An efficient multi-level thresholding method for breast thermograms analysis based on an improved BWO algorithm DOI Creative Commons
Simrandeep Singh, Harbinder Singh, Nitin Mittal

et al.

BMC Medical Imaging, Journal Year: 2024, Volume and Issue: 24(1)

Published: July 30, 2024

Abstract Breast cancer is a prevalent disease and the second leading cause of death in women globally. Various imaging techniques, including mammography, ultrasonography, X-ray, magnetic resonance, are employed for detection. Thermography shows significant promise early breast detection, offering advantages such as being non-ionizing, non-invasive, cost-effective, providing real-time results. Medical image segmentation crucial analysis, this study introduces thermographic algorithm using improved Black Widow Optimization Algorithm (IBWOA). While standard BWOA effective complex optimization problems, it has issues with stagnation balancing exploration exploitation. The proposed method enhances Levy flights improves exploitation quasi-opposition-based learning. Comparing IBWOA other algorithms like Harris Hawks (HHO), Linear Success-History based Adaptive Differential Evolution (LSHADE), whale (WOA), sine cosine (SCA), black widow (BWO) otsu Kapur's entropy method. Results show delivers superior performance both qualitative quantitative analyses visual inspection metrics fitness value, threshold values, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), feature (FSIM). Experimental results demonstrate outperformance IBWOA, validating its effectiveness superiority.

Language: Английский

Improving the segmentation of digital images by using a modified Otsu’s between-class variance DOI Open Access
Simrandeep Singh, Nitin Mittal, Harbinder Singh

et al.

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 82(26), P. 40701 - 40743

Published: March 31, 2023

Language: Английский

Citations

10
Simplified expression and recursive algorithm of multi-threshold Tsallis entropy DOI
Shaoxun Wang, Jiulun Fan

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 237, P. 121690 - 121690

Published: Sept. 20, 2023

Language: Английский

Citations

8
Filament-necking localization method via combining improved PSO with rotated rectangle algorithm for safflower-picking robots DOI
Zhenyu Xing, Zhenguo Zhang,

Ruimeng Shi

et al.

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 215, P. 108464 - 108464

Published: Dec. 1, 2023

Language: Английский

Citations

7
Object segmentation for image indexing in large database DOI Creative Commons
Juel Sikder, Mohammad Khairul Islam, Farah Jahan

et al.

Journal of King Saud University - Computer and Information Sciences, Journal Year: 2024, Volume and Issue: 36(2), P. 101937 - 101937

Published: Jan. 20, 2024

It is a challenging task to design an effective model for object segmentation considering numerous classes because different might have features and backgrounds. We propose unique classification detect classify objects. modified version of the U-Net whereas, task, we fusion scheme by exploiting two popular CNN models including ResNet50 MobileNet. conduct experiments on Caltech101 benchmark dataset which contains 8677 images grouped into 101 classes. Besides, examine performance our proposed method detection, devise polygonal ground-truth based dataset. The feature polygon shape ground truth that it creates mask target image in probability noise very low where there bounding box truth. Extensive demonstrate efficacy approaches compared other existing with accuracy 95.94% 99.90%. also achieved average IoU score 0.98 validates recognition model.

Language: Английский

Citations

2
Application of Improved Satin Bowerbird Optimizer in Image Segmentation DOI Creative Commons
Linguo Li,

Shunqiang Qian,

Zhangfei Li

et al.

Frontiers in Plant Science, Journal Year: 2022, Volume and Issue: 13

Published: May 6, 2022

Aiming at the problems of low optimization accuracy and slow convergence speed Satin Bowerbird Optimizer (SBO), an improved (ISBO) based on chaotic initialization Cauchy mutation strategy is proposed. In order to improve value proposed algorithm in engineering practical applications, we apply it segmentation medical plant images. To accuracy, pertinence initial population, population initialized by introducing Logistic map. avoid falling into local optimum (prematurity), search performance through strategy. Based extensive visual quantitative data analysis, this paper conducts a comparative analysis ISBO with SBO, fuzzy Gray Wolf (FGWO), Fuzzy Coyote Optimization Algorithm (FCOA). The results show that achieves better effects both disease

Language: Английский

Citations

10
Design and synthesis of circular antenna array using artificial hummingbird optimization algorithm DOI
Harbinder Singh, Simrandeep Singh, Amit Gupta

et al.

Journal of Computational Electronics, Journal Year: 2022, Volume and Issue: 21(6), P. 1293 - 1305

Published: Aug. 18, 2022

Language: Английский

Citations

10
A novel algorithm for image segmentation (IP-MH-MLT): employing an image partitioning technique with metaheuristic parameters to enhance multilevel thresholding DOI

Shivankur Thapliyal,

Narender Kumar

International Journal of Systems Assurance Engineering and Management, Journal Year: 2024, Volume and Issue: 15(9), P. 4291 - 4347

Published: Aug. 7, 2024

Language: Английский

Citations

1
Tree ring segmentation using UNEt TRansformer neural network on stained microsections for quantitative wood anatomy DOI Creative Commons
Miguel García‐Hidalgo, Ángel García‐Pedrero, Vicente Rozas

et al.

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 14

Published: Jan. 8, 2024

Forests are critical in the terrestrial carbon cycle, and knowledge of their response to ongoing climate change will be crucial for determining future fluxes trajectories. In areas with contrasting seasons, trees form discrete annual rings that can assigned calendar years, allowing extract valuable information about how respond environment. The anatomical structure wood provides highly-resolved reaction adaptation climate. Quantitative anatomy helps retrieve this by measuring at cellular level using high-resolution images micro-sections. However, whereas large advances have been made identifying structures, obtaining meaningful is still hampered correct tree ring delimitation on images. This a time-consuming task requires experienced operators manually delimit boundaries. Classic methods automatic segmentation based pixel values being replaced new approaches neural networks which capable distinguishing even when demarcations require high expertise. Although used macroscopic wood, complexity cell patterns stained microsections broadleaved species adaptive models accurately accomplish task. We present an boundary delineation cross-sectional microsection from beech cores. trained UNETR, combined network UNET attention mechanisms Visual Transformers, automatically segment Its accuracy was evaluated considering discrepancies manual consequences disparity goals quantitative analyses. most cases (91.8%), matched or improved segmentation, rate vessels assignment similar between two categories, considered better. application convolutional networks-based outperforms human operator segmentations confronting specific parameters analysis. Current may reduce cost massive accurate data collection anatomy.

Language: Английский

Citations

1
Multi-Level Image Segmentation Combining Chaotic Initialized Chimp Optimization Algorithm and Cauchy Mutation DOI Open Access
Shujing Li,

Zhangfei Li,

Wenhui Cheng

et al.

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2024, Volume and Issue: 80(2), P. 2049 - 2063

Published: Jan. 1, 2024

To enhance the diversity and distribution uniformity of initial population, as well to avoid local extrema in Chimp Optimization Algorithm (CHOA), this paper improves CHOA based on chaos initialization Cauchy mutation. First, Sin is introduced improve random population scheme CHOA, which not only guarantees but also enhances population. Next, mutation added optimize global search ability process position (threshold) updating falling into optima. Finally, an improved was formed through combination (CICMCHOA), then taking fuzzy Kapur objective function, applied CICMCHOA natural medical image segmentation, compared it with four algorithms, including Satin Bowerbird optimizer (ISBO), Cuckoo Search (ICS), etc. The experimental results deriving from visual specific indicators demonstrate that delivers superior segmentation effects segmentation.

Language: Английский

Citations

1
Fuzzy Hybrid Coyote Optimization Algorithm for Image Thresholding DOI Open Access
Linguo Li,

Xuwen Huang,

Shunqiang Qian

et al.

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2022, Volume and Issue: 72(2), P. 3073 - 3090

Published: Jan. 1, 2022

In order to address the problems of Coyote Optimization Algorithm in image thresholding, such as easily falling into local optimum, and slow convergence speed, a Fuzzy Hybrid (hereinafter referred FHCOA) based on chaotic initialization reverse learning strategy is proposed, its effect thresholding verified. Through initialization, random number mode standard coyote optimization algorithm (COA) replaced by sequence. Such sequence nonlinear long-term unpredictable, these characteristics can effectively improve diversity population algorithm. Therefore, this paper we first perform using replace COA. By combining lens imaging optimal worst strategy, hybrid then formed. process traversal, best pack are selected for operation respectively, which prevents optimum certain extent also solves problem premature convergence. Based above improvements, has better global computational robustness. The simulation results show that than five commonly used algorithms when multiple images different threshold numbers set.

Language: Английский

Citations

6