Processing math: 100%
 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (12)

Search Parameters:
Keywords = progressive resizing

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
14 pages, 283 KiB  
Article
Clinical Applicability and Cross-Dataset Validation of Machine Learning Models for Binary Glaucoma Detection
by David Remyes, Daniel Nasef, Sarah Remyes, Joseph Tawfellos, Michael Sher, Demarcus Nasef and Milan Toma
Information 2025, 16(6), 432; https://doi.org/10.3390/info16060432 - 24 May 2025
Viewed by 86
Abstract
Glaucoma is a progressive optic nerve disease and a leading cause of irreversible blindness worldwide. Early and accurate detection is critical to prevent vision loss, yet traditional diagnostic methods such as optical coherence tomography and visual field tests face challenges in accessibility, cost, [...] Read more.
Glaucoma is a progressive optic nerve disease and a leading cause of irreversible blindness worldwide. Early and accurate detection is critical to prevent vision loss, yet traditional diagnostic methods such as optical coherence tomography and visual field tests face challenges in accessibility, cost, and consistency, especially in under-resourced areas. This study evaluates the clinical applicability and robustness of three machine learning models for automated glaucoma detection: a convolutional neural network, a deep neural network, and an automated ensemble approach. The models were trained and validated on retinal fundus images and tested on an independent dataset to assess their ability to generalize across different patient populations. Data preprocessing included resizing, normalization, and feature extraction to ensure consistency. Among the models, the deep neural network demonstrated the highest generalizability with stable performance across datasets, while the convolutional neural network showed moderate but consistent results. The ensemble model exhibited overfitting, which limited its practical use. These findings highlight the importance of proper evaluation frameworks, including external validation, to ensure the reliability of artificial intelligence tools for clinical use. The study provides insights into the development of scalable, effective diagnostic solutions that align with regulatory guidelines, addressing the critical need for accessible glaucoma detection tools in diverse healthcare settings. Full article
(This article belongs to the Special Issue Machine Learning and Artificial Intelligence with Applications)
Show Figures

Graphical abstract

16 pages, 1787 KiB  
Article
A Method for Calculating Small Sizes of Volumes in Postsurgical Thyroid SPECT/CT Imaging
by Elena Ttofi, Costas Kyriacou, Theodoros Leontiou and Yiannis Parpottas
Life 2025, 15(2), 200; https://doi.org/10.3390/life15020200 - 29 Jan 2025
Viewed by 875
Abstract
Differentiated thyroid cancer treatment typically involves the surgical removal of the whole or largest part of the thyroid gland. Diagnostic procedures are useful both before and after treatment to determine the need for radioiodine ablation, re-stage the disease, monitor disease progression, or evaluate [...] Read more.
Differentiated thyroid cancer treatment typically involves the surgical removal of the whole or largest part of the thyroid gland. Diagnostic procedures are useful both before and after treatment to determine the need for radioiodine ablation, re-stage the disease, monitor disease progression, or evaluate treatment efficacy. SPECT/CT imaging can be utilized to identify small, distant iodine-avid metastatic lesions and assess their uptake and volume for the above purposes as well as for performing lesion-based dosimetry when indicated. The objective of this study was to develop and validate a method for calculating small sizes of volumes in SPECT/CT imaging as well as to perform calculations utilizing I-131 and I-123 postsurgical SPECT/CT images from a neck–thyroid phantom. In this approach, the calculated volume was unaffected by radiation spillover from high-uptake voxels since it was the result from the successive application of the gray-level histogram technique to SPECT and CT 3D matrices. Beforehand, the SPECT 3D matrix was resized and aligned to the corresponding CT one. The method was validated following the clinical protocols for postsurgical thyroid imaging by using I-123 and I-131 scatter and attenuation-corrected SPECT/CT images from a neck–thyroid phantom. The phantom could accommodate two volumes of different sizes (0.5, 1, 1.5, 3, and 10 mL) and enclose anatomical tissue-equivalent main scattering structures. For the 0.5 and 10 mL volumes, the % differences between the actual and the calculated volumes were 15.2% and 1.2%, respectively. Radiation spillover was only present in SPECT images, and it was more profound at higher administered activities, in I-131 than in I-123 images, and in smaller volumes. When SPECT/low-dose-CT imaging is performed, this method is capable of accurately calculating small volumes without the need of additional modalities. Full article
(This article belongs to the Special Issue Current Progress in Medical Image Segmentation)
Show Figures

Figure 1

37 pages, 3803 KiB  
Article
Sustainable Mobility: Machine Learning-Driven Deployment of EV Charging Points in Dublin
by Alexander Mutiso Mutua and Ruairí de Fréin
Sustainability 2024, 16(22), 9950; https://doi.org/10.3390/su16229950 - 14 Nov 2024
Cited by 1 | Viewed by 1494
Abstract
Electric vehicle (EV) drivers in urban areas face range anxiety due to the fear of running out of charge without timely access to charging points (CPs). The lack of sufficient numbers of CPs has hindered EV adoption and negatively impacted the progress of [...] Read more.
Electric vehicle (EV) drivers in urban areas face range anxiety due to the fear of running out of charge without timely access to charging points (CPs). The lack of sufficient numbers of CPs has hindered EV adoption and negatively impacted the progress of sustainable mobility. We propose a CP distribution algorithm that is machine learning-based and leverages population density, points of interest (POIs), and the most used roads as input parameters to determine the best locations for deploying CPs. The objects of the following research are as follows: (1) to allocate weights to the three parameters in a 6 km by 10 km grid size scenario in Dublin in Ireland so that the best CP distribution is obtained; (2) to use a feedforward neural network (FNNs) model to predict the best parameter weight combinations and the corresponding CPs. CP deployment solutions are classified as successful when an EV is located within 100 m of a CP at the end of a trip. We find that (1) integrating the GEECharge and EV Portacharge algorithms with FNNs optimises the distribution of CPs; (2) the normalised optimal weights for the population density, POIs, and most used road parameters determined by this approach result in approximately 109 CPs being allocated in Dublin; (3) resizing the grid from 6 km by 10 km to 10 km by 6 km and rotating it at an angle of 350 results in a 5.7% rise in the overall number of CPs in Dublin; (4) reducing the grid cell size from 1 km2 to 500 m2 reduces the mean distance between CPs and the EVs. This research is vital to city planners as we show that city planners can use readily available data to generate these parameters for urban planning decisions that result in EV CP networks, which have increased efficiency. This will promote EV usage in urban transportation, leading to greater sustainability. Full article
Show Figures

Figure 1

28 pages, 4011 KiB  
Article
Advanced Deep Learning Fusion Model for Early Multi-Classification of Lung and Colon Cancer Using Histopathological Images
by A. A. Abd El-Aziz, Mahmood A. Mahmood and Sameh Abd El-Ghany
Diagnostics 2024, 14(20), 2274; https://doi.org/10.3390/diagnostics14202274 - 12 Oct 2024
Cited by 2 | Viewed by 2431
Abstract
Background: In recent years, the healthcare field has experienced significant advancements. New diagnostic techniques, treatments, and insights into the causes of various diseases have emerged. Despite these progressions, cancer remains a major concern. It is a widespread illness affecting individuals of all ages [...] Read more.
Background: In recent years, the healthcare field has experienced significant advancements. New diagnostic techniques, treatments, and insights into the causes of various diseases have emerged. Despite these progressions, cancer remains a major concern. It is a widespread illness affecting individuals of all ages and leads to one out of every six deaths. Lung and colon cancer alone account for nearly two million fatalities. Though it is rare for lung and colon cancers to co-occur, the spread of cancer cells between these two areas—known as metastasis—is notably high. Early detection of cancer greatly increases survival rates. Currently, histopathological image (HI) diagnosis and appropriate treatment are key methods for reducing cancer mortality and enhancing survival rates. Digital image processing (DIP) and deep learning (DL) algorithms can be employed to analyze the HIs of five different types of lung and colon tissues. Methods: Therefore, this paper proposes a refined DL model that integrates feature fusion for the multi-classification of lung and colon cancers. The proposed model incorporates three DL architectures: ResNet-101V2, NASNetMobile, and EfficientNet-B0. Each model has limitations concerning variations in the shape and texture of input images. To address this, the proposed model utilizes a concatenate layer to merge the pre-trained individual feature vectors from ResNet-101V2, NASNetMobile, and EfficientNet-B0 into a single feature vector, which is then fine-tuned. As a result, the proposed DL model achieves high success in multi-classification by leveraging the strengths of all three models to enhance overall accuracy. This model aims to assist pathologists in the early detection of lung and colon cancer with reduced effort, time, and cost. The proposed DL model was evaluated using the LC25000 dataset, which contains colon and lung HIs. The dataset was pre-processed using resizing and normalization techniques. Results: The model was tested and compared with recent DL models, achieving impressive results: 99.8% for precision, 99.8% for recall, 99.8% for F1-score, 99.96% for specificity, and 99.94% for accuracy. Conclusions: Thus, the proposed DL model demonstrates exceptional performance across all classification categories. Full article
(This article belongs to the Special Issue Machine-Learning-Based Disease Diagnosis and Prediction)
Show Figures

Figure 1

20 pages, 1102 KiB  
Article
Training Artificial Neural Networks to Detect Multiple Sclerosis Lesions Using Granulometric Data from Preprocessed Magnetic Resonance Images with Morphological Transformations
by Edgar Rafael Ponce de Leon-Sanchez, Jorge Domingo Mendiola-Santibañez, Omar Arturo Dominguez-Ramirez, Ana Marcela Herrera-Navarro, Alberto Vazquez-Cervantes, Hugo Jimenez-Hernandez, Diana Margarita Cordova-Esparza, María de los Angeles Cuán Hernández and Horacio Senties-Madrid
Technologies 2024, 12(9), 145; https://doi.org/10.3390/technologies12090145 - 31 Aug 2024
Viewed by 2856
Abstract
The symptoms of multiple sclerosis (MS) are determined by the location of demyelinating lesions in the white matter of the brain and spinal cord. Currently, magnetic resonance imaging (MRI) is the most common tool used for diagnosing MS, understanding the course of the [...] Read more.
The symptoms of multiple sclerosis (MS) are determined by the location of demyelinating lesions in the white matter of the brain and spinal cord. Currently, magnetic resonance imaging (MRI) is the most common tool used for diagnosing MS, understanding the course of the disease, and analyzing the effects of treatments. However, undesirable components may appear during the generation of MRI scans, such as noise or intensity variations. Mathematical morphology (MM) is a powerful image analysis technique that helps to filter the image and extract relevant structures. Granulometry is an image measurement tool for measuring MM that determines the size distribution of objects in an image without explicitly segmenting each object. While several methods have been proposed for the automatic segmentation of MS lesions in MRI scans, in some cases, only simple data preprocessing, such as image resizing to standardize the input dimensions, has been performed before the algorithm training. Therefore, this paper proposes an MRI preprocessing algorithm capable of performing elementary morphological transformations in brain images of MS patients and healthy individuals in order to delete undesirable components and extract the relevant structures such as MS lesions. Also, the algorithm computes the granulometry in MRI scans to describe the size qualities of lesions. Using this algorithm, we trained two artificial neural networks (ANNs) to predict MS diagnoses. By computing the differences in granulometry measurements between an image with MS lesions and a reference image (without lesions), we determined the size characterization of the lesions. Then, the ANNs were evaluated with the validation set, and the performance results (test accuracy = 0.9753; cross-entropy loss = 0.0247) show that the proposed algorithm can support specialists in making decisions to diagnose MS and estimating the disease progress based on granulometry values. Full article
(This article belongs to the Special Issue Medical Imaging & Image Processing III)
Show Figures

Figure 1

25 pages, 20130 KiB  
Article
Improved YOLOv5 Based on Multi-Strategy Integration for Multi-Category Wind Turbine Surface Defect Detection
by Mingwei Lei, Xingfen Wang, Meihua Wang and Yitao Cheng
Energies 2024, 17(8), 1796; https://doi.org/10.3390/en17081796 - 9 Apr 2024
Cited by 3 | Viewed by 1606
Abstract
Wind energy is a renewable resource with abundant reserves, and its sustainable development and utilization are crucial. The components of wind turbines, particularly the blades and various surfaces, require meticulous defect detection and maintenance due to their significance. The operational status of wind [...] Read more.
Wind energy is a renewable resource with abundant reserves, and its sustainable development and utilization are crucial. The components of wind turbines, particularly the blades and various surfaces, require meticulous defect detection and maintenance due to their significance. The operational status of wind turbine generators directly impacts the efficiency and safe operation of wind farms. Traditional surface defect detection methods for wind turbines often involve manual operations, which suffer from issues such as high subjectivity, elevated risks, low accuracy, and inefficiency. The emergence of computer vision technologies based on deep learning has provided a novel approach to surface defect detection in wind turbines. However, existing datasets designed for wind turbine surface defects exhibit overall category scarcity and an imbalance in samples between categories. The algorithms designed face challenges, with low detection rates for small samples. Hence, this study first constructs a benchmark dataset for wind turbine surface defects comprising seven categories that encompass all common surface defects. Simultaneously, a wind turbine surface defect detection algorithm based on improved YOLOv5 is designed. Initially, a multi-scale copy-paste data augmentation method is proposed, introducing scale factors to randomly resize the bounding boxes before copy-pasting. This alleviates sample imbalances and significantly enhances the algorithm’s detection capabilities for targets of different sizes. Subsequently, a dynamic label assignment strategy based on the Hungarian algorithm is introduced that calculates the matching costs by weighing different losses, enhancing the network’s ability to learn positive and negative samples. To address overfitting and misrecognition resulting from strong data augmentation, a two-stage progressive training method is proposed, aiding the model’s natural convergence and improving generalization performance. Furthermore, a multi-scenario negative-sample-guided learning method is introduced that involves incorporating unlabeled background images from various scenarios into training, guiding the model to learn negative samples and reducing misrecognition. Finally, slicing-aided hyper inference is introduced, facilitating large-scale inference for wind turbine surface defects in actual industrial scenarios. The improved algorithm demonstrates a 3.1% increase in the mean average precision (mAP) on the custom dataset, achieving 95.7% accuracy in mAP_50 (the IoU threshold is half of the mAP). Notably, the mAPs for small, medium, and large targets increase by 18.6%, 16.4%, and 6.8%, respectively. The experimental results indicate that the enhanced algorithm exhibits high detection accuracy, providing a new and more efficient solution for the field of wind turbine surface defect detection. Full article
(This article belongs to the Section A3: Wind, Wave and Tidal Energy)
Show Figures

Figure 1

14 pages, 6718 KiB  
Article
Classification and Detection of Rice Diseases Using a 3-Stage CNN Architecture with Transfer Learning Approach
by Munmi Gogoi, Vikash Kumar, Shahin Ara Begum, Neelesh Sharma and Surya Kant
Agriculture 2023, 13(8), 1505; https://doi.org/10.3390/agriculture13081505 - 27 Jul 2023
Cited by 16 | Viewed by 6851
Abstract
Rice is a vital crop for global food security, but its production is vulnerable to various diseases. Early detection and treatment of rice diseases are crucial to minimise yield losses. Convolutional neural networks (CNNs) have shown great potential for disease detection in plant [...] Read more.
Rice is a vital crop for global food security, but its production is vulnerable to various diseases. Early detection and treatment of rice diseases are crucial to minimise yield losses. Convolutional neural networks (CNNs) have shown great potential for disease detection in plant leaves, but training CNNs requires large datasets of labelled images, which can be expensive and time-consuming. Here, we have experimented a 3-Stage CNN architecture with a transfer learning approach that utilises a pre-trained CNN model fine-tuned on a small dataset of rice disease images. The proposed approach significantly reduces the required training data while achieving high accuracy. We also incorporated deep learning techniques such as progressive re-sizing and parametric rectified linear unit (PReLU) to enhance rice disease detection. Progressive re-sizing improves feature learning by gradually increasing image size during training, while PReLU reduces overfitting and enhances model performance. The proposed approach was evaluated on a dataset of 8883 and 1200 images of disease and healthy rice leaves, respectively, achieving an accuracy of 94% when subjected to the 10-fold cross-validation process, significantly higher than other methods. These simulation results for disease detection in rice prove the feasibility and efficiency and offer a cost-effective, accessible solution for the early detection of rice diseases, particularly useful in developing countries with limited resources that can significantly contribute toward sustainable food production. Full article
(This article belongs to the Section Agricultural Technology)
Show Figures

Figure 1

14 pages, 2942 KiB  
Article
Hair Follicle Classification and Hair Loss Severity Estimation Using Mask R-CNN
by Jong-Hwan Kim, Segi Kwon, Jirui Fu and Joon-Hyuk Park
J. Imaging 2022, 8(10), 283; https://doi.org/10.3390/jimaging8100283 - 14 Oct 2022
Cited by 19 | Viewed by 9741
Abstract
Early and accurate detection of scalp hair loss is imperative to provide timely and effective treatment plans to halt further progression and save medical costs. Many techniques have been developed leveraging deep learning to automate the hair loss detection process. However, the accuracy [...] Read more.
Early and accurate detection of scalp hair loss is imperative to provide timely and effective treatment plans to halt further progression and save medical costs. Many techniques have been developed leveraging deep learning to automate the hair loss detection process. However, the accuracy and robustness of assessing hair loss severity still remain a challenge and barrier for transitioning such a technique into practice. The presented work proposes an efficient and accurate algorithm to classify hair follicles and estimate hair loss severity, which was implemented and validated using a multitask deep learning method via a Mask R-CNN framework. A microscopic image of the scalp was resized, augmented, then processed through pre-trained ResNet models for feature extraction. The key features considered in this study concerning hair loss severity include the number of hair follicles, the thickness of the hair, and the number of hairs in each hair follicle. Based on these key features, labeling of hair follicles (healthy, normal, and severe) were performed on the images collected from 10 men in varying stages of hair loss. More specifically, Mask R-CNN was applied for instance segmentation of the hair follicle region and to classify the hair follicle state into three categories, following the labeling convention (healthy, normal and severe). Based on the state of each hair follicle captured from a single image, an estimation of hair loss severity was determined for that particular region of the scalp, namely local hair loss severity index (P), and by combining P of multiple images taken and processed from different parts of the scalp, we constructed the hair loss severity estimation (Pavg) and visualized in a heatmap to illustrate the overall hair loss type and condition. The proposed hair follicle classification and hair loss severity estimation using Mask R-CNN demonstrated a more efficient and accurate algorithm compared to other methods previously used, enhancing the classification accuracy by 4 to 15%. This performance supports its potential for use in clinical settings to enhance the accuracy and efficiency of current hair loss diagnosis and prognosis techniques. Full article
(This article belongs to the Section AI in Imaging)
Show Figures

Figure 1

14 pages, 3831 KiB  
Article
Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs
by Gurpreet Singh, Darpan Anand, Woong Cho, Gyanendra Prasad Joshi and Kwang Chul Son
Biology 2022, 11(5), 665; https://doi.org/10.3390/biology11050665 - 26 Apr 2022
Cited by 9 | Viewed by 3596
Abstract
The practice of Deep Convolution neural networks in the field of medicine has congregated immense success and significance in present situations. Previously, researchers have developed numerous models for detecting abnormalities in musculoskeletal radiographs of upper extremities, but did not succeed in achieving respectable [...] Read more.
The practice of Deep Convolution neural networks in the field of medicine has congregated immense success and significance in present situations. Previously, researchers have developed numerous models for detecting abnormalities in musculoskeletal radiographs of upper extremities, but did not succeed in achieving respectable accuracy in the case of finger radiographs. A novel deep neural network-based hybrid architecture named ComDNet-512 is proposed in this paper to efficiently detect the bone abnormalities in the musculoskeletal radiograph of a patient. ComDNet-512 comprises a three-phase pipeline structure: compression, training of the dense neural network, and progressive resizing. The ComDNet-512 hybrid model is trained with finger radiographs samples to make a binary prediction, i.e., normal or abnormal bones. The proposed model showed phenomenon outcomes when cross-validated on the testing samples of arthritis patients and gives many superior results when compared with state-of-the-art practices. The model is able to achieve an area under the ROC curve (AUC) equal to 0.894 (sensitivity = 0.941 and specificity = 0.847). The Precision, Recall, F1 Score, and Kappa values, recorded as 0.86, 0.94, 0.89, and 0.78, respectively, are better than any of the previous models’. With an increasing appearance of enormous cases of musculoskeletal conditions in people, deep learning-based computational solutions can play a big role in performing automated detections in the future. Full article
(This article belongs to the Special Issue Advanced Computational Models for Clinical Decision Support)
Show Figures

Figure 1

15 pages, 1042 KiB  
Review
Apalutamide, Darolutamide and Enzalutamide for Nonmetastatic Castration-Resistant Prostate Cancer (nmCRPC): A Critical Review
by Carlo Cattrini, Orazio Caffo, Ugo De Giorgi, Alessia Mennitto, Alessandra Gennari, David Olmos and Elena Castro
Cancers 2022, 14(7), 1792; https://doi.org/10.3390/cancers14071792 - 31 Mar 2022
Cited by 26 | Viewed by 8332
Abstract
Nonmetastatic castration-resistant prostate cancer (nmCRPC) represents a condition in which patients with prostate cancer show biochemical progression during treatment with androgen-deprivation therapy (ADT) without signs of radiographic progression according to conventional imaging. The SPARTAN, ARAMIS and PROSPER trials showed that apalutamide, darolutamide and [...] Read more.
Nonmetastatic castration-resistant prostate cancer (nmCRPC) represents a condition in which patients with prostate cancer show biochemical progression during treatment with androgen-deprivation therapy (ADT) without signs of radiographic progression according to conventional imaging. The SPARTAN, ARAMIS and PROSPER trials showed that apalutamide, darolutamide and enzalutamide, respectively, prolong metastasis-free survival (MFS) and overall survival (OS) of nmCRPC patients with a short PSA doubling time, and these antiandrogens have been recently introduced in clinical practice as a new standard of care. No direct comparison of these three agents has been conducted to support treatment choice. In addition, a significant proportion of nmCRPC on conventional imaging is classified as metastatic with new imaging modalities such as the prostate-specific membrane antigen positron emission tomography (PSMA-PET). Some experts posit that these “new metastatic” patients should be treated as mCRPC, resizing the impact of nmCRPC trials, whereas other authors suggest that they should be treated as nmCRPC patients, based on the design of pivotal trials. This review discusses the most convincing evidence regarding the use of novel antiandrogens in patients with nmCRPC and the implications of novel imaging techniques for treatment selection. Full article
Show Figures

Figure 1

26 pages, 2647 KiB  
Article
A Unified Framework of Deep Learning-Based Facial Expression Recognition System for Diversified Applications
by Sanoar Hossain, Saiyed Umer, Vijayan Asari and Ranjeet Kumar Rout
Appl. Sci. 2021, 11(19), 9174; https://doi.org/10.3390/app11199174 - 2 Oct 2021
Cited by 29 | Viewed by 4542
Abstract
This work proposes a facial expression recognition system for a diversified field of applications. The purpose of the proposed system is to predict the type of expressions in a human face region. The implementation of the proposed method is fragmented into three components. [...] Read more.
This work proposes a facial expression recognition system for a diversified field of applications. The purpose of the proposed system is to predict the type of expressions in a human face region. The implementation of the proposed method is fragmented into three components. In the first component, from the given input image, a tree-structured part model has been applied that predicts some landmark points on the input image to detect facial regions. The detected face region was normalized to its fixed size and then down-sampled to its varying sizes such that the advantages, due to the effect of multi-resolution images, can be introduced. Then, some convolutional neural network (CNN) architectures were proposed in the second component to analyze the texture patterns in the facial regions. To enhance the proposed CNN model’s performance, some advanced techniques, such data augmentation, progressive image resizing, transfer-learning, and fine-tuning of the parameters, were employed in the third component to extract more distinctive and discriminant features for the proposed facial expression recognition system. The performance of the proposed system, due to different CNN models, is fused to achieve better performance than the existing state-of-the-art methods and for this reason, extensive experimentation has been carried out using the Karolinska-directed emotional faces (KDEF), GENKI-4k, Cohn-Kanade (CK+), and Static Facial Expressions in the Wild (SFEW) benchmark databases. The performance has been compared with some existing methods concerning these databases, which shows that the proposed facial expression recognition system outperforms other competing methods. Full article
(This article belongs to the Special Issue Research on Facial Expression Recognition)
Show Figures

Figure 1

20 pages, 4764 KiB  
Article
PCDRN: Progressive Cascade Deep Residual Network for Pansharpening
by Yong Yang, Wei Tu, Shuying Huang and Hangyuan Lu
Remote Sens. 2020, 12(4), 676; https://doi.org/10.3390/rs12040676 - 19 Feb 2020
Cited by 29 | Viewed by 3178
Abstract
Pansharpening is the process of fusing a low-resolution multispectral (LRMS) image with a high-resolution panchromatic (PAN) image. In the process of pansharpening, the LRMS image is often directly upsampled by a scale of 4, which may result in the loss of high-frequency details [...] Read more.
Pansharpening is the process of fusing a low-resolution multispectral (LRMS) image with a high-resolution panchromatic (PAN) image. In the process of pansharpening, the LRMS image is often directly upsampled by a scale of 4, which may result in the loss of high-frequency details in the fused high-resolution multispectral (HRMS) image. To solve this problem, we put forward a novel progressive cascade deep residual network (PCDRN) with two residual subnetworks for pansharpening. The network adjusts the size of an MS image to the size of a PAN image twice and gradually fuses the LRMS image with the PAN image in a coarse-to-fine manner. To prevent an overly-smooth phenomenon and achieve high-quality fusion results, a multitask loss function is defined to train our network. Furthermore, to eliminate checkerboard artifacts in the fusion results, we employ a resize-convolution approach instead of transposed convolution for upsampling LRMS images. Experimental results on the Pléiades and WorldView-3 datasets prove that PCDRN exhibits superior performance compared to other popular pansharpening methods in terms of quantitative and visual assessments. Full article
(This article belongs to the Section Remote Sensing Image Processing)
Show Figures

Graphical abstract

Back to TopTop