Enhanced Detection of Measurement Anomalies in Cartridge Cases Using 3D Gray-Level Co-Occurrence Matrix

Forensic Science International, Journal Year: 2025, Volume and Issue: 367, P. 112366 - 112366

Published: Jan. 7, 2025

Language: Английский

---

Research and Practice of Reconstructing Traditional Non-legacy Clothing Patterns Based on Computer Graphics Technology

Applied Mathematics and Nonlinear Sciences, Journal Year: 2025, Volume and Issue: 10(1)

Published: Jan. 1, 2025

Abstract In fashion design, there is a profound synergy between traditional patterns and non-heritage crafts, which intertwine with each other to produce unique compelling effects. This not only reflects the innovation of but also highlights cultural heritage interpretation. this paper, texture synthesis algorithm based on block sampling used find relevant feature values clothing through gray scale correlation matrix calculate optimal size blocks. The Graphcut proposed connect pixel points overlapping area in selected synthesized block, improved path using A* extract block. For extracted features, 3D model reconstruction technology utilized reconstruct ornament. After empirical analysis, it can be seen that consumers’ preference for more inclined massed diagonal compositions, average scores 7.025 6.896, respectively.For appearance experience, wearing emotional quality experience texture, are 3.345, 3.248, 3.485, 3.321, respectively.The reconstructed paper bring consumers positive emotions.

Language: Английский

---

Research on intelligent prediction of hydrogen pipeline leakage fire based on Finite Ridgelet neural network

International Journal of Hydrogen Energy, Journal Year: 2022, Volume and Issue: 47(55), P. 23316 - 23323

Published: June 1, 2022

Language: Английский

---

Risk Factors for Unilateral Trigeminal Neuralgia Based on Machine Learning

Frontiers in Neurology, Journal Year: 2022, Volume and Issue: 13

Published: April 8, 2022

Neurovascular compression (NVC) is considered as the main factor leading to classical trigeminal neuralgia (CTN), and a part of idiopathic TN (ITN) may be caused by NVC (ITN-nvc). This study aimed explore risk factors for unilateral CTN or ITN-nvc (UC-ITN), which have bilateral NVC, using machine learning (ML).A total 89 patients with UC-ITN were recruited prospectively. According whether there was on unaffected side, divided into two groups. All underwent magnetic resonance imaging (MRI) scan. The cisternal segment nerve manually delineated, avoided offending vessel (Ofv), features extracted. Dimensionality reduction, feature selection, model construction, evaluation performed step-by-step.Four textural greater weight selected in without side. For six selected. (rad_score) showed significant differences between affected sides (p < 0.05). nomogram had optimal diagnostic power, area under curve (AUC) training validation cohorts 0.76 0.77, respectively. Ofv rad_score according nomogram.Besides texture trigeminal-nerve also UC-ITN. These findings provided basis further exploration microscopic etiology

Language: Английский

---

An ensemble mosaicing and ridgelet based fusion technique for underwater panoramic image reconstruction and its refinement

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 82(22), P. 33719 - 33771

Published: March 8, 2023

Language: Английский

---

Approach to breech face impression comparison based on the robust estimation of a correspondence function

Forensic Science International, Journal Year: 2022, Volume and Issue: 333, P. 111229 - 111229

Published: Feb. 11, 2022

Language: Английский

---

Fractal Geometry and Convolutional Neural Networks for the Characterization of Thermal Shock Resistances of Ultra-High Temperature Ceramics

Fractal and Fractional, Journal Year: 2022, Volume and Issue: 6(10), P. 605 - 605

Published: Oct. 17, 2022

The accurate characterization of the surface microstructure ultra-high temperature ceramics after thermal shocks is great practical significance for evaluating their resistance properties. In this paper, a fractal reconstruction method image Ultra-high repeated proposed. nonlinearity and spatial distribution characteristics oxidized surfaces were extracted. A convolutional neural network model based on deep learning was established to realize automatic recognition classification shock cycles ceramics, obtaining accuracy 93.74%. It provides novel quantitative character which contributes understanding influence oxidation shocks.

Language: Английский

---

Color Image Watermarking Using Adaptive Tunable Q Wavelet, Finite Ridge Let, and Arnold Transforms with TSVD

IETE Journal of Research, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 13

Published: Jan. 17, 2024

In recent years, researchers have been working to integrate watermarking practices anchored in wavelet transform (WT) coefficients and Singular value decomposition (SVD) recover the robustness of watermarked images opposition geometric non-geometric attacks. Conversely, watermark embedding, can initiate vagueness false-positive problem (FPP). To address this issue, Flamingo search algorithm-based Color Image Watermarking using Adaptive Tunable Q wavelet, Finite ridge let, Arnold transforms with Truncated (ATQWT-FRT-AT-TSVD-FSOA-CIW) is proposed. The proposed ATQWT-FRTAT-TSVD-FSOA-CIW method separated into two stages: (i) embedding (ii) extraction. scaling factor optimized help algorithm, which provides higher robustness, strength, resistance a problem, better quality scheme. ATQWT-FRT-AT-TSVD-FSOA-CIW simulated MATLAB tool. performance design estimated under several metrics, such as Peak signal noise ratio (PSNR), Structural similarity index measurement (SSIM), Normalized cross-correlation (NCC). attains 35%, 22.43%, 21.157%, 13.96%, 7.186% PSNR compared existing designs, like secure robust color image utilizing nature-inspired intelligence (DWT-SVD-ABCOA-CIW), Artificial bee colony basis perceptually tuned blind hybrid LWT-DCT domain (LWT-DCT-ABCOA-CIW), DWT-SVD based adaptive multi-watermarking scheme for copyright protection AMEF PSO-GWO (DWT-SVD-Hybrid PSO-GWOA-CIW), Robust on fractional Krawtchouk optimization (FrKT-Hybrid FO-CSOA-CIW), semi-blind (DWTFRT-AT-SVD-PSO-CIW).

Language: Английский

---

Fusion model of gray level co-occurrence matrix and convolutional neural network faced for histopathological images

Review of Scientific Instruments, Journal Year: 2024, Volume and Issue: 95(10)

Published: Oct. 1, 2024

The image recognition of cancer cells plays an important role in diagnosing and treating cancer. Deep learning is suitable for classifying histopathological images providing auxiliary technology diagnosis. convolutional neural network employed the classification images; however, model’s accuracy may decrease along with increase layers. Extracting appropriate features helpful classification. In this paper, different are represented by extracting gray co-occurrence matrix. These recombined into a 16 × 3 matrix to form artificial image. original fused summing softmax output. divided training set, validation testing set. Each dataset consists 1500 images, while test each consist 500 images. results indicate that effectiveness our fusion model demonstrated through significant improvements accuracy, precision, recall, F1-score, average reaching 99.31%. This approach not only enhances performance tissue pathology but also holds promise advancing computer-aided diagnosis pathology.

Language: Английский

---

Generalizable features-based method for breech face comparisons

Published: Sept. 13, 2024

Language: Английский

---