Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning
share announcement

Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (31 January 2024) | Viewed by 26705

Special Issue Editors

Dr. Jie Wen

E-Mail Website
Guest Editor
School of Computer Science & Technology, Harbin Institute of Technology, Shenzhen 150001, China
Interests: machine learning; data mining; pattern recognition; computer vision
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Yongbing Zhang

E-Mail Website
Guest Editor
School of Computer Science & Technology, Harbin Institute of Technology, Shenzhen 150001, China
Interests: signal processing; video compression; computational camera; big data acquisition; deep learning
Prof. Dr. Lunke Fei

E-Mail Website
Guest Editor
School of Computer Science, Guangdong University of Technology, Guangzhou 510006, China
Interests: deep learning; palmprint recognition; multi-view learning; feature extraction

Special Issue Information

Dear Colleagues,

Artificial intelligence, pattern recognition, and deep learning have become hot topics in recent years. From basic necessities to aerospace, pattern recognition, deep learning, and artificial intelligence are everywhere. For example, face recognition, fingerprint recognition, and palmprint recognition are widely used for access control and attendance systems in daily life. We often enjoy smart product recommendations from many shopping platforms. Automatic driving cars, virtual reality, navigation and positioning, and beauty camera software in mobile phones are also representative applications of artificial intelligence, pattern recognition, and deep learning. In fact, all of the artificial intelligence, pattern recognition, and deep learning algorithms highly rely on mathematical modeling and mathematical calculation. Good mathematical models and efficient calculation algorithms are crucial to success in these applications. For instance, it is very important to design a robust and efficient mathematical model for behavioral decisions in the application of multi-view information-based autonomous driving. The aim of this Special Issue is to highlight recent advances in mathematics-based methods in artificial intelligence, pattern recognition, and deep learning. Papers with interesting/significant new applications of artificial intelligence, pattern recognition, and deep learning are also welcome.

Topics of interest include, but are not limited to:

  • Mathematics-based methods in artificial intelligence;
  • Mathematics-based methods in pattern recognition;
  • Biometric recognition algorithms and applications, such as face recognition, palmprint recognition, eye classification, fingerprint recognition;
  • Multi-view/-modal learning and fusion;
  • Dimensionality reduction;
  • Subspace learning and clustering;
  • Deep-learning-based methods and applications;
  • Image super-resolution/enhancing/restoration;
  • Mathematics-based methods in computer vision, such as object tracking and detection;
  • Sparse representation and application.

Dr. Jie Wen
Prof. Dr. Yongbing Zhang
Prof. Dr. Lunke Fei
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. Mathematics 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 2600 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

  • pattern recognition and application
  • deep learning
  • artificial intelligence
  • computer vision

Published Papers (15 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

Jump to: Review

18 pages, 526 KiB  
Article
A Simple Model for Targeting Industrial Investments with Subsidies and Taxes
by Dmitry B. Rokhlin and Gennady A. Ougolnitsky
Mathematics 2024, 12(6), 822; https://doi.org/10.3390/math12060822 - 11 Mar 2024
Viewed by 401
Abstract
We consider an investor, whose capital is divided into an industrial investment xt and cash yt, and satisfy a nonlinear deterministic dynamical system. The investor fixes fractions of capital to be invested, withdrawn, and consumed, and also the production factor [...] Read more.
We consider an investor, whose capital is divided into an industrial investment xt and cash yt, and satisfy a nonlinear deterministic dynamical system. The investor fixes fractions of capital to be invested, withdrawn, and consumed, and also the production factor parameter. The government fixes a subsidy fraction for industrial investments and a tax fraction for the capital outflow. We study a Stackelberg game, corresponding to the asymptotically stable equilibrium (x∗,y∗) of the mentioned dynamical system. In this game, the government (the leader) uses subsidies to make incentives for the investor (the follower) to maintain the desired level of x∗, and uses taxes to achieve this with the minimal cost. The investor’s aim is to maximize the difference between the consumption and the price of the production factor at equilibrium. We present an explicit analytical solution of the specified Stackelberg game. Based on this solution, we introduce the notion of a fair industrial investment level, which is costless for the government, and show that it can produce realistic results using a case study of water production in Lahore. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

20 pages, 2332 KiB  
Article
Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm
by Weiwei Xie, Haifeng Wu, Boyu Liu, Shengdong Mu and Nedjah Nadia
Mathematics 2024, 12(4), 614; https://doi.org/10.3390/math12040614 - 19 Feb 2024
Viewed by 470
Abstract
The time series of exchange rate fluctuations are characterized by non-stationary and nonlinear features, and forecasting using traditional linear or single-machine models can cause significant bias. Based on this, the authors propose the combination of the advantages of the EMD and LSTM models [...] Read more.
The time series of exchange rate fluctuations are characterized by non-stationary and nonlinear features, and forecasting using traditional linear or single-machine models can cause significant bias. Based on this, the authors propose the combination of the advantages of the EMD and LSTM models to reduce the complexity by analyzing and decomposing the time series and forming a new model, EMD-LSTM-SVR, with a stronger generalization ability. More than 30,000 units of data on the USD/CNY exchange rate opening price from 2 January 2015 to 30 April 2022 were selected for an empirical demonstration of the model’s accuracy. The empirical results showed that the prediction of the exchange rate fluctuation with the EMD-LSTM-SVR model not only had higher accuracy, but also ensured that most of the predicted positions deviated less from the actual positions. The new model had a stronger generalization ability, a concise structure, and a high degree of ability to fit nonlinear features, and it prevented gradient vanishing and overfitting to achieve a higher degree of prediction accuracy. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

18 pages, 4825 KiB  
Article
Optimization of Personal Credit Evaluation Based on a Federated Deep Learning Model
by Shengdong Mu, Boyu Liu, Chaolung Lien and Nedjah Nadia
Mathematics 2023, 11(21), 4499; https://doi.org/10.3390/math11214499 - 31 Oct 2023
Viewed by 748
Abstract
Financial institutions utilize data for the intelligent assessment of personal credit. However, the privacy of financial data is gradually increasing, and the training data of a single financial institution may exhibit problems regarding low data volume and poor data quality. Herein, by fusing [...] Read more.
Financial institutions utilize data for the intelligent assessment of personal credit. However, the privacy of financial data is gradually increasing, and the training data of a single financial institution may exhibit problems regarding low data volume and poor data quality. Herein, by fusing federated learning with deep learning (FL-DL), we innovatively propose a dynamic communication algorithm and an adaptive aggregation algorithm as means of effectively solving the following problems, which are associated with personal credit evaluation: data privacy protection, distributed computing, and distributed storage. The dynamic communication algorithm utilizes a combination of fixed communication intervals and constrained variable intervals, which enables the federated system to utilize multiple communication intervals in a single learning task; thus, the performance of personal credit assessment models is enhanced. The adaptive aggregation algorithm proposes a novel aggregation weight formula. This algorithm enables the aggregation weights to be automatically updated, and it enhances the accuracy of individual credit assessment by exploiting the interplay between global and local models, which entails placing an additional but small computational burden on the powerful server side rather than on the resource-constrained client side. Finally, with regard to both algorithms and the FL-DL model, experiments and analyses are conducted using Lending Club financial company data; the results of the analysis indicate that both algorithms outperform the algorithms that are being compared and that the FL-DL model outperforms the advanced learning model. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

12 pages, 3047 KiB  
Article
CMKG: Construction Method of Knowledge Graph for Image Recognition
by Lijun Chen, Jingcan Li, Qiuting Cai, Xiangyu Han, Yunqian Ma and Xia Xie
Mathematics 2023, 11(19), 4174; https://doi.org/10.3390/math11194174 - 5 Oct 2023
Viewed by 1440
Abstract
With the continuous development of artificial intelligence technology and the exponential growth in the number of images, image detection and recognition technology is becoming more widely used. Image knowledge management is extremely urgent. The data source of a knowledge graph is not only [...] Read more.
With the continuous development of artificial intelligence technology and the exponential growth in the number of images, image detection and recognition technology is becoming more widely used. Image knowledge management is extremely urgent. The data source of a knowledge graph is not only the text and structured data but also the visual or auditory data such as images, video, and audio. How to use multimodal information to build an information management platform is a difficult problem. In this paper, a method is proposed to construct the result of image recognition as a knowledge graph. First of all, based on the improvement in the BlendMASK algorithm, the hollow convolution kernel is added. Secondly, the effect of image recognition and the relationships between all kinds of information are analyzed. Finally, the image knowledge graph is constructed by using the relationship between the image entities. The contributions of this paper are as follows. (1) The hollow convolution kernel is added to reduce the loss from extracting feature information from high-level feature images. (2) In this paper, a method is proposed to determine the relationship between entities by dividing the recognition results of entities in an image with a threshold, which makes it possible for the relationships between images to be interconnected. The experimental results show that this method improves the accuracy and F1 value of the image recognition algorithm. At the same time, the method achieves integrity in the construction of a multimodal knowledge graph. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

22 pages, 1240 KiB  
Article
Broad Learning Model with a Dual Feature Extraction Strategy for Classification
by Qi Zhang, Zuobin Ying, Jianhang Zhou, Jingzhang Sun and Bob Zhang
Mathematics 2023, 11(19), 4087; https://doi.org/10.3390/math11194087 - 26 Sep 2023
Viewed by 764
Abstract
The broad learning system (BLS) is a brief, flat neural network structure that has shown effectiveness in various classification tasks. However, original input data with high dimensionality often contain superfluous and correlated information affecting recognition performance. Moreover, the large number of randomly mapped [...] Read more.
The broad learning system (BLS) is a brief, flat neural network structure that has shown effectiveness in various classification tasks. However, original input data with high dimensionality often contain superfluous and correlated information affecting recognition performance. Moreover, the large number of randomly mapped feature nodes and enhancement nodes may also cause a risk of redundant information that interferes with the conciseness and performance of the broad learning paradigm. To address the above-mentioned issues, we aim to introduce a broad learning model with a dual feature extraction strategy (BLM_DFE). In particular, kernel principal component analysis (KPCA) is applied to process the original input data before extracting effective low-dimensional features for the broad learning model. Afterwards, we perform KPCA again to simplify the feature nodes and enhancement nodes in the broad learning architecture to obtain more compact nodes for classification. As a result, the proposed model has a more straightforward structure with fewer nodes and retains superior recognition performance. Extensive experiments on diverse datasets and comparisons with various popular classification approaches are investigated and evaluated to support the effectiveness of the proposed model (e.g., achieving the best result of 77.28%, compared with 61.44% achieved with the standard BLS, on the GT database). Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

18 pages, 2281 KiB  
Article
A Novel Artificial Visual System for Motion Direction Detection with Completely Modeled Retinal Direction-Selective Pathway
by Sichen Tao, Xiliang Zhang, Yuxiao Hua, Zheng Tang and Yuki Todo
Mathematics 2023, 11(17), 3732; https://doi.org/10.3390/math11173732 - 30 Aug 2023
Viewed by 693
Abstract
Some fundamental visual features have been found to be fully extracted before reaching the cerebral cortex. We focus on direction-selective ganglion cells (DSGCs), which exist at the terminal end of the retinal pathway, at the forefront of the visual system. By utilizing a [...] Read more.
Some fundamental visual features have been found to be fully extracted before reaching the cerebral cortex. We focus on direction-selective ganglion cells (DSGCs), which exist at the terminal end of the retinal pathway, at the forefront of the visual system. By utilizing a layered pathway composed of various relevant cells in the early stage of the retina, DSGCs can extract multiple motion directions occurring in the visual field. However, despite a considerable amount of comprehensive research (from cells to structures), a definitive conclusion explaining the specific details of the underlying mechanisms has not been reached. In this paper, leveraging some important conclusions from neuroscience research, we propose a complete quantified model for the retinal motion direction selection pathway and elucidate the global motion direction information acquisition mechanism from DSGCs to the cortex using a simple spiking neural mechanism. This mechanism is referred to as the artificial visual system (AVS). We conduct extensive testing, including one million sets of two-dimensional eight-directional binary object motion instances with 10 different object sizes and random object shapes. We also evaluate AVS’s noise resistance and generalization performance by introducing random static and dynamic noises. Furthermore, to thoroughly validate AVS’s efficiency, we compare its performance with two state-of-the-art deep learning algorithms (LeNet-5 and EfficientNetB0) in all tests. The experimental results demonstrate that due to its highly biomimetic design and characteristics, AVS exhibits outstanding performance in motion direction detection. Additionally, AVS possesses biomimetic computing advantages in terms of hardware implementation, learning difficulty, and parameter quantity. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

17 pages, 2865 KiB  
Article
A Lightweight YOLOv5-Based Model with Feature Fusion and Dilation Convolution for Image Segmentation
by Linwei Chen and Jingjing Yang
Mathematics 2023, 11(16), 3538; https://doi.org/10.3390/math11163538 - 16 Aug 2023
Viewed by 1436
Abstract
Image segmentation has played an essential role in computer vision. The target detection model represented by YOLOv5 is widely used in image segmentation. However, YOLOv5 has performance bottlenecks such as object scale variation, object occlusion, computational volume, and speed when processing complex images. [...] Read more.
Image segmentation has played an essential role in computer vision. The target detection model represented by YOLOv5 is widely used in image segmentation. However, YOLOv5 has performance bottlenecks such as object scale variation, object occlusion, computational volume, and speed when processing complex images. To solve these problems, an enhanced algorithm based on YOLOv5 is proposed. MobileViT is used as the backbone network of the YOLOv5 algorithm, and feature fusion and dilated convolution are added to the model. This method is validated on the COCO and PASCAL-VOC datasets. Experimental results show that it significantly reduces the processing time and achieves high segmentation quality with an accuracy of 95.32% on COCO and 96.02% on PASCAL-VOC. The improved model is 116 M, 52 M, and 76 M, smaller than U-Net, SegNet, and Mask R-CNN, respectively. This paper provides a new idea and method with which to solve the problems in the field of image segmentation, and the method has strong practicality and generalization value. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

18 pages, 2065 KiB  
Article
An Improved Deep-Learning-Based Financial Market Forecasting Model in the Digital Economy
by Yang Dexiang, Mu Shengdong, Yunjie Liu, Gu Jijian and Lien Chaolung
Mathematics 2023, 11(6), 1466; https://doi.org/10.3390/math11061466 - 17 Mar 2023
Cited by 1 | Viewed by 2679
Abstract
The high-complexity, high-reward, and high-risk characteristics of financial markets make them an important and interesting study area. Elliott’s wave theory describes the changing models of financial markets categorically in terms of wave models and is an advanced feature representation of financial time series. [...] Read more.
The high-complexity, high-reward, and high-risk characteristics of financial markets make them an important and interesting study area. Elliott’s wave theory describes the changing models of financial markets categorically in terms of wave models and is an advanced feature representation of financial time series. Meanwhile, deep learning is a breakthrough technique for nonlinear intelligent models, which aims to discover advanced feature representations of data and thus obtain the intrinsic laws underlying the data. This study proposes an innovative combination of these two concepts to create a deep learning + Elliott wave principle (DL-EWP) model. This model achieves the prediction of future market movements by extracting and classifying Elliott wave models from financial time series. The model’s effectiveness is empirically validated by running it on financial data from three major markets and comparing the results with those of the SAE, MLP, BP network, PCA-BP, and SVD-BP models. Interestingly, the DL-EWP model based on deep confidence networks outperforms other models in terms of stability, convergence speed, and accuracy and has a higher forecasting performance. Thus, the DL-EWP model can improve the accuracy of financial forecasting models that incorporate Elliott’s wave theory. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

18 pages, 982 KiB  
Article
Optimization Model and Algorithm of Logistics Vehicle Routing Problem under Major Emergency
by Kangye Tan, Weihua Liu, Fang Xu and Chunsheng Li
Mathematics 2023, 11(5), 1274; https://doi.org/10.3390/math11051274 - 6 Mar 2023
Cited by 8 | Viewed by 3145
Abstract
The novel coronavirus pandemic is a major global public health emergency, and has presented new challenges and requirements for the timely response and operational stability of emergency logistics that were required to address the major public health events outbreak in China. Based on [...] Read more.
The novel coronavirus pandemic is a major global public health emergency, and has presented new challenges and requirements for the timely response and operational stability of emergency logistics that were required to address the major public health events outbreak in China. Based on the problems of insufficient timeliness and high total system cost of emergency logistics distribution in major epidemic situations, this paper takes the minimum vehicle distribution travel cost, time cost, early/late punishment cost, and fixed cost of the vehicle as the target, the soft time window for receiving goods at each demand point, the rated load of the vehicle, the volume, maximum travel of the vehicle in a single delivery as constraints, and an emergency logistics vehicle routing problem optimization model for major epidemics was constructed. The convergence speed improvement strategy, particle search improvement strategy, and elite retention improvement strategy were introduced to improve the particle swarm optimization (PSO) algorithm for it to be suitable for solving global optimization problems. The simulation results prove that the improved PSO algorithm required to solve the emergency medical supplies logistics vehicle routing problem for the major emergency can reach optimal results. Compared with the basic PSO algorithm, the total cost was reduced by 20.09%. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

16 pages, 1389 KiB  
Article
Intelligent Prediction of Customer Churn with a Fused Attentional Deep Learning Model
by Yunjie Liu, Mu Shengdong, Gu Jijian and Nadia Nedjah
Mathematics 2022, 10(24), 4733; https://doi.org/10.3390/math10244733 - 13 Dec 2022
Cited by 6 | Viewed by 1895
Abstract
In recent years, churn rates in industries such as finance have increased, and the cost of acquiring new users is more than five times the cost of retaining existing users. To improve the intelligent prediction accuracy of customer churn rate, artificial intelligence is [...] Read more.
In recent years, churn rates in industries such as finance have increased, and the cost of acquiring new users is more than five times the cost of retaining existing users. To improve the intelligent prediction accuracy of customer churn rate, artificial intelligence is gradually used. In this paper, the bidirectional long short-term memory convolutional neural network (BiLSTM-CNN) model is integrated with recurrent neural networks (RNNs) and convolutional neural networks (CNNs) in parallel, which well solves the defective problem that RNNs and CNNs run separately, and it also solves the problem that the output results of a long short-term memory network (LSTM) layer in a densely-connected LSTM-CNN (DLCNN) model will ignore some local information when input to the convolutional layer. In order to explore whether the attention bidirectional long short-term memory convolutional neural network (AttnBLSTM-CNN) model can perform better than BiLSTM-CNN, this paper uses bank data to compare the two models. The experimental results show that the accuracy of the AttnBiLSTM-CNN model is improved by 0.2%, the churn rate is improved by 1.3%, the F1 value is improved by 0.0102, and the AUC value is improved by 0.0103 compared with the BLSTM model. Therefore, introducing the attention mechanism into the BiLSTM-CNN model can further improve the performance of the model. The improvement of the accuracy of the user churn prediction model can warn of the possibility of user churn in advance and take effective measures in advance to prevent user churn and improve the core competitiveness of financial institutions. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

16 pages, 1592 KiB  
Article
Neural Subspace Learning for Surface Defect Detection
by Bin Liu, Weifeng Chen, Bo Li and Xiuping Liu
Mathematics 2022, 10(22), 4351; https://doi.org/10.3390/math10224351 - 19 Nov 2022
Viewed by 1212
Abstract
Surface defect inspection is a key technique in industrial product assessments. Compared with other visual applications, industrial defect inspection suffers from a small sample problem and a lack of labeled data. Therefore, conventional deep-learning methods depending on huge supervised samples cannot be directly [...] Read more.
Surface defect inspection is a key technique in industrial product assessments. Compared with other visual applications, industrial defect inspection suffers from a small sample problem and a lack of labeled data. Therefore, conventional deep-learning methods depending on huge supervised samples cannot be directly generalized to this task. To deal with the lack of labeled data, unsupervised subspace learning provides more clues for the task of defect inspection. However, conventional subspace learning methods focus on studying the linear subspace structure. In order to explore the nonlinear manifold structure, a novel neural subspace learning algorithm is proposed by substituting linear operators with nonlinear neural networks. The low-rank property of the latent space is approximated by limiting the dimensions of the encoded feature, and the sparse coding property is simulated by quantized autoencoding. To overcome the small sample problem, a novel data augmentation strategy called thin-plate-spline deformation is proposed. Compared with the rigid transformation methods used in previous literature, our strategy could generate more reliable training samples. Experiments on real-world datasets demonstrate that our method achieves state-of-the-art performance compared with unsupervised methods. More importantly, the proposed method is competitive and has a better generalization capability compared with supervised methods based on deep learning techniques. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

19 pages, 2960 KiB  
Article
Exemplar-Based Sketch Colorization with Cross-Domain Dense Semantic Correspondence
by Jinrong Cui, Haowei Zhong, Hailong Liu and Yulu Fu
Mathematics 2022, 10(12), 1988; https://doi.org/10.3390/math10121988 - 9 Jun 2022
Cited by 3 | Viewed by 1933
Abstract
This paper aims to solve the task of coloring a sketch image given a ready-colored exemplar image. Conventional exemplar-based colorization methods tend to transfer styles from reference images to grayscale images by employing image analogy techniques or establishing semantic correspondences. However, their practical [...] Read more.
This paper aims to solve the task of coloring a sketch image given a ready-colored exemplar image. Conventional exemplar-based colorization methods tend to transfer styles from reference images to grayscale images by employing image analogy techniques or establishing semantic correspondences. However, their practical capabilities are limited when semantic correspondences are elusive. This is the case with coloring for sketches (where semantic correspondences are challenging to find) since it contains only edge information of the object and usually contains much noise. To address this, we present a framework for exemplar-based sketch colorization tasks that synthesizes colored images from sketch input and reference input in a distinct domain. Generally, we jointly proposed our domain alignment network, where the dense semantic correspondence can be established, with a simple but valuable adversarial strategy, that we term the structural and colorific conditions. Furthermore, we proposed to utilize a self-attention mechanism for style transfer from exemplar to sketch. It facilitates the establishment of dense semantic correspondence, which we term the spatially corresponding semantic transfer module. We demonstrate the effectiveness of our proposed method in several sketch-related translation tasks via quantitative and qualitative evaluation. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

15 pages, 945 KiB  
Article
A Survey on Face and Body Based Human Recognition Robust to Image Blurring and Low Illumination
by Ja Hyung Koo, Se Woon Cho, Na Rae Baek, Young Won Lee and Kang Ryoung Park
Mathematics 2022, 10(9), 1522; https://doi.org/10.3390/math10091522 - 2 May 2022
Cited by 3 | Viewed by 1882
Abstract
Many studies have been actively conducted on human recognition in indoor and outdoor environments. This is because human recognition methods in such environments are closely related to everyday life situations. Besides, these methods can be applied for finding missing children and identifying criminals. [...] Read more.
Many studies have been actively conducted on human recognition in indoor and outdoor environments. This is because human recognition methods in such environments are closely related to everyday life situations. Besides, these methods can be applied for finding missing children and identifying criminals. Methods for human recognition in indoor and outdoor environments can be classified into three categories: face-, body-, and gait-based methods. There are various factors that hinder indoor and outdoor human recognition, for example, blurring of captured images, cutoff in images due to the camera angle, and poor recognition in images acquired in low-illumination environments. Previous studies conducted to solve these problems focused on facial recognition only. This is because the face is typically assumed to contain more important information for human recognition than the body. However, when a human face captured by a distant camera is small, or even impossible to identify with the naked eye, the body’s information can help with recognition. For this reason, this survey paper reviews both face- and body-based human recognition methods. In previous surveys, recognition on low-resolution images were reviewed. However, survey papers on blurred images are not comprehensive. Therefore, in this paper, we review studies on blurred image restoration in detail by classifying them based on whether deep learning was used and whether the human face and body were combined. Although previous survey papers on recognition covered low-illumination environments as well, they excluded deep learning methods. Therefore, in this survey, we also include details on deep-learning-based low-illumination image recognition methods. We aim to help researchers who will study related fields in the future. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

Review

Jump to: Research

37 pages, 13108 KiB  
Review
Logical Rule-Based Knowledge Graph Reasoning: A Comprehensive Survey
by Zefan Zeng, Qing Cheng and Yuehang Si
Mathematics 2023, 11(21), 4486; https://doi.org/10.3390/math11214486 - 30 Oct 2023
Viewed by 3036
Abstract
With its powerful expressive capability and intuitive presentation, the knowledge graph has emerged as one of the primary forms of knowledge representation and management. However, the presence of biases in our cognitive and construction processes often leads to varying degrees of incompleteness and [...] Read more.
With its powerful expressive capability and intuitive presentation, the knowledge graph has emerged as one of the primary forms of knowledge representation and management. However, the presence of biases in our cognitive and construction processes often leads to varying degrees of incompleteness and errors within knowledge graphs. To address this, reasoning becomes essential for supplementing and rectifying these shortcomings. Logical rule-based knowledge graph reasoning methods excel at performing inference by uncovering underlying logical rules, showcasing remarkable generalization ability and interpretability. Moreover, the flexibility of logical rules allows for seamless integration with diverse neural network models, thereby offering promising prospects for research and application. Despite the growing number of logical rule-based knowledge graph reasoning methods, a systematic classification and analysis of these approaches is lacking. In this review, we delve into the relevant research on logical rule-based knowledge graph reasoning, classifying them into four categories: methods based on inductive logic programming (ILP), methods that unify probabilistic graphical models and logical rules, methods that unify embedding techniques and logical rules, and methods that jointly use neural networks (NNs) and logical rules. We introduce and analyze the core concepts and key techniques, as well as the advantages and disadvantages associated with these methods, while also providing a comparative evaluation of their performance. Furthermore, we summarize the main problems and challenges, and offer insights into potential directions for future research. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

17 pages, 3844 KiB  
Review
Multiview-Learning-Based Generic Palmprint Recognition: A Literature Review
by Shuping Zhao, Lunke Fei and Jie Wen
Mathematics 2023, 11(5), 1261; https://doi.org/10.3390/math11051261 - 6 Mar 2023
Cited by 5 | Viewed by 1941
Abstract
Palmprint recognition has been widely applied to security authentication due to its rich characteristics, i.e., local direction, wrinkle, and texture. However, different types of palmprint images captured from different application scenarios usually contain a variety of dominant features. Specifically, the palmprint recognition performance [...] Read more.
Palmprint recognition has been widely applied to security authentication due to its rich characteristics, i.e., local direction, wrinkle, and texture. However, different types of palmprint images captured from different application scenarios usually contain a variety of dominant features. Specifically, the palmprint recognition performance will be degraded by the interference factors, i.e., noise, rotations, and shadows, while palmprint images are acquired in the open-set environments. Seeking to handle the long-standing interference information in the images, multiview palmprint feature learning has been proposed to enhance the feature expression by exploiting multiple characteristics from diverse views. In this paper, we first introduced six types of palmprint representation methods published from 2004 to 2022, which described the characteristics of palmprints from a single view. Afterward, a number of multiview-learning-based palmprint recognition methods (2004–2022) were listed, which discussed how to achieve better recognition performances by adopting different complementary types of features from multiple views. To date, there is no work to summarize the multiview fusion for different types of palmprint features. In this paper, the aims, frameworks, and related methods of multiview palmprint representation will be summarized in detail. Full article
(This article belongs to the Special Issue Mathematics-Based Methods in Artificial Intelligence, Pattern Recognition and Deep Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-15
Back to TopTop