High-Noise Grayscale Image Denoising Using an Improved Median Filter for the Adaptive Selection of a Threshold

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(2), P. 635 - 635

Published: Jan. 11, 2024

Grayscale image processing is a key research area in the field of computer vision and analysis, where quality visualization effects may be seriously damaged by high-density salt pepper noise. A traditional median filter for noise removal result poor detail reservation performance under strong judgment different characteristics has dependence rather weak robustness. In order to reduce on when high-noise grayscale images, an improved two-dimensional maximum Shannon entropy (TSETMF) proposed adaptive selection threshold enhance while stably effectively retaining details images. The framework TSETMF algorithm designed detail. images filtered means automatically partitioning window size, value which adaptively calculated using entropy. theoretical model verified analyzed through comparative experiments three kinds classical experimental results demonstrate that exhibits better than filter, with higher suppression denoising stability. This stronger ability demonstrated peak signal-to-noise ratio (PSNR) 24.97 dB 95% density located Lena image. stability, from 5% 95%, minor decline PSNR approximately 10.78% relative 23.10 Cameraman Furthermore, it can advanced promote filtering stability

Language: Английский

---

Grade Prediction Modeling in Hybrid Learning Environments for Sustainable Engineering Education

Sustainability, Journal Year: 2022, Volume and Issue: 14(9), P. 5205 - 5205

Published: April 26, 2022

Since mid-March 2020, due to the COVID-19 pandemic, higher education has been facing a very uncertain situation, despite hasty implementation of information and communication technologies for distance online learning. Hybrid learning, i.e., mixing face-to-face seems be rule in most universities today. In order build post-COVID-19 university education, one that is increasingly digital sustainable, it essential learn from these years health crisis. this context, paper aims identify quantify main factors affecting mechanical engineering student performance generalized linear autoregressive (GLAR) model. This model, which distinguished by its simplicity ease implementation, responsible predicting grades learning situations hybrid environments. The thirty or so variables identified previously tested model 2020–2021, was exclusive mode were evaluated blended spaces. Given low predictive power original about ten new factors, specific then tested. refined version GLAR predicts within ±1 with success rate 63.70%, making 28.08% more accurate than originally created 2020–2021. Special attention also given students whose grade predictions underestimated who failed. methodology presented applicable all aspects academic process, including students, instructors, decisionmakers.

Language: Английский

---

An adaptive watershed segmentation based medical image denoising using deep convolutional neural networks

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 93, P. 106119 - 106119

Published: March 2, 2024

Language: Английский

---

Advanced genetic image encryption algorithms for intelligent transport systems

Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110162 - 110162

Published: Feb. 17, 2025

---

A Comprehensive survey on ear recognition: Databases, approaches, comparative analysis, and open challenges

Neurocomputing, Journal Year: 2023, Volume and Issue: 537, P. 236 - 270

Published: March 30, 2023

Language: Английский

---

Transfer Learning-Based Automatic Hurricane Damage Detection Using Satellite Images

Electronics, Journal Year: 2022, Volume and Issue: 11(9), P. 1448 - 1448

Published: April 30, 2022

After the occurrence of a hurricane, assessing damage is extremely important for emergency managers so that relief aid could be provided to afflicted people. One method determine damaged and undamaged buildings post-hurricane. Normally, assessment performed by conducting ground surveys, which are time-consuming involve immense effort. In this paper, transfer learning techniques have been used determining in post-hurricane satellite images. Four different techniques, include VGG16, MobileNetV2, InceptionV3 DenseNet121, applied 23,000 Hurricane Harvey images, occurred Texas region. A comparative analysis these models has on basis number epochs optimizers used. The performance VGG16 pre-trained model was better than other achieved an accuracy 0.75, precision 0.74, recall 0.95 F1-score 0.83 when Adam optimizer When comparison best performing terms various optimizers, produced 0.78 RMSprop optimizer.

Language: Английский

---

A novel content-selected image encryption algorithm based on the LS chaotic model

Journal of King Saud University - Computer and Information Sciences, Journal Year: 2022, Volume and Issue: 34(10), P. 8245 - 8259

Published: Aug. 10, 2022

Many holistic image encryption schemes have been proposed in recent decades that achieve a certain security level. However, considering the actual application environment, sometimes it is not necessary to encrypt whole image, but rather selected specific content of image. Thus, this paper proposes chaos-based algorithm for contents with non-regular size. First, we construct novel LS chaos model combines Sine map and Logistic then improve its chaotic complexity by perturbing control parameters introducing delayed states. Second, obtain coordinates each pixel using PSPNet semantic segmentation trained on Cityscapes dataset Faster-RCNN target detection MS-COCO dataset. Finally, pixels are encrypted size algorithm. Several simulation experimental results prove new exhibits superior properties generates complex pseudo-random sequences. Furthermore, our effectively implements shows excellent performance, indicating highly competitive terms capability.

Language: Английский

---

Particle Swarm Optimization and Two-Way Fixed-Effects Analysis of Variance for Efficient Brain Tumor Segmentation

Cancers, Journal Year: 2022, Volume and Issue: 14(18), P. 4399 - 4399

Published: Sept. 10, 2022

Segmentation of brain tumor images, to refine the detection and understanding abnormal masses in brain, is an important research topic medical imaging. This paper proposes a new segmentation method, consisting three main steps, detect lesions using magnetic resonance imaging (MRI). In first step, parts image delineating skull bone are removed, exclude insignificant data. second which contribution this study, particle swarm optimization (PSO) technique applied, block that contains lesions. The fitness function, used determine best among all candidate blocks, based on two-way fixed-effects analysis variance (ANOVA). last step algorithm, K-means method lesion block, classify it as or not. A thorough evaluation proposed algorithm was performed, using: (1) private MRI database provided by Kouba center-Algiers (KICA); (2) multimodal challenge (BraTS) 2015 database. Estimates selected function were compared those sum-of-absolute-differences (SAD) dissimilarity criterion, demonstrate efficiency robustness ANOVA. performance optimized then results several state-of-the-art techniques. obtained, Dice coefficient, Jaccard distance, correlation root mean square error (RMSE) measurements, demonstrated superiority over equivalent

Language: Английский

---

Deep learning based computer vision under the prism of 3D point clouds: a systematic review

The Visual Computer, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 29, 2024

Abstract Point clouds consist of 3D data points and are among the most considerable formats for representations. Their popularity is due to their broad application areas, such as robotics autonomous driving, employment in basic vision tasks segmentation, classification, detection. However, processing point challenging compared other visual forms images, mainly unstructured nature. Deep learning (DL) has been established a powerful tool processing, reporting remarkable performance enhancements traditional methods all 2D tasks. However new challenges emerging when it comes clouds. This work aims guide future research by providing systematic review DL on clouds, holistically covering technologies cloud formation reviewed each other. The discussed, state-of-the-art models’ performances focusing solutions. Moreover, this popular benchmark datasets summarized based task-oriented applications, aiming highlight existing constraints comparatively evaluate them. Future directions upcoming trends also highlighted.

Language: Английский

---

Facial Micro-Expression Recognition Based on Deep Local-Holistic Network

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(9), P. 4643 - 4643

Published: May 5, 2022

A micro-expression is a subtle, local and brief facial movement. It can reveal the genuine emotions that person tries to conceal considered an important clue for lie detection. The research has attracted much attention due its promising applications in various fields. However, short duration low intensity of movements, recognition faces great challenges, accuracy still demands improvement. To improve efficiency feature extraction, inspired by psychological study attentional resource allocation cognition, we propose deep local-holistic network method recognition. Our proposed algorithm consists two sub-networks. first Hierarchical Convolutional Recurrent Neural Network (HCRNN), which extracts abundant spatio-temporal features. second Robust principal-component-analysis-based recurrent neural (RPRNN), global sparse features with micro-expression-specific representations. extracted effective are employed through fusion We evaluate on combined databases consisting four most commonly used databases, i.e., CASME, CASME II, CAS(ME)2, SAMM. experimental results show our achieves reasonably good performance.

Language: Английский

---