Journal of Imaging

17 pages, 910 KiB

Open AccessArticle

Lip Reading by Alternating between Spatiotemporal and Spatial Convolutions

by Dimitrios Tsourounis, Dimitris Kastaniotis and Spiros Fotopoulos

J. Imaging 2021, 7(5), 91; https://doi.org/10.3390/jimaging7050091 - 20 May 2021

Cited by 16 | Viewed by 2401

Lip reading (LR) is the task of predicting the speech utilizing only the visual information of the speaker. In this work, for the first time, the benefits of alternating between spatiotemporal and spatial convolutions for learning effective features from the LR sequences are [...] Read more.

Lip reading (LR) is the task of predicting the speech utilizing only the visual information of the speaker. In this work, for the first time, the benefits of alternating between spatiotemporal and spatial convolutions for learning effective features from the LR sequences are studied. In this context, a new learnable module named ALSOS (Alternating Spatiotemporal and Spatial Convolutions) is introduced in the proposed LR system. The ALSOS module consists of spatiotemporal (3D) and spatial (2D) convolutions along with two conversion components (3D-to-2D and 2D-to-3D) providing a sequence-to-sequence-mapping. The designed LR system utilizes the ALSOS module in-between ResNet blocks, as well as Temporal Convolutional Networks (TCNs) in the backend for classification. The whole framework is composed by feedforward convolutional along with residual layers and can be trained end-to-end directly from the image sequences in the word-level LR problem. The ALSOS module can capture spatiotemporal dynamics and can be advantageous in the task of LR when combined with the ResNet topology. Experiments with different combinations of ALSOS with ResNet are performed on a dataset in Greek language simulating a medical support application scenario and on the popular large-scale LRW-500 dataset of English words. Results indicate that the proposed ALSOS module can improve the performance of a LR system. Overall, the insertion of ALSOS module into the ResNet architecture obtained higher classification accuracy since it incorporates the contribution of the temporal information captured at different spatial scales of the framework. Full article

(This article belongs to the Section Computer Vision and Pattern Recognition)

► Show Figures

Figure 1

15 pages, 2801 KiB

Open AccessArticle

End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream

by Slim Hamdi, Samir Bouindour, Hichem Snoussi, Tian Wang and Mohamed Abid

J. Imaging 2021, 7(5), 90; https://doi.org/10.3390/jimaging7050090 - 19 May 2021

Cited by 12 | Viewed by 3241

Abstract

In recent years, the use of drones for surveillance tasks has been on the rise worldwide. However, in the context of anomaly detection, only normal events are available for the learning process. Therefore, the implementation of a generative learning method in an unsupervised [...] Read more.

In recent years, the use of drones for surveillance tasks has been on the rise worldwide. However, in the context of anomaly detection, only normal events are available for the learning process. Therefore, the implementation of a generative learning method in an unsupervised mode to solve this problem becomes fundamental. In this context, we propose a new end-to-end architecture capable of generating optical flow images from original UAV images and extracting compact spatio-temporal characteristics for anomaly detection purposes. It is designed with a custom loss function as a sum of three terms, the reconstruction loss (

R_{l}

), the generation loss (

G_{l}

) and the compactness loss (

C_{l}

) to ensure an efficient classification of the “deep-one” class. In addition, we propose to minimize the effect of UAV motion in video processing by applying background subtraction on optical flow images. We tested our method on very complex datasets called the mini-drone video dataset, and obtained results surpassing existing techniques’ performances with an AUC of 85.3. Full article

(This article belongs to the Special Issue Image and Video Forensics)

► Show Figures

Figure 1

28 pages, 1508 KiB

Open AccessReview

Feature Extraction for Finger-Vein-Based Identity Recognition

by George K. Sidiropoulos, Polixeni Kiratsa, Petros Chatzipetrou and George A. Papakostas

J. Imaging 2021, 7(5), 89; https://doi.org/10.3390/jimaging7050089 - 15 May 2021

Cited by 25 | Viewed by 5417

Abstract

This paper aims to provide a brief review of the feature extraction methods applied for finger vein recognition. The presented study is designed in a systematic way in order to bring light to the scientific interest for biometric systems based on finger vein [...] Read more.

This paper aims to provide a brief review of the feature extraction methods applied for finger vein recognition. The presented study is designed in a systematic way in order to bring light to the scientific interest for biometric systems based on finger vein biometric features. The analysis spans over a period of 13 years (from 2008 to 2020). The examined feature extraction algorithms are clustered into five categories and are presented in a qualitative manner by focusing mainly on the techniques applied to represent the features of the finger veins that uniquely prove a human’s identity. In addition, the case of non-handcrafted features learned in a deep learning framework is also examined. The conducted literature analysis revealed the increased interest in finger vein biometric systems as well as the high diversity of different feature extraction methods proposed over the past several years. However, last year this interest shifted to the application of Convolutional Neural Networks following the general trend of applying deep learning models in a range of disciplines. Finally, yet importantly, this work highlights the limitations of the existing feature extraction methods and describes the research actions needed to face the identified challenges. Full article

(This article belongs to the Section Biometrics, Forensics, and Security)

► Show Figures

Figure 1

9 pages, 26408 KiB

Open AccessArticle

Remote Density Measurements of Molten Salts via Neutron Radiography

by Alexander M. Long, S. Scott Parker, D. Travis Carver, J. Matt Jackson, Marisa J. Monreal, Darcy A. Newmark and Sven C. Vogel

J. Imaging 2021, 7(5), 88; https://doi.org/10.3390/jimaging7050088 - 14 May 2021

Cited by 6 | Viewed by 2476

Abstract

With an increased interest in the use of molten salts in both nuclear and non-nuclear systems, measuring important thermophysical properties of specific salt mixtures becomes critical in understanding salt performance and behavior. One of the more basic and significant thermophysical properties of a [...] Read more.

With an increased interest in the use of molten salts in both nuclear and non-nuclear systems, measuring important thermophysical properties of specific salt mixtures becomes critical in understanding salt performance and behavior. One of the more basic and significant thermophysical properties of a given salt system is density as a function of temperature. With this in mind, this work aims to present and layout a novel approach to measuring densities of molten salt systems using neutron radiography. This work was performed on Flight Path 5 at the Los Alamos Neutron Science Center at Los Alamos National Laboratory. In order to benchmark this initial work, three salt mixtures were measured, NaCl, LiCl (58.2 mol%) + KCl (41.8 mol%), and MgCl

_{2}

(32 mol%) + KCl (68 mol%). Resulting densities as a function of temperature for each sample from this work were then compared to previous works employing traditional techniques. Results from this work match well with previous literature values for all salt mixtures measured, establishing that neutron radiography is a viable technique to measure density as a function of temperature in molten salt systems. Finally, advantages of using neutron radiography over other methods are discussed and future work in improving this technique is covered. Full article

► Show Figures

Figure 1

29 pages, 15516 KiB

Open AccessArticle

Simulation-Based Estimation of the Number of Cameras Required for 3D Reconstruction in a Narrow-Baseline Multi-Camera Setup

by Andreas Wachter, Jan Kost and Werner Nahm

J. Imaging 2021, 7(5), 87; https://doi.org/10.3390/jimaging7050087 - 13 May 2021

Cited by 2 | Viewed by 2531

Abstract

Graphical visualization systems are a common clinical tool for displaying digital images and three-dimensional volumetric data. These systems provide a broad spectrum of information to support physicians in their clinical routine. For example, the field of radiology enjoys unrestricted options for interaction with [...] Read more.

Graphical visualization systems are a common clinical tool for displaying digital images and three-dimensional volumetric data. These systems provide a broad spectrum of information to support physicians in their clinical routine. For example, the field of radiology enjoys unrestricted options for interaction with the data, since information is pre-recorded and available entirely in digital form. However, some fields, such as microsurgery, do not benefit from this yet. Microscopes, endoscopes, and laparoscopes show the surgical site as it is. To allow free data manipulation and information fusion, 3D digitization of surgical sites is required. We aimed to find the number of cameras needed to add this functionality to surgical microscopes. For this, we performed in silico simulations of the 3D reconstruction of representative models of microsurgical sites with different numbers of cameras in narrow-baseline setups. Our results show that eight independent camera views are preferable, while at least four are necessary for a digital surgical site. In most cases, eight cameras allow the reconstruction of over 99% of the visible part. With four cameras, still over 95% can be achieved. This answers one of the key questions for the development of a prototype microscope. In future, such a system can provide functionality which is unattainable today. Full article

(This article belongs to the Section Medical Imaging)

► Show Figures

Graphical abstract

14 pages, 1185 KiB

Open AccessArticle

Formalization of the Burning Process of Virtual Reality Objects in Adaptive Training Complexes

by Mikhail Krasnyanskiy, Artem Obukhov and Denis Dedov

J. Imaging 2021, 7(5), 86; https://doi.org/10.3390/jimaging7050086 - 12 May 2021

Cited by 3 | Viewed by 1909

Abstract

Within the scope of this article, the problem of the formalization of physical processes in adaptive training complexes is considered on the example of virtual objects burning. Despite a fairly complete study of this process, the existing mathematical models are not adapted for [...] Read more.

Within the scope of this article, the problem of the formalization of physical processes in adaptive training complexes is considered on the example of virtual objects burning. Despite a fairly complete study of this process, the existing mathematical models are not adapted for the application in training complexes, which leads to a significant increase in costs and lower productivity due to the complexity of the calculations. Therefore, an adapted mathematical model is proposed that allows us to formalize the structure of virtual objects of burning, their basic properties and the processes of changing states, starting from the flame development of an object and ending with their complete destruction or extinguishment. The article proposes the use of threshold value diagrams and rules for changing the states of virtual reality objects to solve the problem of the formalization of burning processes. This tool is quite multi-purpose, which allows you to describe various physical processes, such as smoke, flooding, the spread of toxic gases, etc. The area of the proposed formalization approach includes the design and implementation of physical processes in simulators and multimedia complexes using virtual and augmented reality. Thus, the presented scientific research can be used to formalize the physical processes in adaptive training complexes for professional ergatic systems. Full article

(This article belongs to the Special Issue The Mixed Reality Revolution: Challenges and Prospects)

► Show Figures

Figure 1

24 pages, 41526 KiB

Open AccessArticle

Utilizing a Terrestrial Laser Scanner for 3D Luminance Measurement of Indoor Environments

by Matti Kurkela, Mikko Maksimainen, Arttu Julin, Toni Rantanen, Juho-Pekka Virtanen, Juha Hyyppä, Matti Tapio Vaaja and Hannu Hyyppä

J. Imaging 2021, 7(5), 85; https://doi.org/10.3390/jimaging7050085 - 10 May 2021

Cited by 3 | Viewed by 3232

Abstract

We aim to present a method to measure 3D luminance point clouds by applying the integrated high dynamic range (HDR) panoramic camera system of a terrestrial laser scanning (TLS) instrument for performing luminance measurements simultaneously with laser scanning. We present the luminance calibration [...] Read more.

We aim to present a method to measure 3D luminance point clouds by applying the integrated high dynamic range (HDR) panoramic camera system of a terrestrial laser scanning (TLS) instrument for performing luminance measurements simultaneously with laser scanning. We present the luminance calibration of a laser scanner and assess the accuracy, color measurement properties, and dynamic range of luminance measurement achieved in the laboratory environment. In addition, we demonstrate the 3D luminance measuring process through a case study with a luminance-calibrated laser scanner. The presented method can be utilized directly as the luminance data source. A terrestrial laser scanner can be prepared, characterized, and calibrated to apply it to the simultaneous measurement of both geometry and luminance. We discuss the state and limitations of contemporary TLS technology for luminance measuring. Full article

(This article belongs to the Special Issue High Dynamic Range Imaging)

► Show Figures

Figure 1

15 pages, 3706 KiB

Open AccessArticle

Vegetation Structure Index (VSI): Retrieving Vegetation Structural Information from Multi-Angular Satellite Remote Sensing

by Ram C. Sharma

J. Imaging 2021, 7(5), 84; https://doi.org/10.3390/jimaging7050084 - 9 May 2021

Cited by 5 | Viewed by 2363

Abstract

Utilization of the Bidirectional Reflectance Distribution Function (BRDF) model parameters obtained from the multi-angular remote sensing is one of the approaches for the retrieval of vegetation structural information. In this research, the potential of multi-angular vegetation indices, formulated by the combination of multi-spectral [...] Read more.

Utilization of the Bidirectional Reflectance Distribution Function (BRDF) model parameters obtained from the multi-angular remote sensing is one of the approaches for the retrieval of vegetation structural information. In this research, the potential of multi-angular vegetation indices, formulated by the combination of multi-spectral reflectance from different view angles, for the retrieval of forest above-ground biomass was assessed in the New England region. The multi-angular vegetation indices were generated by the simulation of the Moderate Resolution Imaging Spectroradiometer (MODIS) BRDF/Albedo Model Parameters Product (MCD43A1 Version 6)-based BRDF parameters. The effects of the seasonal (spring, summer, autumn, and winter) composites of the multi-angular vegetation indices on the above-ground biomass, the angular relationship of the spectral reflectance with above-ground biomass, and the interrelationships between the multi-angular vegetation indices were analyzed. Among the existing multi-angular vegetation indices, only the Nadir BRDF-adjusted NDVI and Hot-spot incorporated NDVI showed significant relationship (more than 50%) with the above-ground biomass. The Vegetation Structure Index (VSI), newly proposed in the research, performed in the most efficient way and explained 64% variation of the above-ground biomass, suggesting that the right choice of the spectral channel and observation geometry should be considered for improving the estimates of the above-ground biomass. In addition, the right choice of seasonal data (summer) was found to be important for estimating the forest biomass, while other seasonal data were either insensitive or pointless. The promising results shown by the VSI suggest that it could be an appropriate candidate for monitoring vegetation structure from the multi-angular satellite remote sensing. Full article

► Show Figures

Figure 1

14 pages, 1698 KiB

Open AccessArticle

Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data

by Mahmoud Elbattah, Colm Loughnane, Jean-Luc Guérin, Romuald Carette, Federica Cilia and Gilles Dequen

J. Imaging 2021, 7(5), 83; https://doi.org/10.3390/jimaging7050083 - 3 May 2021

Cited by 42 | Viewed by 6744

Abstract

Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or [...] Read more.

Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or lack of data-sharing incentives. Such challenges have attached significance to the application of generative modeling and data augmentation in that domain. In this context, this study explores a machine learning-based approach for generating synthetic eye-tracking data. We explore a novel application of variational autoencoders (VAEs) in this regard. More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths. Overall, our results validate that the VAE model could generate a plausible output from a limited dataset. Finally, it is empirically demonstrated that such approach could be employed as a mechanism for data augmentation to improve the performance in classification tasks. Full article

► Show Figures

Figure 1

17 pages, 5020 KiB

Open AccessArticle

Optical Imaging of Magnetic Particle Cluster Oscillation and Rotation in Glycerol

by River Gassen, Dennis Thompkins, Austin Routt, Philippe Jones, Meghan Smith, William Thompson, Paul Couture, Dmytro A. Bozhko, Zbigniew Celinski, Robert E. Camley, Guy M. Hagen and Kathrin Spendier

J. Imaging 2021, 7(5), 82; https://doi.org/10.3390/jimaging7050082 - 29 Apr 2021

Cited by 2 | Viewed by 2487

Abstract

Magnetic particles have been evaluated for their biomedical applications as a drug delivery system to treat asthma and other lung diseases. In this study, ferromagnetic barium hexaferrite (BaFe

_{12}

O

_{19}

) and iron oxide (Fe

_{3}

O

_{4}

) particles were suspended [...] Read more.

Magnetic particles have been evaluated for their biomedical applications as a drug delivery system to treat asthma and other lung diseases. In this study, ferromagnetic barium hexaferrite (BaFe

_{12}

O

_{19}

) and iron oxide (Fe

_{3}

O

_{4}

) particles were suspended in water or glycerol, as glycerol can be 1000 times more viscous than water. The particle concentration was 2.50 mg/mL for BaFe

_{12}

O

_{19}

particle clusters and 1.00 mg/mL for Fe

_{3}

O

_{4}

particle clusters. The magnetic particle cluster cross-sectional area ranged from 15 to 1000 μ

μ

m

^{2}

, and the particle cluster diameter ranged from 5 to 45 μ

μ

m. The magnetic particle clusters were exposed to oscillating or rotating magnetic fields and imaged with an optical microscope. The oscillation frequency of the applied magnetic fields, which was created by homemade wire spools inserted into an optical microscope, ranged from 10 to 180 Hz. The magnetic field magnitudes varied from 0.25 to 9 mT. The minimum magnetic field required for particle cluster rotation or oscillation in glycerol was experimentally measured at different frequencies. The results are in qualitative agreement with a simplified model for single-domain magnetic particles, with an average deviation from the model of 1.7 ± 1.3. The observed difference may be accounted for by the fact that our simplified model does not include effects on particle cluster motion caused by randomly oriented domains in multi-domain magnetic particle clusters, irregular particle cluster size, or magnetic anisotropy, among other effects. Full article

(This article belongs to the Special Issue Current Highlights and Future Applications of Computational Imaging)

► Show Figures

Figure 1

14 pages, 5483 KiB

Open AccessArticle

CORONA-Net: Diagnosing COVID-19 from X-ray Images Using Re-Initialization and Classification Networks

by Sherif Elbishlawi, Mohamed H. Abdelpakey, Mohamed S. Shehata and Mostafa M. Mohamed

J. Imaging 2021, 7(5), 81; https://doi.org/10.3390/jimaging7050081 - 28 Apr 2021

Cited by 10 | Viewed by 4291

Abstract

The COVID-19 pandemic has been deemed a global health pandemic. The early detection of COVID-19 is key to combating its outbreak and could help bring this pandemic to an end. One of the biggest challenges in combating COVID-19 is accurate testing for the [...] Read more.

The COVID-19 pandemic has been deemed a global health pandemic. The early detection of COVID-19 is key to combating its outbreak and could help bring this pandemic to an end. One of the biggest challenges in combating COVID-19 is accurate testing for the disease. Utilizing the power of Convolutional Neural Networks (CNNs) to detect COVID-19 from chest X-ray images can help radiologists compare and validate their results with an automated system. In this paper, we propose a carefully designed network, dubbed CORONA-Net, that can accurately detect COVID-19 from chest X-ray images. CORONA-Net is divided into two phases: (1) The reinitialization phase and (2) the classification phase. In the reinitialization phase, the network consists of encoder and decoder networks. The objective of this phase is to train and initialize the encoder and decoder networks by a distribution that comes out of medical images. In the classification phase, the decoder network is removed from CORONA-Net, and the encoder network acts as a backbone network to fine-tune the classification phase based on the learned weights from the reinitialization phase. Extensive experiments were performed on a publicly available dataset, COVIDx, and the results show that CORONA-Net significantly outperforms the current state-of-the-art networks with an overall accuracy of 95.84%. Full article

(This article belongs to the Special Issue X-ray Digital Radiography and Computed Tomography)

► Show Figures

Figure 1

18 pages, 3952 KiB

Open AccessArticle

From IR Images to Point Clouds to Pose: Point Cloud-Based AR Glasses Pose Estimation

by Ahmet Firintepe, Carolin Vey, Stylianos Asteriadis, Alain Pagani and Didier Stricker

J. Imaging 2021, 7(5), 80; https://doi.org/10.3390/jimaging7050080 - 27 Apr 2021

Cited by 5 | Viewed by 3227

Abstract

In this paper, we propose two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation. Our first approach “PointsToRotation” is based on a Deep Neural Network alone, whereas our second approach “PointsToPose” is [...] Read more.

In this paper, we propose two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation. Our first approach “PointsToRotation” is based on a Deep Neural Network alone, whereas our second approach “PointsToPose” is a hybrid model combining Deep Learning and a voting-based mechanism. Our methods utilize a point cloud estimator, which we trained on multi-view infrared images in a semi-supervised manner, generating point clouds based on one image only. We generate a point cloud dataset with our point cloud estimator using the HMDPose dataset, consisting of multi-view infrared images of various AR glasses with the corresponding 6-DoF poses. In comparison to another point cloud-based 6-DoF pose estimation named CloudPose, we achieve an error reduction of around 50%. Compared to a state-of-the-art image-based method, we reduce the pose estimation error by around 96%. Full article

(This article belongs to the Special Issue Advanced Scene Perception for Augmented Reality)

► Show Figures

Figure 1

10 pages, 2669 KiB

Open AccessArticle

Determination of the Round Window Niche Anatomy Using Cone Beam Computed Tomography Imaging as Preparatory Work for Individualized Drug-Releasing Implants

by Farnaz Matin, Ziwen Gao, Felix Repp, Samuel John, Thomas Lenarz and Verena Scheper

J. Imaging 2021, 7(5), 79; https://doi.org/10.3390/jimaging7050079 - 26 Apr 2021

Cited by 9 | Viewed by 7404

Abstract

Modern therapy of inner ear disorders is increasingly shifting to local drug delivery using a growing number of pharmaceuticals. Access to the inner ear is usually made via the round window membrane (RWM), located in the bony round window niche (RWN). We hypothesize [...] Read more.

Modern therapy of inner ear disorders is increasingly shifting to local drug delivery using a growing number of pharmaceuticals. Access to the inner ear is usually made via the round window membrane (RWM), located in the bony round window niche (RWN). We hypothesize that the individual shape and size of the RWN have to be taken into account for safe reliable and controlled drug delivery. Therefore, we investigated the anatomy and its variations. Cone beam computed tomography (CBCT) images of 50 patients were analyzed. Based on the reconstructed 3D volumes, individual anatomies of the RWN, RWM, and bony overhang were determined by segmentation using 3D Slicer^TM with a custom build plug-in. A large individual anatomical variability of the RWN with a mean volume of 4.54 mm³ (min 2.28 mm³, max 6.64 mm³) was measured. The area of the RWM ranged from 1.30 to 4.39 mm² (mean: 2.93 mm²). The bony overhang had a mean length of 0.56 mm (min 0.04 mm, max 1.24 mm) and the shape was individually very different. Our data suggest that there is a potential for individually designed and additively manufactured RWN implants due to large differences in the volume and shape of the RWN. Full article

(This article belongs to the Special Issue The Application of Imaging Technology in Medical Intervention and Surgery)

► Show Figures

Figure 1

15 pages, 3676 KiB

Open AccessArticle

Structural Beauty: A Structure-Based Computational Approach to Quantifying the Beauty of an Image

by Bin Jiang and Chris de Rijke

J. Imaging 2021, 7(5), 78; https://doi.org/10.3390/jimaging7050078 - 23 Apr 2021

Cited by 11 | Viewed by 4805

Abstract

To say that beauty is in the eye of the beholder means that beauty is largely subjective so varies from person to person. While the subjectivity view is commonly held, there is also an objectivity view that seeks to measure beauty or aesthetics [...] Read more.

To say that beauty is in the eye of the beholder means that beauty is largely subjective so varies from person to person. While the subjectivity view is commonly held, there is also an objectivity view that seeks to measure beauty or aesthetics in some quantitative manners. Christopher Alexander has long discovered that beauty or coherence highly correlates to the number of subsymmetries or substructures and demonstrated that there is a shared notion of beauty—structural beauty—among people and even different peoples, regardless of their faiths, cultures, and ethnicities. This notion of structural beauty arises directly out of living structure or wholeness, a physical and mathematical structure that underlies all space and matter. Based on the concept of living structure, this paper develops an approach for computing the structural beauty or life of an image (L) based on the number of automatically derived substructures (S) and their inherent hierarchy (H). To verify this approach, we conducted a series of case studies applied to eight pairs of images including Leonardo da Vinci’s Mona Lisa and Jackson Pollock’s Blue Poles. We discovered among others that Blue Poles is more structurally beautiful than the Mona Lisa, and traditional buildings are in general more structurally beautiful than their modernist counterparts. This finding implies that goodness of things or images is largely a matter of fact rather than an opinion or personal preference as conventionally conceived. The research on structural beauty has deep implications on many disciplines, where beauty or aesthetics is a major concern such as image understanding and computer vision, architecture and urban design, humanities and arts, neurophysiology, and psychology. Full article

► Show Figures

Figure 1

10 pages, 32497 KiB

Open AccessCommunication

UnCanny: Exploiting Reversed Edge Detection as a Basis for Object Tracking in Video

by Wesley T. Honeycutt and Eli S. Bridge

J. Imaging 2021, 7(5), 77; https://doi.org/10.3390/jimaging7050077 - 23 Apr 2021

Cited by 2 | Viewed by 2739

Abstract

Few object detection methods exist which can resolve small objects (<20 pixels) from complex static backgrounds without significant computational expense. A framework capable of meeting these needs which reverses the steps in classic edge detection methods using the Canny filter for edge detection [...] Read more.

Few object detection methods exist which can resolve small objects (<20 pixels) from complex static backgrounds without significant computational expense. A framework capable of meeting these needs which reverses the steps in classic edge detection methods using the Canny filter for edge detection is presented here. Sample images taken from sequential frames of video footage were processed by subtraction, thresholding, Sobel edge detection, Gaussian blurring, and Zhang–Suen edge thinning to identify objects which have moved between the two frames. The results of this method show distinct contours applicable to object tracking algorithms with minimal “false positive” noise. This framework may be used with other edge detection methods to produce robust, low-overhead object tracking methods. Full article

(This article belongs to the Special Issue Edge Detection Evaluation)

► Show Figures

Graphical abstract

25 pages, 2722 KiB

Open AccessArticle

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval

by Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Franca Debole, Fabrizio Falchi, Claudio Gennaro, Lucia Vadicamo and Claudio Vairo

J. Imaging 2021, 7(5), 76; https://doi.org/10.3390/jimaging7050076 - 23 Apr 2021

Cited by 15 | Viewed by 3095

Abstract

This paper describes in detail VISIONE, a video search system that allows users to search for videos using textual keywords, the occurrence of objects and their spatial relationships, the occurrence of colors and their spatial relationships, and image similarity. These modalities can be [...] Read more.

This paper describes in detail VISIONE, a video search system that allows users to search for videos using textual keywords, the occurrence of objects and their spatial relationships, the occurrence of colors and their spatial relationships, and image similarity. These modalities can be combined together to express complex queries and meet users’ needs. The peculiarity of our approach is that we encode all information extracted from the keyframes, such as visual deep features, tags, color and object locations, using a convenient textual encoding that is indexed in a single text retrieval engine. This offers great flexibility when results corresponding to various parts of the query (visual, text and locations) need to be merged. In addition, we report an extensive analysis of the retrieval performance of the system, using the query logs generated during the Video Browser Showdown (VBS) 2019 competition. This allowed us to fine-tune the system by choosing the optimal parameters and strategies from those we tested. Full article

(This article belongs to the Special Issue 2020 Selected Papers from Journal of Imaging Editorial Board Members)

► Show Figures

Figure 1

17 pages, 1056 KiB

Open AccessReview

An Update of the Possible Applications of Magnetic Resonance Imaging (MRI) in Dentistry: A Literature Review

by Rodolfo Reda, Alessio Zanza, Alessandro Mazzoni, Andrea Cicconetti, Luca Testarelli and Dario Di Nardo

J. Imaging 2021, 7(5), 75; https://doi.org/10.3390/jimaging7050075 - 21 Apr 2021

Cited by 75 | Viewed by 9064

Abstract

This narrative review aims to evaluate the current evidence for the application of magnetic resonance imaging (MRI), a radiation-free diagnostic exam, in some fields of dentistry. Background: Radiographic imaging plays a significant role in current first and second level dental diagnostics and treatment [...] Read more.

This narrative review aims to evaluate the current evidence for the application of magnetic resonance imaging (MRI), a radiation-free diagnostic exam, in some fields of dentistry. Background: Radiographic imaging plays a significant role in current first and second level dental diagnostics and treatment planning. However, the main disadvantage is the high exposure to ionizing radiation for patients. Methods: A search for articles on dental MRI was performed using the PubMed electronic database, and 37 studies were included. Only some articles about endodontics, conservative dentistry, implantology, and oral and craniofacial surgery that best represented the aim of this study were selected. Results: All the included articles showed that MRI can obtain well-defined images, which can be applied in operative dentistry. Conclusions: This review highlights the potential of MRI for diagnosis in dental clinical practice, without the risk of biological damage from continuous ionizing radiation exposure. Full article

(This article belongs to the Special Issue New Frontiers of Advanced Imaging in Dentistry)

► Show Figures

Figure 1

Journal Menu

Journal Browser

J. Imaging, Volume 7, Issue 5 (May 2021) – 17 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI