Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Browser

New Trends on Pattern Recognition and Computer Vision, Applications and Systems

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

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 (28 November 2021) | Viewed by 19278

Share This Special Issue

Special Issue Editors

Prof. Dr. Hugo Pedro Proença

E-Mail Website
Guest Editor

Department of Computer Science, University of Beira Interior, 6201-001 Covilhã, Portugal
Interests: pattern recognition; computer vision; biometrics; visual surveillance
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. João C. Neves

E-Mail Website
Guest Editor

Department of Computer Science, University of Beira Interior, 6201-001 Covilhã, Portugal
Interests: computer vision; machine learning; face recognition; biometrics

Special Issue Information

Dear Colleagues,

Recent advances in Pattern Recognition have been boosting the development of intelligent applications for many different kinds of industries/domains. Such solutions are not only seamlessly integrated in the environment, but typically have large adaptability for unexpected conditions, which increases their usefulness for real-world problems.

The New Trends on Pattern Recognition, Applications and Systems special issue aims to collect the latest approaches and findings, as well as to discuss the current challenges of Pattern recognition solutions for a broad range of applications. We expect this special issue addresses the research issues in the closely related areas of Pattern Recognition, such as Machine Learning, Data Mining, Computer Vision and Image Processing. We encourage the interdisciplinary research and applications of these areas.

We welcome high-quality submissions with important new theories, methods, applications, and systems in emerging topics of pattern recognition. The topics of interest include, but are not limited to:

Interpretable Machine Learning for Computer Vision;
Automated Deep Learning, including one or multiple stages of the machine learning process (e.g., data pre-processing, network architecture selection, hyper-parameter optimisation);
Zero-shot learning applied to real-world problems, such as Medical Imaging or Autonomous Systems;
Neural Rendering, including any approach using deep generative models for the generation of photo-realistic virtual data;
Autonomous Driving, including novel methods for object detection, object classification, object tracking and prediction of movement;
Semi-supervised, Weakly-supervised and Unsupervised learning frameworks for Pattern Recognition systems;
Real-time Pattern Recognition applications;
Multi-modal solutions for Pattern Recognition problems;
Signal processing for Pattern Recognition solutions;
Ethics/Privacy issues in deploying Pattern Recognition-based systems;
Benchmarks of current Pattern Recognition-based solutions for real-world problems;

Prof. Dr. Hugo Pedro Proença
Prof. Dr. João C. Neves
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. 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

Machine Learning
Computer Vision
Medical Imaging
object detection
object classification
Pattern Recognition systems
Signal processing
Autonomous Driving

Published Papers (6 papers)

Download All Papers

Research

Jump to: Review

11 pages, 2582 KiB

Open AccessArticle

Assessing Robustness of Morphological Characteristics of Arbitrary Grayscale Images

by Igor Smolyar and Daniel Smolyar

Appl. Sci. 2022, 12(4), 2037; https://0-doi-org.brum.beds.ac.uk/10.3390/app12042037 - 16 Feb 2022

Viewed by 965

Abstract

In our previous work, we introduced an empirical model (EM) of arbitrary binary images and three morphological characteristics: disorder of layer structure (DStr), disorder of layer size (DSize), and pattern complexity (PCom). The basic concept of the EM is that forms of lines play no role as a morphological factor in any narrow area of an arbitrary binary image; instead, the basic factor is the type of line connectivity, i.e., isotropic/anisotropic connections. The goal of the present work is to justify the possibility of making the EM applicable for the processing of grayscale arbitrary images. One of the possible ways to reach this goal is to assess the influence of image binarization on the robustness of DStr and DSize. Images that exhibit high and low edge gradient are used for this experimental study. The robustness of DStr and DSize against the binarization procedure is described in absolute (deviation from average) and relative (Pearson’s coefficient correlation) terms. Images with low edge gradient are converted into binary contour maps by applying the watershed algorithm, and DStr and DSize are then calculated for these maps. The robustness of DStr and DSize were assessed against the image threshold for images with high edge gradient and against the grid size of contour maps and Gaussian blur smoothing for images with low edge gradient. Experiments with grayscale arbitrary patterns, such as the surface of Earth and Mars, tidal sand ripples, turbulent flow, a melanoma, and cloud images, are presented to illustrate the spectrum of problems that may be possible to solve by applying the EM. The majority of our experiments show a high level of robustness for DStr and DSize. Full article

(This article belongs to the Special Issue New Trends on Pattern Recognition and Computer Vision, Applications and Systems)

► Show Figures

Figure 1

31 pages, 13408 KiB

Open AccessArticle

Comparison of Quantitative Morphology of Layered and Arbitrary Patterns: Contrary to Visual Perception, Binary Arbitrary Patterns Are Layered from a Structural Point of View

by Igor Smolyar and Daniel Smolyar

Appl. Sci. 2021, 11(14), 6300; https://0-doi-org.brum.beds.ac.uk/10.3390/app11146300 - 08 Jul 2021

Cited by 1 | Viewed by 2059

Abstract

Patterns found among both living systems, such as fish scales, bones, and tree rings, and non-living systems, such as terrestrial and extraterrestrial dunes, microstructures of alloys, and geological seismic profiles, are comprised of anisotropic layers of different thicknesses and lengths. These layered patterns form a record of internal and external factors that regulate pattern formation in their various systems, making it potentially possible to recognize events in the formation history of these systems. In our previous work, we developed an empirical model (EM) of anisotropic layered patterns using an N-partite graph, denoted as G(N), and a Boolean function to formalize the layer structure. The concept of isotropic and anisotropic layers was presented and described in terms of the G(N) and Boolean function. The central element of the present work is the justification that arbitrary binary patterns are made up of such layers. It has been shown that within the frame of the proposed model, it is the isotropic and anisotropic layers themselves that are the building blocks of binary layered and arbitrary patterns; pixels play no role. This is why the EM can be used to describe the morphological characteristics of such patterns. We present the parameters disorder of layer structure, disorder of layer size, and pattern complexity to describe the degree of deviation of the structure and size of an arbitrary anisotropic pattern being studied from the structure and size of a layered isotropic analog. Experiments with arbitrary patterns, such as regular geometric figures, convex and concave polygons, contour maps, the shape of island coastlines, river meanders, historic texts, and artistic drawings are presented to illustrate the spectrum of problems that it may be possible to solve by applying the EM. The differences and similarities between the proposed and existing morphological characteristics of patterns has been discussed, as well as the pros and cons of the suggested method. Full article

(This article belongs to the Special Issue New Trends on Pattern Recognition and Computer Vision, Applications and Systems)

► Show Figures

Figure 1

21 pages, 67265 KiB

Open AccessFeature PaperArticle

A Low-Cost Contactless Overhead Micrometer Surface Scanner

by Xenophon Zabulis, Panagiotis Koutlemanis, Nikolaos Stivaktakis and Nikolaos Partarakis

Appl. Sci. 2021, 11(14), 6274; https://0-doi-org.brum.beds.ac.uk/10.3390/app11146274 - 07 Jul 2021

Cited by 3 | Viewed by 2408

Abstract

The design and implementation of a contactless scanner and its software are proposed. The scanner regards the photographic digitization of planar and approximately planar surfaces and is proposed as a cost-efficient alternative to off-the-shelf solutions. The result is 19.8 Kppi micrometer scans, in the service of several applications. Accurate surface mosaics are obtained based on a novel image acquisition and image registration approach that actively seeks registration cues by acquiring auxiliary images and fusing proprioceptive data in correspondence and registration tasks. The device and operating software are explained, provided as an open prototype, and evaluated qualitatively and quantitatively. Full article

(This article belongs to the Special Issue New Trends on Pattern Recognition and Computer Vision, Applications and Systems)

► Show Figures

Figure 1

25 pages, 65229 KiB

Open AccessArticle

Deep-Feature-Based Approach to Marine Debris Classification

by Ivana Marin, Saša Mladenović, Sven Gotovac and Goran Zaharija

Appl. Sci. 2021, 11(12), 5644; https://0-doi-org.brum.beds.ac.uk/10.3390/app11125644 - 18 Jun 2021

Cited by 20 | Viewed by 5708

Abstract

The global community has recognized an increasing amount of pollutants entering oceans and other water bodies as a severe environmental, economic, and social issue. In addition to prevention, one of the key measures in addressing marine pollution is the cleanup of debris already present in marine environments. Deployment of machine learning (ML) and deep learning (DL) techniques can automate marine waste removal, making the cleanup process more efficient. This study examines the performance of six well-known deep convolutional neural networks (CNNs), namely VGG19, InceptionV3, ResNet50, Inception-ResNetV2, DenseNet121, and MobileNetV2, utilized as feature extractors according to three different extraction schemes for the identification and classification of underwater marine debris. We compare the performance of a neural network (NN) classifier trained on top of deep CNN feature extractors when the feature extractor is (1) fixed; (2) fine-tuned on the given task; (3) fixed during the first phase of training and fine-tuned afterward. In general, fine-tuning resulted in better-performing models but is much more computationally expensive. The overall best NN performance showed the fine-tuned Inception-ResNetV2 feature extractor with an accuracy of

91.40 %

and F1-score

92.08 %

, followed by fine-tuned InceptionV3 extractor. Furthermore, we analyze conventional ML classifiers’ performance when trained on features extracted with deep CNNs. Finally, we show that replacing NN with a conventional ML classifier, such as support vector machine (SVM) or logistic regression (LR), can further enhance the classification performance on new data. Full article

(This article belongs to the Special Issue New Trends on Pattern Recognition and Computer Vision, Applications and Systems)

► Show Figures

Figure 1

17 pages, 3430 KiB

Open AccessArticle

RCBi-CenterNet: An Absolute Pose Policy for 3D Object Detection in Autonomous Driving

by Kang An, Yixin Chen, Suhong Wang and Zhifeng Xiao

Appl. Sci. 2021, 11(12), 5621; https://0-doi-org.brum.beds.ac.uk/10.3390/app11125621 - 18 Jun 2021

Cited by 2 | Viewed by 2280

Abstract

3D Object detection is a critical mission of the perception system of a self-driving vehicle. Existing bounding box-based methods are hard to train due to the need to remove duplicated detections in the post-processing stage. In this paper, we propose a center point-based deep neural network (DNN) architecture named RCBi-CenterNet that predicts the absolute pose for each detected object in the 3D world space. RCBi-CenterNet is composed of a recursive composite network with a dual-backbone feature extractor and a bi-directional feature pyramid network (BiFPN) for cross-scale feature fusion. In the detection head, we predict a confidence heatmap that is used to determine the position of detected objects. The other pose information, including depth and orientation, is regressed. We conducted extensive experiments on the Peking University/Baidu-Autonomous Driving dataset, which contains more than 60,000 labeled 3D vehicle instances from 5277 real-world images, and each vehicle object is annotated with the absolute pose described by the six degrees of freedom (6DOF). We validated the design choices of various data augmentation methods and the backbone options. Through an ablation study and an overall comparison with the state-of-the-art (SOTA), namely CenterNet, we showed that the proposed RCBi-CenterNet presents performance gains of 2.16%, 2.76%, and 5.24% in Top 1, Top 3, and Top 10 mean average precision (mAP). The model and the result could serve as a credible benchmark for future research in center point-based object detection. Full article

(This article belongs to the Special Issue New Trends on Pattern Recognition and Computer Vision, Applications and Systems)

► Show Figures

Figure 1

Review

Jump to: Research

22 pages, 2011 KiB

Open AccessReview

Review of Visual Saliency Prediction: Development Process from Neurobiological Basis to Deep Models

by Fei Yan, Cheng Chen, Peng Xiao, Siyu Qi, Zhiliang Wang and Ruoxiu Xiao

Appl. Sci. 2022, 12(1), 309; https://0-doi-org.brum.beds.ac.uk/10.3390/app12010309 - 29 Dec 2021

Cited by 10 | Viewed by 3080

Abstract

The human attention mechanism can be understood and simulated by closely associating the saliency prediction task to neuroscience and psychology. Furthermore, saliency prediction is widely used in computer vision and interdisciplinary subjects. In recent years, with the rapid development of deep learning, deep models have made amazing achievements in saliency prediction. Deep learning models can automatically learn features, thus solving many drawbacks of the classic models, such as handcrafted features and task settings, among others. Nevertheless, the deep models still have some limitations, for example in tasks involving multi-modality and semantic understanding. This study focuses on summarizing the relevant achievements in the field of saliency prediction, including the early neurological and psychological mechanisms and the guiding role of classic models, followed by the development process and data comparison of classic and deep saliency prediction models. This study also discusses the relationship between the model and human vision, as well as the factors that cause the semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications, to provide new saliency predictions for follow-up work and the necessary help and advice. Full article

(This article belongs to the Special Issue New Trends on Pattern Recognition and Computer Vision, Applications and Systems)

► Show Figures