Mathematics

Research

Jump to: Review

26 pages, 15315 KiB

Open AccessArticle

IFS-Based Image Reconstruction of Binary Images with Functional Networks

by Akemi Gálvez, Iztok Fister, Andrés Iglesias, Iztok Fister, Jr., Valentín Gómez-Jauregui, Cristina Manchado and César Otero

Mathematics 2022, 10(7), 1107; https://doi.org/10.3390/math10071107 - 29 Mar 2022

Cited by 1 | Viewed by 1748

Abstract

This work addresses the IFS-based image reconstruction problem for binary images. Given a binary image as the input, the goal is to obtain all the parameters of an iterated function system whose attractor approximates the input image accurately; the quality of this approximation [...] Read more.

This work addresses the IFS-based image reconstruction problem for binary images. Given a binary image as the input, the goal is to obtain all the parameters of an iterated function system whose attractor approximates the input image accurately; the quality of this approximation is measured according to a similarity function between the original and the reconstructed images. This paper introduces a new method to tackle this issue. The method is based on functional networks, a powerful extension of neural networks that uses functions instead of the scalar weights typically found in standard neural networks. The method relies on an artificial network comprised of several functional networks, one for each of the contractive affine maps forming the IFS. The method is applied to an illustrative and challenging example of a fractal binary image exhibiting a complicated shape. The graphical and numerical results show that the method performs very well and is able to reconstruct the input image using IFS with high accuracy. The results also show that the method is not yet optimal and offers room for further improvement. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

30 pages, 14633 KiB

Open AccessArticle

Reversible Data Hiding with a New Local Contrast Enhancement Approach

by Eduardo Fragoso-Navarro, Manuel Cedillo-Hernandez, Francisco Garcia-Ugalde and Robert Morelos-Zaragoza

Mathematics 2022, 10(5), 841; https://doi.org/10.3390/math10050841 - 7 Mar 2022

Cited by 5 | Viewed by 2531

Abstract

Reversible data hiding schemes hide information into a digital image and simultaneously increase its contrast. The improvements of the different approaches aim to increase the capacity, contrast, and quality of the image. However, recent proposals contrast the image globally and lose local details [...] Read more.

Reversible data hiding schemes hide information into a digital image and simultaneously increase its contrast. The improvements of the different approaches aim to increase the capacity, contrast, and quality of the image. However, recent proposals contrast the image globally and lose local details since they use two common methodologies that may not contribute to obtaining better results. Firstly, to generate vacancies for hiding information, most schemes start with a preprocessing applied to the histogram that may introduce visual distortions and set the maximum hiding rate in advance. Secondly, just a few hiding ranges are selected in the histogram, which means that just limited contrast and capacity may be achieved. To solve these problems, in this paper, a novel approach without preprocessing performs an automatic selection of multiple hiding ranges into the histograms. The selection stage is based on an optimization process, and the iterative-based algorithm increases capacity at embedding execution. Results show that quality and capacity values overcome previous approaches. Additionally, visual results show how greyscale values are better differentiated in the image, revealing details globally and locally. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

26 pages, 35233 KiB

Open AccessArticle

Deep Red Lesion Classification for Early Screening of Diabetic Retinopathy

by Muhammad Nadeem Ashraf, Muhammad Hussain and Zulfiqar Habib

Mathematics 2022, 10(5), 686; https://doi.org/10.3390/math10050686 - 23 Feb 2022

Cited by 4 | Viewed by 2520

Abstract

Diabetic retinopathy (DR) is an asymptotic and vision-threatening complication among working-age adults. To prevent blindness, a deep convolutional neural network (CNN) based diagnosis can help to classify less-discriminative and small-sized red lesions in early screening of DR patients. However, training deep models with [...] Read more.

Diabetic retinopathy (DR) is an asymptotic and vision-threatening complication among working-age adults. To prevent blindness, a deep convolutional neural network (CNN) based diagnosis can help to classify less-discriminative and small-sized red lesions in early screening of DR patients. However, training deep models with minimal data is a challenging task. Fine-tuning through transfer learning is a useful alternative, but performance degradation, overfitting, and domain adaptation issues further demand architectural amendments to effectively train deep models. Various pre-trained CNNs are fine-tuned on an augmented set of image patches. The best-performing ResNet50 model is modified by introducing reinforced skip connections, a global max-pooling layer, and the sum-of-squared-error loss function. The performance of the modified model (DR-ResNet50) on five public datasets is found to be better than state-of-the-art methods in terms of well-known metrics. The highest scores (0.9851, 0.991, 0.991, 0.991, 0.991, 0.9939, 0.0029, 0.9879, and 0.9879) for sensitivity, specificity, AUC, accuracy, precision, F1-score, false-positive rate, Matthews’s correlation coefficient, and kappa coefficient are obtained within a 95% confidence interval for unseen test instances from e-Ophtha_MA. This high sensitivity and low false-positive rate demonstrate the worth of a proposed framework. It is suitable for early screening due to its performance, simplicity, and robustness. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

17 pages, 5224 KiB

Open AccessArticle

PDE-Based 3D Surface Reconstruction from Multi-View 2D Images

by Zaiping Zhu, Andres Iglesias, Liqi Zhou, Lihua You and Jianjun Zhang

Mathematics 2022, 10(4), 542; https://doi.org/10.3390/math10040542 - 9 Feb 2022

Cited by 5 | Viewed by 4122

Abstract

Partial differential equation (PDE) based surfaces own a lot of advantages, compared to other types of 3D representation. For instance, fewer variables are required to represent the same 3D shape; the position, tangent, and even curvature continuity between PDE surface patches can be [...] Read more.

Partial differential equation (PDE) based surfaces own a lot of advantages, compared to other types of 3D representation. For instance, fewer variables are required to represent the same 3D shape; the position, tangent, and even curvature continuity between PDE surface patches can be naturally maintained when certain conditions are satisfied, and the physics-based nature is also kept. Although some works applied implicit PDEs to 3D surface reconstruction from images, there is little work on exploiting the explicit solutions of PDE to this topic, which is more efficient and accurate. In this paper, we propose a new method to apply the explicit solutions of a fourth-order partial differential equation to surface reconstruction from multi-view images. The method includes two stages: point clouds data are extracted from multi-view images in the first stage, which is followed by PDE-based surface reconstruction from the obtained point clouds data. Our computational experiments show that the reconstructed PDE surfaces exhibit good quality and can recover the ground truth with high accuracy. A comparison between various solutions with different complexity to the fourth-order PDE is also made to demonstrate the power and flexibility of our proposed explicit PDE for surface reconstruction from images. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

14 pages, 3187 KiB

Open AccessArticle

GeoStamp: Detail Transfer Based on Mean Curvature Field

by Jung-Ho Park, Ji-Hye Moon, Sanghun Park and Seung-Hyun Yoon

Mathematics 2022, 10(3), 500; https://doi.org/10.3390/math10030500 - 4 Feb 2022

Cited by 2 | Viewed by 1641

Abstract

A shape detail transfer is the process of extracting the geometric details of a source region and transferring it onto a target region. In this paper, we present a simple and effective method, called GeoStamp, for transferring shape details using a Poisson [...] Read more.

A shape detail transfer is the process of extracting the geometric details of a source region and transferring it onto a target region. In this paper, we present a simple and effective method, called GeoStamp, for transferring shape details using a Poisson equation. First, the mean curvature field on a source region is computed by using the Laplace–Beltrami operator and is defined as the shape details of the source region. Subsequently, the source and target regions are parameterized on a common 2D domain, and a mean curvature field on the target region is interpolated by the correspondence between two regions. Finally, we solve the Poisson equation using the interpolated mean curvature field and the Laplacian matrix of the target region. Consequently, the mean curvature field of the target region is replaced with that of the source region, which results in the transfer of shape details from the source region to the target region. We demonstrate the effectiveness of our technique by showing several examples and also show that our method is quite useful for adding shape details to a surface patch filling a hole in a triangular mesh. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

26 pages, 17007 KiB

Open AccessArticle

CellsDeepNet: A Novel Deep Learning-Based Web Application for the Automated Morphometric Analysis of Corneal Endothelial Cells

by Alaa S. Al-Waisy, Abdulrahman Alruban, Shumoos Al-Fahdawi, Rami Qahwaji, Georgios Ponirakis, Rayaz A. Malik, Mazin Abed Mohammed and Seifedine Kadry

Mathematics 2022, 10(3), 320; https://doi.org/10.3390/math10030320 - 20 Jan 2022

Cited by 8 | Viewed by 2733

Abstract

The quantification of corneal endothelial cell (CEC) morphology using manual and semi-automatic software enables an objective assessment of corneal endothelial pathology. However, the procedure is tedious, subjective, and not widely applied in clinical practice. We have developed the CellsDeepNet system to automatically segment [...] Read more.

The quantification of corneal endothelial cell (CEC) morphology using manual and semi-automatic software enables an objective assessment of corneal endothelial pathology. However, the procedure is tedious, subjective, and not widely applied in clinical practice. We have developed the CellsDeepNet system to automatically segment and analyse the CEC morphology. The CellsDeepNet system uses Contrast-Limited Adaptive Histogram Equalization (CLAHE) to improve the contrast of the CEC images and reduce the effects of non-uniform image illumination, 2D Double-Density Dual-Tree Complex Wavelet Transform (2DDD-TCWT) to reduce noise, Butterworth Bandpass filter to enhance the CEC edges, and moving average filter to adjust for brightness level. An improved version of U-Net was used to detect the boundaries of the CECs, regardless of the CEC size. CEC morphology was measured as mean cell density (MCD, cell/mm²), mean cell area (MCA, μm²), mean cell perimeter (MCP, μm), polymegathism (coefficient of CEC size variation), and pleomorphism (percentage of hexagonality coefficient). The CellsDeepNet system correlated highly significantly with the manual estimations for MCD (r = 0.94), MCA (r = 0.99), MCP (r = 0.99), polymegathism (r = 0.92), and pleomorphism (r = 0.86), with p < 0.0001 for all the extracted clinical features. The Bland–Altman plots showed excellent agreement. The percentage difference between the manual and automated estimations was superior for the CellsDeepNet system compared to the CEAS system and other state-of-the-art CEC segmentation systems on three large and challenging corneal endothelium image datasets captured using two different ophthalmic devices. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 5541 KiB

Open AccessArticle

3D Modelling with C² Continuous PDE Surface Patches

by Haibin Fu, Shaojun Bian, Ouwen Li, Jon Macey, Andres Iglesias, Ehtzaz Chaudhry, Lihua You and Jian Jun Zhang

Mathematics 2022, 10(3), 319; https://doi.org/10.3390/math10030319 - 20 Jan 2022

Cited by 1 | Viewed by 2043

Abstract

In this paper, we present a new modelling method to create 3D models. First, characteristic cross section curves are generated and approximated by generalized elliptic curves. Then, a vector-valued sixth-order partial differential equation is proposed, and its closed form solution is derived to [...] Read more.

In this paper, we present a new modelling method to create 3D models. First, characteristic cross section curves are generated and approximated by generalized elliptic curves. Then, a vector-valued sixth-order partial differential equation is proposed, and its closed form solution is derived to create PDE surface patches from cross section curves where two adjacent PDE-surface patches are automatically stitched together. With the approach presented in this paper, C² continuity between adjacent surface patches is well-maintained. Since surface creation of the model is transformed into the generation of cross sectional curves and few undetermined constants are required to describe cross sectional curves accurately, the proposed approach can save manual operations, reduce information storage, and generate 3D models quickly. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

Figure 1
Comparison of different digital 3D modeling methods. Full article ">Figure 2
Overall proposed algorithm. Full article ">Figure 3
Curve fitting example. The ground truth curves are shown in blue and fitted generalized elliptic curves are in red. Full article ">Figure 4
Surface creation example. The six curves <math display="inline"><semantics> <mrow> <msub> <mi mathvariant="bold-italic">C</mi> <mn>4</mn> </msub> </mrow> </semantics></math> − <math display="inline"><semantics> <mrow> <msub> <mi mathvariant="bold-italic">C</mi> <mn>9</mn> </msub> </mrow> </semantics></math> (red) are used to construct the PDE surface patch 1. Full article ">Figure 5
The cross section curves and created human body parts. Full article ">Figure 6
The cross section curves of the human body and the created human body model in front and side views using <math display="inline"><semantics> <mrow> <msup> <mi>C</mi> <mn>2</mn> </msup> </mrow> </semantics></math> continues PDE method. Full article ">Figure 7
Surface shape generation from cross section curves by using the method proposed in this paper. (a) a smooth vase model, (b) a horse belly model, (c) front leg and nose models of an elephant. Full article ">

15 pages, 20739 KiB

Open AccessArticle

Melanoma Classification from Dermoscopy Images Using Ensemble of Convolutional Neural Networks

by Rehan Raza, Fatima Zulfiqar, Shehroz Tariq, Gull Bano Anwar, Allah Bux Sargano and Zulfiqar Habib

Mathematics 2022, 10(1), 26; https://doi.org/10.3390/math10010026 - 22 Dec 2021

Cited by 29 | Viewed by 5041

Abstract

Human skin is the most exposed part of the human body that needs constant protection and care from heat, light, dust, and direct exposure to other harmful radiation, such as UV rays. Skin cancer is one of the dangerous diseases found in humans. [...] Read more.

Human skin is the most exposed part of the human body that needs constant protection and care from heat, light, dust, and direct exposure to other harmful radiation, such as UV rays. Skin cancer is one of the dangerous diseases found in humans. Melanoma is a form of skin cancer that begins in the cells (melanocytes) that control the pigment in human skin. Early detection and diagnosis of skin cancer, such as melanoma, is necessary to reduce the death rate due to skin cancer. In this paper, the classification of acral lentiginous melanoma, a type of melanoma with benign nevi, is being carried out. The proposed stacked ensemble method for melanoma classification uses different pre-trained models, such as Xception, Inceptionv3, InceptionResNet-V2, DenseNet121, and DenseNet201, by employing the concept of transfer learning and fine-tuning. The selection of pre-trained CNN architectures for transfer learning is based on models having the highest top-1 and top-5 accuracies on ImageNet. A novel stacked ensemble-based framework is presented to improve the generalizability and increase robustness by fusing fine-tuned pre-trained CNN models for acral lentiginous melanoma classification. The performance of the proposed method is evaluated by experimenting on a Figshare benchmark dataset. The impact of applying different augmentation techniques has also been analyzed through extensive experimentations. The results confirm that the proposed method outperforms state-of-the-art techniques and achieves an accuracy of 97.93%. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

19 pages, 27092 KiB

Open AccessArticle

PDE Surface-Represented Facial Blendshapes

by Haibin Fu, Shaojun Bian, Ehtzaz Chaudhry, Shuangbu Wang, Lihua You and Jian Jun Zhang

Mathematics 2021, 9(22), 2905; https://doi.org/10.3390/math9222905 - 15 Nov 2021

Cited by 1 | Viewed by 2491

Abstract

Partial differential equation (PDE)-based geometric modelling and computer animation has been extensively investigated in the last three decades. However, the PDE surface-represented facial blendshapes have not been investigated. In this paper, we propose a new method of facial blendshapes by using curve-defined and [...] Read more.

Partial differential equation (PDE)-based geometric modelling and computer animation has been extensively investigated in the last three decades. However, the PDE surface-represented facial blendshapes have not been investigated. In this paper, we propose a new method of facial blendshapes by using curve-defined and Fourier series-represented PDE surfaces. In order to develop this new method, first, we design a curve template and use it to extract curves from polygon facial models. Then, we propose a second-order partial differential equation and combine it with the constraints of the extracted curves as boundary curves to develop a mathematical model of curve-defined PDE surfaces. After that, we introduce a generalized Fourier series representation to solve the second-order partial differential equation subjected to the constraints of the extracted boundary curves and obtain an analytical mathematical expression of curve-defined and Fourier series-represented PDE surfaces. The mathematical expression is used to develop a new PDE surface-based interpolation method of creating new facial models from one source facial model and one target facial model and a new PDE surface-based blending method of creating more new facial models from one source facial model and many target facial models. Some examples are presented to demonstrate the effectiveness and applications of the proposed method in 3D facial blendshapes. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

15 pages, 854 KiB

Open AccessArticle

DSTnet: Deformable Spatio-Temporal Convolutional Residual Network for Video Super-Resolution

by Anusha Khan, Allah Bux Sargano and Zulfiqar Habib

Mathematics 2021, 9(22), 2873; https://doi.org/10.3390/math9222873 - 12 Nov 2021

Cited by 1 | Viewed by 2500

Abstract

Video super-resolution (VSR) aims at generating high-resolution (HR) video frames with plausible and temporally consistent details using their low-resolution (LR) counterparts, and neighboring frames. The key challenge for VSR lies in the effective exploitation of intra-frame spatial relation and temporal dependency between consecutive [...] Read more.

Video super-resolution (VSR) aims at generating high-resolution (HR) video frames with plausible and temporally consistent details using their low-resolution (LR) counterparts, and neighboring frames. The key challenge for VSR lies in the effective exploitation of intra-frame spatial relation and temporal dependency between consecutive frames. Many existing techniques utilize spatial and temporal information separately and compensate motion via alignment. These methods cannot fully exploit the spatio-temporal information that significantly affects the quality of resultant HR videos. In this work, a novel deformable spatio-temporal convolutional residual network (DSTnet) is proposed to overcome the issues of separate motion estimation and compensation methods for VSR. The proposed framework consists of 3D convolutional residual blocks decomposed into spatial and temporal (2+1) D streams. This decomposition can simultaneously utilize input video’s spatial and temporal features without a separate motion estimation and compensation module. Furthermore, the deformable convolution layers have been used in the proposed model that enhances its motion-awareness capability. Our contribution is twofold; firstly, the proposed approach can overcome the challenges in modeling complex motions by efficiently using spatio-temporal information. Secondly, the proposed model has fewer parameters to learn than state-of-the-art methods, making it a computationally lean and efficient framework for VSR. Experiments are conducted on a benchmark Vid4 dataset to evaluate the efficacy of the proposed approach. The results demonstrate that the proposed approach achieves superior quantitative and qualitative performance compared to the state-of-the-art methods. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

15 pages, 3985 KiB

Open AccessArticle

Optimized Unidirectional and Bidirectional Stiffened Objects for Minimum Material Consumption of 3D Printing

by Anzong Zheng, Zaiping Zhu, Shaojun Bian, Jian Chang, Habibollah Haron, Andres Iglesias, Lihua You and Jianjun Zhang

Mathematics 2021, 9(21), 2835; https://doi.org/10.3390/math9212835 - 8 Nov 2021

Cited by 1 | Viewed by 2283

Abstract

3D printing, regarded as the most popular additive manufacturing technology, is finding many applications in various industrial sectors. Along with the increasing number of its industrial applications, reducing its material consumption and increasing the strength of 3D printed objects have become an important [...] Read more.

3D printing, regarded as the most popular additive manufacturing technology, is finding many applications in various industrial sectors. Along with the increasing number of its industrial applications, reducing its material consumption and increasing the strength of 3D printed objects have become an important topic. In this paper, we introduce unidirectionally and bidirectionally stiffened structures into 3D printing to increase the strength and stiffness of 3D printed objects and reduce their material consumption. To maximize the advantages of such stiffened structures, we investigated finite element analysis, especially for general cases of stiffeners in arbitrary positions and directions, and performed optimization design to minimize the total volume of stiffened structures. Many examples are presented to demonstrate the effectiveness of the proposed finite element analysis and optimization design as well as significant reductions in the material costs and stresses in 3D printed objects stiffened with unidirectional and bidirectional stiffeners. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

23 pages, 108354 KiB

Open AccessArticle

Imperceptible–Visible Watermarking to Information Security Tasks in Color Imaging

by Oswaldo Ulises Juarez-Sandoval, Francisco Javier Garcia-Ugalde, Manuel Cedillo-Hernandez, Jazmin Ramirez-Hernandez and Leobardo Hernandez-Gonzalez

Mathematics 2021, 9(19), 2374; https://doi.org/10.3390/math9192374 - 24 Sep 2021

Cited by 7 | Viewed by 3048

Abstract

Digital image watermarking algorithms have been designed for intellectual property, copyright protection, medical data management, and other related fields; furthermore, in real-world applications such as official documents, banknotes, etc., they are used to deliver additional information about the documents’ authenticity. In this context, [...] Read more.

Digital image watermarking algorithms have been designed for intellectual property, copyright protection, medical data management, and other related fields; furthermore, in real-world applications such as official documents, banknotes, etc., they are used to deliver additional information about the documents’ authenticity. In this context, the imperceptible–visible watermarking (IVW) algorithm has been designed as a digital reproduction of the real-world watermarks. This paper presents a new improved IVW algorithm for copyright protection that can deliver additional information to the image content. The proposed algorithm is divided into two stages: in the embedding stage, a human visual system-based strategy is used to embed an owner logotype or a 2D quick response (QR) code as a watermark into a color image, maintaining a high watermark imperceptibility and low image-quality degradation. In the exhibition, a new histogram binarization function approach is introduced to exhibit any watermark with enough quality to be recognized or decoded by any application, which is focused on reading QR codes. The experimental results show that the proposed algorithm can embed one or more watermark patterns, maintaining the high imperceptibility and visual quality of the embedded and the exhibited watermark. The performance evaluation shows that the method overcomes several drawbacks reported in previous algorithms, including geometric and image processing attacks such as JPEG and JPEG2000. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

11 pages, 2680 KiB

Open AccessArticle

Voxel-Based 3D Object Reconstruction from Single 2D Image Using Variational Autoencoders

by Rohan Tahir, Allah Bux Sargano and Zulfiqar Habib

Mathematics 2021, 9(18), 2288; https://doi.org/10.3390/math9182288 - 17 Sep 2021

Cited by 23 | Viewed by 8910

Abstract

In recent years, learning-based approaches for 3D reconstruction have gained much popularity due to their encouraging results. However, unlike 2D images, 3D cannot be represented in its canonical form to make it computationally lean and memory-efficient. Moreover, the generation of a 3D model [...] Read more.

In recent years, learning-based approaches for 3D reconstruction have gained much popularity due to their encouraging results. However, unlike 2D images, 3D cannot be represented in its canonical form to make it computationally lean and memory-efficient. Moreover, the generation of a 3D model directly from a single 2D image is even more challenging due to the limited details available from the image for 3D reconstruction. Existing learning-based techniques still lack the desired resolution, efficiency, and smoothness of the 3D models required for many practical applications. In this paper, we propose voxel-based 3D object reconstruction (V3DOR) from a single 2D image for better accuracy, one using autoencoders (AE) and another using variational autoencoders (VAE). The encoder part of both models is used to learn suitable compressed latent representation from a single 2D image, and a decoder generates a corresponding 3D model. Our contribution is twofold. First, to the best of the authors’ knowledge, it is the first time that variational autoencoders (VAE) have been employed for the 3D reconstruction problem. Second, the proposed models extract a discriminative set of features and generate a smoother and high-resolution 3D model. To evaluate the efficacy of the proposed method, experiments have been conducted on a benchmark ShapeNet data set. The results confirm that the proposed method outperforms state-of-the-art methods. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

43 pages, 20071 KiB

Open AccessArticle

Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN

by Ja Hyung Koo, Se Woon Cho, Na Rae Baek and Kang Ryoung Park

Mathematics 2021, 9(16), 1934; https://doi.org/10.3390/math9161934 - 13 Aug 2021

Cited by 7 | Viewed by 2511

Abstract

Human recognition in indoor environments occurs both during the day and at night. During the day, human recognition encounters performance degradation owing to a blur generated when a camera captures a person’s image. However, when images are captured at night with a camera, [...] Read more.

Human recognition in indoor environments occurs both during the day and at night. During the day, human recognition encounters performance degradation owing to a blur generated when a camera captures a person’s image. However, when images are captured at night with a camera, it is difficult to obtain perfect images of a person without light, and the input images are very noisy owing to the properties of camera sensors in low-illumination environments. Studies have been conducted in the past on face recognition in low-illumination environments; however, there is lack of research on face- and body-based human recognition in very low illumination environments. To solve these problems, this study proposes a modified enlighten generative adversarial network (modified EnlightenGAN) in which a very low illumination image is converted to a normal illumination image, and the matching scores of deep convolutional neural network (CNN) features of the face and body in the converted image are combined with a score-level fusion for recognition. The two types of databases used in this study are the Dongguk face and body database version 3 (DFB-DB3) and the ChokePoint open dataset. The results of the experiment conducted using the two databases show that the human verification accuracy (equal error rate (ERR)) and identification accuracy (rank 1 genuine acceptance rate (GAR)) of the proposed method were 7.291% and 92.67% for DFB-DB3 and 10.59% and 87.78% for the ChokePoint dataset, respectively. Accordingly, the performance of the proposed method was better than the previous methods. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

12 pages, 5900 KiB

Open AccessArticle

The Development of Long-Distance Viewing Direction Analysis and Recognition of Observed Objects Using Head Image and Deep Learning

by Yu-Shiuan Tsai, Nai-Chi Chen, Yi-Zeng Hsieh and Shih-Syun Lin

Mathematics 2021, 9(16), 1880; https://doi.org/10.3390/math9161880 - 7 Aug 2021

Cited by 1 | Viewed by 2512

Abstract

In this study, we use OpenPose to capture many facial feature nodes, create a data set and label it, and finally bring in the neural network model we created. The purpose is to predict the direction of the person’s line of sight from [...] Read more.

In this study, we use OpenPose to capture many facial feature nodes, create a data set and label it, and finally bring in the neural network model we created. The purpose is to predict the direction of the person’s line of sight from the face and facial feature nodes and finally add object detection technology to calculate the object that the person is observing. After implementing this method, we found that this method can correctly estimate the human body’s form. Furthermore, if multiple lenses can get more information, the effect will be better than a single lens, evaluating the observed objects more accurately. Furthermore, we found that the head in the image can judge the direction of view. In addition, we found that in the case of the test face tilt, approximately at a tilt angle of 60 degrees, the face nodes can still be captured. Similarly, when the inclination angle is greater than 60 degrees, the facing node cannot be used. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 5767 KiB

Open AccessArticle

Image Region Prediction from Thermal Videos Based on Image Prediction Generative Adversarial Network

by Ganbayar Batchuluun, Ja Hyung Koo, Yu Hwan Kim and Kang Ryoung Park

Mathematics 2021, 9(9), 1053; https://doi.org/10.3390/math9091053 - 7 May 2021

Cited by 6 | Viewed by 2386

Abstract

Various studies have been conducted on object detection, tracking, and action recognition based on thermal images. However, errors occur during object detection, tracking, and action recognition when a moving object leaves the field of view (FOV) of a camera and part of the [...] Read more.

Various studies have been conducted on object detection, tracking, and action recognition based on thermal images. However, errors occur during object detection, tracking, and action recognition when a moving object leaves the field of view (FOV) of a camera and part of the object becomes invisible. However, no studies have examined this issue so far. Therefore, this article proposes a method for widening the FOV of the current image by predicting images outside the FOV of the camera using the current image and previous sequential images. In the proposed method, the original one-channel thermal image is converted into a three-channel thermal image to perform image prediction using an image prediction generative adversarial network. When image prediction and object detection experiments were conducted using the marathon sub-dataset of the Boston University-thermal infrared video (BU-TIV) benchmark open dataset, we confirmed that the proposed method showed the higher accuracies of image prediction (structural similarity index measure (SSIM) of 0.9839) and object detection (F1 score (F1) of 0.882, accuracy (ACC) of 0.983, and intersection over union (IoU) of 0.791) than the state-of-the-art methods. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

18 pages, 4585 KiB

Open AccessArticle

Semantic Segmentation by Multi-Scale Feature Extraction Based on Grouped Dilated Convolution Module

by Dong Seop Kim, Yu Hwan Kim and Kang Ryoung Park

Mathematics 2021, 9(9), 947; https://doi.org/10.3390/math9090947 - 23 Apr 2021

Cited by 7 | Viewed by 3160

Abstract

Existing studies have shown that effective extraction of multi-scale information is a crucial factor directly related to the increase in performance of semantic segmentation. Accordingly, various methods for extracting multi-scale information have been developed. However, these methods face problems in that they require [...] Read more.

Existing studies have shown that effective extraction of multi-scale information is a crucial factor directly related to the increase in performance of semantic segmentation. Accordingly, various methods for extracting multi-scale information have been developed. However, these methods face problems in that they require additional calculations and vast computing resources. To address these problems, this study proposes a grouped dilated convolution module that combines existing grouped convolutions and atrous spatial pyramid pooling techniques. The proposed method can learn multi-scale features more simply and effectively than existing methods. Because each convolution group has different dilations in the proposed model, they have receptive fields of different sizes and can learn features corresponding to these receptive fields. As a result, multi-scale context can be easily extracted. Moreover, optimal hyper-parameters are obtained from an in-depth analysis, and excellent segmentation performance is derived. To evaluate the proposed method, open databases of the Cambridge Driving Labeled Video Database (CamVid) and the Stanford Background Dataset (SBD) are utilized. The experimental results indicate that the proposed method shows a mean intersection over union of 73.15% based on the CamVid dataset and 72.81% based on the SBD, thereby exhibiting excellent performance compared to other state-of-the-art methods. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

Figure 1
Examples of semantic segmentation applying pixel-wise classification, with the left column showing input images and the right column showing ground truth in which challenging factors, such as various classes and multi-scale objects, exist. Full article ">Figure 2
Examples of each method: (a) grouped convolutions when G is two; (b) atrous pyramid pooling based on dilated convolutions among spatial pyramid pooling techniques; (c) structure of the proposed GDCM. * means convolution operation. Full article ">Figure 3
Proposed GDCM in which all 32 grouped convolutions are applied in a convolution layer. All are divided into four subgroups that apply different dilation convolutions. The value of a dilation parameter is established to be 1, 2, 3 or 4 according to the group, and the final output is derived via concatenation. Full article ">Figure 4
Examples of experimental databases: (a,b) CamVid; (c,d) SBD; In (a–d), the left and right images show the input and ground-truth images, respectively. Full article ">Figure 4 Cont.
Examples of experimental databases: (a,b) CamVid; (c,d) SBD; In (a–d), the left and right images show the input and ground-truth images, respectively. Full article ">Figure 5
Training loss graphs. Full article ">Figure 6
Detected results by proposed method. The images in the 1st and 2nd rows are from CamVid and those in the 3rd row are from SBD. In each row, input, ground-truth, and detected result are respectively shown from the left. Class information is shown in <a href="#mathematics-09-00947-f004" class="html-fig">Figure 4</a>. Full article ">Figure 7
Jetson TX2 embedded system. Full article ">

14 pages, 8447 KiB

Open AccessArticle

Underwater Image Enhancement Based on Multi-Scale Fusion and Global Stretching of Dual-Model

by Huajun Song and Rui Wang

Mathematics 2021, 9(6), 595; https://doi.org/10.3390/math9060595 - 10 Mar 2021

Cited by 18 | Viewed by 3783

Abstract

Aimed at the two problems of color deviation and poor visibility of the underwater image, this paper proposes an underwater image enhancement method based on the multi-scale fusion and global stretching of dual-model (MFGS), which does not rely on the underwater optical imaging [...] Read more.

Aimed at the two problems of color deviation and poor visibility of the underwater image, this paper proposes an underwater image enhancement method based on the multi-scale fusion and global stretching of dual-model (MFGS), which does not rely on the underwater optical imaging model. The proposed method consists of three stages: Compared with other color correction algorithms, white-balancing can effectively eliminate the undesirable color deviation caused by medium attenuation, so it is selected to correct the color deviation in the first stage. Then, aimed at the problem of the poor performance of the saliency weight map in the traditional fusion processing, this paper proposed an updated strategy of saliency weight coefficient combining contrast and spatial cues to achieve high-quality fusion. Finally, by analyzing the characteristics of the results of the above steps, it is found that the brightness and clarity need to be further improved. The global stretching of the full channel in the red, green, blue (RGB) model is applied to enhance the color contrast, and the selective stretching of the L channel in the Commission International Eclairage-Lab (CIE-Lab) model is implemented to achieve a better de-hazing effect. Quantitative and qualitative assessments on the underwater image enhancement benchmark dataset (UIEBD) show that the enhanced images of the proposed approach achieve significant and sufficient improvements in color and visibility. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

Review

Jump to: Research

38 pages, 2144 KiB

Open AccessReview

Digital Video Tampering Detection and Localization: Review, Representations, Challenges and Algorithm

by Naheed Akhtar, Mubbashar Saddique, Khurshid Asghar, Usama Ijaz Bajwa, Muhammad Hussain and Zulfiqar Habib

Mathematics 2022, 10(2), 168; https://doi.org/10.3390/math10020168 - 6 Jan 2022

Cited by 27 | Viewed by 6653

Abstract

Digital videos are now low-cost, easy to capture and easy to share on social media due to the common feature of video recording in smart phones and digital devices. However, with the advancement of video editing tools, videos can be tampered (forged) easily [...] Read more.

Digital videos are now low-cost, easy to capture and easy to share on social media due to the common feature of video recording in smart phones and digital devices. However, with the advancement of video editing tools, videos can be tampered (forged) easily for propaganda or to gain illegal advantages—ultimately, the authenticity of videos shared on social media cannot be taken for granted. Over the years, significant research has been devoted to developing new techniques for detecting different types of video tampering. In this paper, we offer a detailed review of existing passive video tampering detection techniques in a systematic way. The answers to research questions prepared for this study are also elaborated. The state-of-the-art research work is analyzed extensively, highlighting the pros and cons and commonly used datasets. Limitations of existing video forensic algorithms are discussed, and we conclude with research challenges and future directions. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 9520 KiB

Open AccessReview

Mathematical Principles of Object 3D Reconstruction by Shape-from-Focus Methods

by Dalibor Martišek and Karel Mikulášek

Mathematics 2021, 9(18), 2253; https://doi.org/10.3390/math9182253 - 14 Sep 2021

Cited by 3 | Viewed by 2671

Abstract

Shape-from-Focus (SFF) methods have been developed for about twenty years. They able to obtain the shape of 3D objects from a series of partially focused images. The plane to which the microscope or camera is focused intersects the 3D object in a contour [...] Read more.

Shape-from-Focus (SFF) methods have been developed for about twenty years. They able to obtain the shape of 3D objects from a series of partially focused images. The plane to which the microscope or camera is focused intersects the 3D object in a contour line. Due to wave properties of light and due to finite resolution of the output device, the image can be considered as sharp not only on this contour line, but also in a certain interval of height—the zone of sharpness. SSFs are able to identify these focused parts to compose a fully focused 2D image and to reconstruct a 3D profile of the surface to be observed. Full article

(This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Computer Graphics, Image Processing and Artificial Intelligence

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (20 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI