sensors-logo

Journal Browser

Journal Browser

Special Issue "Computational Methods in Imagery (CMI)"

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: closed (28 February 2022) | Viewed by 13570

Special Issue Editors

1. University of Pennsylvania Goddard Bldg., 3710 Hamilton Walk, Philadelphia, PA 19104, USA
2. Computer Vision and System Laboratory (CVSL), Department of Electrical and Computer Engineering, Laval University, Quebec City, QC, Canada
Interests: infrared hyperspectral imagery; pattern recognition; machine learning
Special Issues, Collections and Topics in MDPI journals
Research Assistant Professor, Department of Electrical and Computer Engineering—Electrophysics, University of Southern California, Pasadena, CA, USA
Interests: microwave remote sensing; applied and computational electromagnetics; radar remote sensing; inverse models and algorithms for environmental and Earth science applications
Special Issues, Collections and Topics in MDPI journals
Department of Information Engineering and Computer Science and Mathematics, University of L’Aquila, L'Aquila, Italy
Interests: Numerical Analysis; Applied Mathematics; Mathematics of Signal Processing
Department of Industrial and Information Engineering and Economics, University of L’Aquila, L'Aquila, Italy
Interests: building heritage; building pathology; infrared thermography; in situ and laboratory testing; hygrothermal behaviour of buildings; energy efficiency; thermal comfort; numerical modelling; heat transfer; optical metrology; composite materials; NDT
Special Issues, Collections and Topics in MDPI journals
Computer Vision and Systems Laboratory (CVSL), Department of Electrical and Computer Engineering, Laval University, Quebec City, QC G1V 0A6, Canada
Interests: NDT; health diagnostics; non-invasive imaging; autonomous systems inspections; composites; structures; thermal imaging; monitoring
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The importance of computational imaging techniques is unequivocally recognized in industries for a variety of applications, including medical, environmental, and security applications. Many techniques have been developed to strengthen previous approaches by improving the computational time, safety (quality control and monitoring), accuracy, reliability, and computational time. Such methods are considerably attractive to scientists, engineers, and those in various industries. This Special Issue, “Computational Methods in Imagery (CMI)” focuses on development, comparison, and application of sensors in image analysis, mathematical methods, and laboratory and in-situ measurements. The subjects include, but are not limited to, the following:

  • Computational image processing methods, models, and algorithms.
  • Machine learning and pattern recognition approaches in infrared and thermography.
  • Medical imaging for diagnostic and prognostic assessments.
  • Enhanced experimental methodologies involving different excitation ways such as mechanical, laser, optical, and inductive.
  • Numerical modelling integrated with experimental tests.
  • Applications in radar remote sensing, environmental and Earth science, imaging-based material evaluation, art and cultural heritage, archeology, and advanced industrial applications.

Dr. Bardia Yousefi
Dr. Alireza Tabatabaeenejad
Dr. Antonio Cicone
Dr. Stefano Sfarra
Prof. Dr. Nicolas P. Avdelidis
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. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (7 papers)

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

Research

Article
Light Field Reconstruction Using Residual Networks on Raw Images
Sensors 2022, 22(5), 1956; https://doi.org/10.3390/s22051956 - 02 Mar 2022
Cited by 8 | Viewed by 1908
Abstract
Although Light-Field (LF) technology attracts attention due to its large number of applications, especially with the introduction of consumer LF cameras and its frequent use, reconstructing densely sampled LF images represents a great challenge to the use and development of LF technology. Our [...] Read more.
Although Light-Field (LF) technology attracts attention due to its large number of applications, especially with the introduction of consumer LF cameras and its frequent use, reconstructing densely sampled LF images represents a great challenge to the use and development of LF technology. Our paper proposes a learning-based method to reconstruct densely sampled LF images from a sparse set of input images. We trained our model with raw LF images rather than using multiple images of the same scene. Raw LF can represent the two-dimensional array of images captured in a single image. Therefore, it enables the network to understand and model the relationship between different images of the same scene well and thus restore more texture details and provide better quality. Using raw images has transformed the task from image reconstruction into image-to-image translation. The feature of small-baseline LF was used to define the images to be reconstructed using the nearest input view to initialize input images. Our network was trained end-to-end to minimize the sum of absolute errors between the reconstructed and ground-truth images. Experimental results on three challenging real-world datasets demonstrate the high performance of our proposed method and its outperformance over the state-of-the-art methods. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Article
On the Post Hoc Explainability of Optimized Self-Organizing Reservoir Network for Action Recognition
Sensors 2022, 22(5), 1905; https://doi.org/10.3390/s22051905 - 01 Mar 2022
Cited by 3 | Viewed by 1232
Abstract
This work proposes a novel unsupervised self-organizing network, called the Self-Organizing Convolutional Echo State Network (SO-ConvESN), for learning node centroids and interconnectivity maps compatible with the deterministic initialization of Echo State Network (ESN) input and reservoir weights, in the context of human action [...] Read more.
This work proposes a novel unsupervised self-organizing network, called the Self-Organizing Convolutional Echo State Network (SO-ConvESN), for learning node centroids and interconnectivity maps compatible with the deterministic initialization of Echo State Network (ESN) input and reservoir weights, in the context of human action recognition (HAR). To ensure stability and echo state property in the reservoir, Recurrent Plots (RPs) and Recurrence Quantification Analysis (RQA) techniques are exploited for explainability and characterization of the reservoir dynamics and hence tuning ESN hyperparameters. The optimized self-organizing reservoirs are cascaded with a Convolutional Neural Network (CNN) to ensure that the activation of internal echo state representations (ESRs) echoes similar topological qualities and temporal features of the input time-series, and the CNN efficiently learns the dynamics and multiscale temporal features from the ESRs for action recognition. The hyperparameter optimization (HPO) algorithms are additionally adopted to optimize the CNN stage in SO-ConvESN. Experimental results on the HAR problem using several publicly available 3D-skeleton-based action datasets demonstrate the showcasing of the RPs and RQA technique in examining the explainability of reservoir dynamics for designing stable self-organizing reservoirs and the usefulness of implementing HPOs in SO-ConvESN for the HAR task. The proposed SO-ConvESN exhibits competitive recognition accuracy. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Article
Multi-Excitation Infrared Fusion for Impact Evaluation of Aluminium-BFRP/GFRP Hybrid Composites
Sensors 2021, 21(17), 5961; https://doi.org/10.3390/s21175961 - 05 Sep 2021
Cited by 3 | Viewed by 1400
Abstract
Fibre metal laminates are widely implemented in the aerospace industry owing to the merits of fatigue resistance and plastic properties. An effective defect assessment technique needs to be investigated for this type of composite materials. In order to achieve accurate impact-induced damage evaluation, [...] Read more.
Fibre metal laminates are widely implemented in the aerospace industry owing to the merits of fatigue resistance and plastic properties. An effective defect assessment technique needs to be investigated for this type of composite materials. In order to achieve accurate impact-induced damage evaluation, a multi-excitation infrared fusion method is introduced in this study. Optical excitation thermography with high performance on revealing surface and subsurface defects is combined with vibro-thermography to improve the capability of detection on defects. Quantitative analysis is carried out on the temperature curve to assess the impact-induced deformation. A new image fusion framework including feature extraction, feature selection and fusion steps is proposed to fully utilize the information from two excitation modalities. Six fibre metal laminates which contain aluminium-basalt fibre reinforced plastic and aluminium-glass fibre reinforced plastic are investigated. Features from different perspectives are compared and selected via intensity contrast on deformation area for fusion imaging. Both types of defects (i.e., surface and sub-surface) and the internal deformation situation of these six samples are characterized clearly and intuitively. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Article
A Study of Deep Learning-Based Face Recognition Models for Sibling Identification
Sensors 2021, 21(15), 5068; https://doi.org/10.3390/s21155068 - 27 Jul 2021
Cited by 7 | Viewed by 2718
Abstract
Accurate identification of siblings through face recognition is a challenging task. This is predominantly because of the high degree of similarities among the faces of siblings. In this study, we investigate the use of state-of-the-art deep learning face recognition models to evaluate their [...] Read more.
Accurate identification of siblings through face recognition is a challenging task. This is predominantly because of the high degree of similarities among the faces of siblings. In this study, we investigate the use of state-of-the-art deep learning face recognition models to evaluate their capacity for discrimination between sibling faces using various similarity indices. The specific models examined for this purpose are FaceNet, VGGFace, VGG16, and VGG19. For each pair of images provided, the embeddings have been calculated using the chosen deep learning model. Five standard similarity measures, namely, cosine similarity, Euclidean distance, structured similarity, Manhattan distance, and Minkowski distance, are used to classify images looking for their identity on the threshold defined for each of the similarity measures. The accuracy, precision, and misclassification rate of each model are calculated using standard confusion matrices. Four different experimental datasets for full-frontal-face, eyes, nose, and forehead of sibling pairs are constructed using publicly available HQf subset of the SiblingDB database. The experimental results show that the accuracy of the chosen deep learning models to distinguish siblings based on the full-frontal-face and cropped face areas vary based on the face area compared. It is observed that VGGFace is best while comparing the full-frontal-face and eyes—the accuracy of classification being with more than 95% in this case. However, its accuracy degrades significantly when the noses are compared, while FaceNet provides the best result for classification based on the nose. Similarly, VGG16 and VGG19 are not the best models for classification using the eyes, but these models provide favorable results when foreheads are compared. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Article
New Method for Analysis of the Temporomandibular Joint Using Cone Beam Computed Tomography
Sensors 2021, 21(9), 3070; https://doi.org/10.3390/s21093070 - 28 Apr 2021
Cited by 5 | Viewed by 1512
Abstract
Modern dentistry commonly uses a variety of imaging methods to support diagnosis and treatment. Among them, cone beam computed tomography (CBCT) is particularly useful in presenting head structures, such as the temporomandibular joint (TMJ). The determination of the morphology of the joint is [...] Read more.
Modern dentistry commonly uses a variety of imaging methods to support diagnosis and treatment. Among them, cone beam computed tomography (CBCT) is particularly useful in presenting head structures, such as the temporomandibular joint (TMJ). The determination of the morphology of the joint is an important part of the diagnosis as well as the monitoring of the treatment results. It can be accomplished by measurement of the TMJ gap width at three selected places, taken at a specific cross-section. This study presents a new approach to these measurements. First, the CBCT images are denoised using curvilinear methods, and the volume of interest is determined. Then, the orientation of the vertical cross-section plane is computed based on segmented axial sections of the TMJ head. Finally, the cross-section plane is used to determine the standardized locations, at which the width of the gap between condyle and fossa is measured. The elaborated method was tested on selected TMJ CBCT scans with satisfactory results. The proposed solution lays the basis for the development of an autonomous method of TMJ index identification. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Article
Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model
Sensors 2021, 21(9), 2989; https://doi.org/10.3390/s21092989 - 24 Apr 2021
Cited by 13 | Viewed by 1851
Abstract
Leukaemia is a dysfunction that affects the production of white blood cells in the bone marrow. Young cells are abnormally produced, replacing normal blood cells. Consequently, the person suffers problems in transporting oxygen and in fighting infections. This article proposes a convolutional neural [...] Read more.
Leukaemia is a dysfunction that affects the production of white blood cells in the bone marrow. Young cells are abnormally produced, replacing normal blood cells. Consequently, the person suffers problems in transporting oxygen and in fighting infections. This article proposes a convolutional neural network (CNN) named LeukNet that was inspired on convolutional blocks of VGG-16, but with smaller dense layers. To define the LeukNet parameters, we evaluated different CNNs models and fine-tuning methods using 18 image datasets, with different resolution, contrast, colour and texture characteristics. We applied data augmentation operations to expand the training dataset, and the 5-fold cross-validation led to an accuracy of 98.61%. To evaluate the CNNs generalisation ability, we applied a cross-dataset validation technique. The obtained accuracies using cross-dataset experiments on three datasets were 97.04, 82.46 and 70.24%, which overcome the accuracies obtained by current state-of-the-art methods. We conclude that using the most common and deepest CNNs may not be the best choice for applications where the images to be classified differ from those used in pre-training. Additionally, the adopted cross-dataset validation approach proved to be an excellent choice to evaluate the generalisation capability of a model, as it considers the model performance on unseen data, which is paramount for CAD systems. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Article
CMOS Fixed Pattern Noise Elimination Based on Sparse Unidirectional Hybrid Total Variation
Sensors 2020, 20(19), 5567; https://doi.org/10.3390/s20195567 - 28 Sep 2020
Cited by 2 | Viewed by 1733
Abstract
With the improvement of semiconductor technology, the performance of CMOS Image Sensor has been greatly improved, reaching the same level as that of CCD in dark current, linearity and readout noise. However, due to the production process, CMOS has higher fix pattern noise [...] Read more.
With the improvement of semiconductor technology, the performance of CMOS Image Sensor has been greatly improved, reaching the same level as that of CCD in dark current, linearity and readout noise. However, due to the production process, CMOS has higher fix pattern noise than CCD at present. Therefore, the removal of CMOS fixed pattern noise has become the research content of many scholars. For current fixed pattern noise (FPN) removal methods, the most effective one is based on optimization. Therefore, the optimization method has become the focus of many scholars. However, most optimization models only consider the image itself, and rarely consider the structural characteristics of FPN. The proposed sparse unidirectional hybrid total variation (SUTV) algorithm takes into account both the sparse structure of column fix pattern noise (CFPN) and the random properties of pixel fix pattern noise (PFPN), and uses adaptive adjustment strategies for some parameters. From the experimental values of PSNR and SSM as well as the rate of change, the SUTV model meets the design expectations with effective noise reduction and robustness. Full article
(This article belongs to the Special Issue Computational Methods in Imagery (CMI))
Show Figures

Figure 1

Back to TopTop