshoud and Heba Kurdi
Appl. Sci. 2021, 11(1), 89; https://0-doi-org.brum.beds.ac.uk/10.3390/app11010089 - 24 Dec 2020
Cited by 20 | Viewed by 2718
Abstract
Face gender recognition has many useful applications in human–robot interactions as it can improve the overall user experience. Support vector machines (SVM) and convolutional neural networks (CNNs) have been used successfully in this domain. Researchers have shown an increased interest in comparing and [...] Read more.
Face gender recognition has many useful applications in human–robot interactions as it can improve the overall user experience. Support vector machines (SVM) and convolutional neural networks (CNNs) have been used successfully in this domain. Researchers have shown an increased interest in comparing and combining different feature extraction paradigms, including deep-learned features, hand-crafted features, and the fusion of both features. Related research in face gender recognition has been mostly restricted to limited comparisons of the deep-learned and fused features with the CNN model or only deep-learned features with the CNN and SVM models. In this work, we perform a comprehensive comparative study to analyze the classification performance of two widely used learning models (i.e., CNN and SVM), when they are combined with seven features that include hand-crafted, deep-learned, and fused features. The experiments were performed using two challenging unconstrained datasets, namely, Adience and Labeled Faces in the Wild. Further, we used T-tests to assess the statistical significance of the differences in performances with respect to the accuracy, f-score, and area under the curve. Our results proved that SVMs showed best performance with fused features, whereas CNN showed the best performance with deep-learned features. CNN outperformed SVM significantly at p < 0.05. Full article
(This article belongs to the Special Issue Deep Learning towards Robot 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 1-3
Back to TopTop