Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
3.4
Journals
Biomimetics
Special Issues
Exploration of Bioinspired Computer Vision and Pattern Recognition
share announcement

Exploration of Bioinspired Computer Vision and Pattern Recognition

A special issue of Biomimetics (ISSN 2313-7673). This special issue belongs to the section "Bioinspired Sensorics, Information Processing and Control".

Deadline for manuscript submissions: 30 March 2025 | Viewed by 1536

Special Issue Editor

Dr. Qian Jiang

E-Mail Website
Guest Editor
Department of Computer Science, Yunnan University, Kunming, China
Interests: information and communication technology; image fusion; color image; computer vision; deep learning; image colorization

Special Issue Information

Dear Colleagues,

Artificial neural networks, such as multilayer perceptual machines, feedback neural networks, convolutional neural networks, and spiking neural networks, are inspired by biological nervous systems and partially simulate them. The rapid development of deep learning offers new solutions to many problems and generates significant challenges. Especially in the field of computer vision and pattern recognition, AI has led to unprecedented disruptive changes. The challenge lies in further exploring the performance of AI, broadening the scope of AI applications, and driving technological development through advances in the field. Current applications, such as generative AI, have raised concerns about authenticity, and ethical concerns around AI applications have emerged, involving deepfakes, adversarial attacks, and the traceability of digital media. Therefore, there are still many aspects of artificial neural networks that need to be developed and many issues that need to be addressed. First, the application of AI in image processing is expanding, showing great potential in areas such as image enhancement and virtual reality, but there are still many areas where there are unresolved issues. Second, the authenticity of images poses a serious challenge, and traditional detection algorithms are often overwhelmed when working with these highly synthesized images. Finally, research on adversarial attacks brings new perspectives to the study of deep neural networks. Therefore, it is urgent to conduct further research on computer vision and pattern recognition.

In this context, this Special Issue seeks contributions on new advances in the fields of computer vision and pattern recognition to improve the application and development of neural networks; related research on neural networks’ application is also welcome.

Dr. Qian Jiang
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. Biomimetics is an international peer-reviewed open access monthly 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 2200 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 neural networks
  • bioinformatics
  • deepfake detection
  • image fusion
  • image colorization
  • image super-resolution
  • adversarial attack and defence on neural networks
  • pattern recognition

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

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

21 pages, 1358 KiB  
Article
A 3D Face Recognition Algorithm Directly Applied to Point Clouds
by Xingyi You and Xiaohu Zhao
Biomimetics 2025, 10(2), 70; https://doi.org/10.3390/biomimetics10020070 - 23 Jan 2025
Viewed by 556
Abstract
Face recognition technology, despite its widespread use in various applications, still faces challenges related to occlusions, pose variations, and expression changes. Three-dimensional face recognition with depth information, particularly using point cloud-based networks, has shown effectiveness in overcoming these challenges. However, due to the [...] Read more.
Face recognition technology, despite its widespread use in various applications, still faces challenges related to occlusions, pose variations, and expression changes. Three-dimensional face recognition with depth information, particularly using point cloud-based networks, has shown effectiveness in overcoming these challenges. However, due to the limited extent of extensive 3D facial data and the non-rigid nature of facial structures, extracting distinct facial representations directly from point clouds remains challenging. To address this, our research proposes two key approaches. Firstly, we introduce a learning framework guided by a small amount of real face data based on morphable models with Gaussian processes. This system uses a novel method for generating large-scale virtual face scans, addressing the scarcity of 3D data. Secondly, we present a dual-branch network that directly extracts non-rigid facial features from point clouds, using kernel point convolution (KPConv) as its foundation. A local neighborhood adaptive feature learning module is introduced and employs context sampling technology, hierarchically downsampling feature-sensitive points critical for deep transfer and aggregation of discriminative facial features, to enhance the extraction of discriminative facial features. Notably, our training strategy combines large-scale face scanning data with 967 real face data from the FRGC v2.0 subset, demonstrating the effectiveness of guiding with a small amount of real face data. Experiments on the FRGC v2.0 dataset and the Bosphorus dataset demonstrate the effectiveness and potential of our method. Full article
(This article belongs to the Special Issue Exploration of Bioinspired Computer Vision and Pattern Recognition)
►▼ Show Figures

Figure 1

18 pages, 3461 KiB  
Article
Dynamic Structure-Aware Modulation Network for Underwater Image Super-Resolution
by Li Wang, Ke Li, Chengang Dong, Keyong Shen and Yang Mu
Biomimetics 2024, 9(12), 774; https://doi.org/10.3390/biomimetics9120774 - 19 Dec 2024
Viewed by 647
Abstract
Image super-resolution (SR) is a formidable challenge due to the intricacies of the underwater environment such as light absorption, scattering, and color distortion. Plenty of deep learning methods have provided a substantial performance boost for SR. Nevertheless, these methods are not only computationally [...] Read more.
Image super-resolution (SR) is a formidable challenge due to the intricacies of the underwater environment such as light absorption, scattering, and color distortion. Plenty of deep learning methods have provided a substantial performance boost for SR. Nevertheless, these methods are not only computationally expensive but also often lack flexibility in adapting to severely degraded image statistics. To counteract these issues, we propose a dynamic structure-aware modulation network (DSMN) for efficient and accurate underwater SR. A Mixed Transformer incorporated a structure-aware Transformer block and multi-head Transformer block, which could comprehensively utilize local structural attributes and global features to enhance the details of underwater image restoration. Then, we devised a dynamic information modulation module (DIMM), which adaptively modulated the output of the Mixed Transformer with appropriate weights based on input statistics to highlight important information. Further, a hybrid-attention fusion module (HAFM) adopted spatial and channel interaction to aggregate more delicate features, facilitating high-quality underwater image reconstruction. Extensive experiments on benchmark datasets revealed that our proposed DSMN surpasses the most renowned SR methods regarding quantitative and qualitative metrics, along with less computational effort. Full article
(This article belongs to the Special Issue Exploration of Bioinspired Computer Vision and Pattern 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 1-2
Back to TopTop