Journal Browser

Journal Browser

Advances of Computer 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 (15 April 2020) | Viewed by 3663

Special Issue Editors

E-Mail Website
Guest Editor
Electrical Engineering, Fu Jen Catholic University, New Taipei 24205, Taiwan
Interests: intelligent video surveillance; face recognition; deep learning for object detection; robotic vision; embedded computer vision; sleep healthcare; neuromorphic computing
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science and Information Engineering, National United University, Miaoli, Taiwan
Interests: computer vision; face recognition; video surveillance; hyperspectral image classification; content-based image retrieval; vision-based applications on embedded systems

E-Mail Website
Guest Editor
Department of Computer Science and Information Engineering, National Dong Hwa University, Hualien, Taiwan
Interests: image processing; computer vision; intelligent video surveillance; object detection and tracking; human pose estimation; 3D data acquisition technology; multimedia systems

Special Issue Information

Dear Colleagues,

Computer vision has become one of the most successful research topics in artificial intelligence. It is a key driving factor of successful applications such as face recognition, optical character recognition, biometrics, and video surveillance, which teach machines to see. Machines have eyes and brains to interpret the world by extracting meanings from image pixels. Recently, a vast development in various novel applications, including augmented reality, computational photography, autonomous vehicles, unmanned air vehicles and unmanned stores, egocentric vision, and three-dimensional movies, has brought computer vision to a new peak. In more real and complicated applications, machine learning and neural networks are employed to achieve a big leap in computer vision. Especially, deep learning shows great promises for computer vision applications.

Computer vision dramatically consumes processing power. However, thanks to the continuously increasing processing and sensing power of mobile processors and the quality of emerging displays, computer vision no longer requires an expensive specialized lab equipment and has proven its practical applicability in many domains like health, automotive, art, education, intelligent manufacturing, smart agriculture, and others. Embedded computer vision applies DSP processors, FPGA, and GPU devices to achieve edge computing. Moreover, neuromorphic computing, that is, the so-called next-level neural networks, can simulate the visual cortex and has great potential to develop high-performance computer vision algorithms.

In this Special Issue on “Advances in Computer Vision”, we invite authors to submit original research articles, reviews, and viewpoint articles related to recent advances at all levels of the applications and technologies of computer vision. We are particularly interested in presenting emerging technologies related to machine learning and deep learning that may have a significant impact on this research field. We are open to papers addressing a broad range of topics, from foundational topics regarding theoretical issues of computer vision to novel algorithms improving classical vision problems, advanced and technological systems for interesting applications, and innovative approaches in edge computing and neuromorphic computing. Topics of interest for this Special Issue include but are not limited to:

  • Object detection, tracking, categorization, and recognition
  • Machine learning and deep learning for computer vision
  • Segmentation, feature extraction, and registration for images and videos
  • Three-dimensional imaging, analysis, and applications
  • Biometrics by the recognition of face, fingerprint, palm, iris and more
  • Gesture, behavior, and event analysis for videos
  • Computational photography, such as super-resolution, high-dynamic-range imaging, style transfer, colorization and decolorization, and more
  • Beyond visual spectrum in computer vision, such as near-infrared and thermal image
  • Embedded computer vision for edge computing
  • Novel applications in video surveillance, augmented reality, sport video analysis, unmanned air vehicle, robotic vision, medical image, health care, AIoT, intelligent consumer electronics, and so on.
  • Neuromorphic computing for computer vision.

Prof. Yuan-Kai Wang
Prof. Chin-Chuan Han
Prof. I-Cheng Chang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at 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.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


12 pages, 1889 KiB  
Using Feature Fusion and Parameter Optimization of Dual-input Convolutional Neural Network for Face Gender Recognition
by Cheng-Jian Lin, Cheng-Hsien Lin and Shiou-Yun Jeng
Appl. Sci. 2020, 10(9), 3166; - 1 May 2020
Cited by 16 | Viewed by 3014
In recent years, convolutional neural networks (CNNs) have been successfully used in image recognition and image classification. General CNNs only use a single image as feature extraction. If the quality of the obtained image is not good, it is easy to cause misjudgment [...] Read more.
In recent years, convolutional neural networks (CNNs) have been successfully used in image recognition and image classification. General CNNs only use a single image as feature extraction. If the quality of the obtained image is not good, it is easy to cause misjudgment or recognition error. Therefore, this study proposes the feature fusion of a dual-input CNN for the application of face gender classification. In order to improve the traditional feature fusion method, this paper also proposes a new feature fusion method, called the weighting fusion method, which can effectively improve the overall accuracy. In addition, in order to avoid the parameters of the traditional CNN being determined by the user, this paper uses a uniform experimental design (UED) instead of the user to set the network parameters. The experimental results show that in the dual-input CNN experiment, average accuracy rates of 99.98% and 99.11% on the CIA and MORPH data sets are achieved, respectively, which is superior to the traditional feature fusion method. Full article
(This article belongs to the Special Issue Advances of Computer Vision)
Show Figures

Figure 1

Back to TopTop