Hyper-spectral image segmentation using an improved PSO aided with multilevel fuzzy entropy

Chakraborty, Rupak; Sushil, Rama; Garg, M. L.

doi:10.1007/s11042-019-08114-x

Cited by 10 publications

(4 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed scheme in future may be extended for medical image segmentation due to its rapid segmentation capability 54 Improved Particle Swarm Optimization (IPSO) algorithm aided with fuzzy-entropy, IPSO-Fuzzy. Output of IPSO-fuzzy is used to train SVM classifier Fuzzy entropy Chakraborty et al ( 2019a ) Various Satellite and Standard Color Images Proposed method is compared with CS, DE, FF, GA and PSO PSNR, FSIM, Overall Accuracy, Kappa Index, Mean Accuracy and IoU The proposed IPSO doesn’t prematurely converge and in future may be applied on some larger dataset like ImageNet, COCO with respect to object recognition 55 Improved Elephant Herding Optimization (IEHO) Kapur’s entropy and between-class variance (Otsu’s thresholding) Chakraborty et al ( 2019b ) Standard Gray Scale Images Proposed method is compared with CS, ABC, BA, PSO, EHO and DP PSNR, FSIM and SSIM The proposed IEHO performs better than that of the conventional algorithms both in terms of quality and convergence rate 56 Whale Optimization Algorithm-Differential Evolution(WOA-DE) Kapur’s entropy Lang and Jia ( 2019 ) MRI: Medical Images, Satellite Images, standard gray scale Images Proposed method is compared with WOA, SSA, SCA, ALO, HSO, BA, PSO, BDE and IDSA. Otsu WOA-DE is compared with Kapur WOA-DE Average Fitness Values, PSNR, FSIM and SSIM The proposed WOA-DE avoids the loss due to population diversity and dropping into local optimum.…”

Section: Recent Trends In Multi-level Thresholding Using Nature-inspi...mentioning

confidence: 99%

Nature-inspired optimization algorithms and their significance in multi-thresholding image segmentation: an inclusive review

2022

View full text Add to dashboard Cite

Multilevel Thresholding (MLT) is considered as a significant and imperative research field in image segmentation that can efficiently resolve difficulties aroused while analyzing the segmented regions of multifaceted images with complicated nonlinear conditions. MLT being a simple exponential combinatorial optimization problem is commonly phrased by means of a sophisticated objective function requirement that can only be addressed by nondeterministic approaches. Consequently, researchers are engaging Nature-Inspired Optimization Algorithms (NIOA) as an alternate methodology that can be widely employed for resolving problems related to MLT. This paper delivers an acquainted review related to novel NIOA shaped lately in last three years (2019–2021) highlighting and exploring the major challenges encountered during the development of image multi-thresholding models based on NIOA.

show abstract

Section: Recent Trends In Multi-level Thresholding Using Nature-inspi...mentioning

confidence: 99%

Nature-inspired optimization algorithms and their significance in multi-thresholding image segmentation: an inclusive review

2022

View full text Add to dashboard Cite

show abstract

“…However, the complex data structure and high information redundancy of hyperspectral images make this task challenging. Although the operation of traditional image segmentation [15][16][17][18][19][20][21] is relatively simple, it is difficult to obtain satisfactory performance because it mostly relies on handmade features. Therefore, it is of great research significance to establish an efficient semantic segmentation model for hyperspectral images.…”

Section: Introductionmentioning

confidence: 99%

DCCaps-UNet: A U-Shaped Hyperspectral Semantic Segmentation Model Based on the Depthwise Separable and Conditional Convolution Capsule Network

Wei

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Traditional hyperspectral image semantic segmentation algorithms can not fully utilize the spatial information or realize efficient segmentation with less sample data. In order to solve the above problems, a U-shaped hyperspectral semantic segmentation model (DCCaps-UNet) based on the depthwise separable and conditional convolution capsule network was proposed in this study. The whole network is an encoding–decoding structure. In the encoding part, image features are firstly fully extracted and fused. In the decoding part, images are then reconstructed by upsampling. In the encoding part, a dilated convolutional capsule block is proposed to fully acquire spatial information and deep features and reduce the calculation cost of dynamic routes using a conditional sliding window. A depthwise separable block is constructed to replace the common convolution layer in the traditional capsule network and efficiently reduce network parameters. After principal component analysis (PCA) dimension reduction and patch preprocessing, the proposed model was experimentally tested with Indian Pines and Pavia University public hyperspectral image datasets. The obtained segmentation results of various ground objects were analyzed and compared with those obtained with other semantic segmentation models. The proposed model performed better than other semantic segmentation methods and achieved higher segmentation accuracy with the same samples. Dice coefficients reached 0.9989 and 0.9999. The OA value can reach 99.92% and 100%, respectively, thus, verifying the effectiveness of the proposed model.

show abstract

“…This not only preserved the edges and effectively reduced the halo artifacts, but also had a better effect on image edge smoothing. The "Summit Navigator" method proposed by Dinh T H et al [17], and the histogram-based hyperspectral image segmentation algorithm proposed by Chakraborty R et al [18], which can effectively extract the local maxima of the image histogram, but did not work well for differentiating objects of different sizes and states. A lightweight deep learning architecture Cloud Seg Net was proposed by Dev S et al [19], which was the first image segmentation framework for daytime and nighttime images containing clouds, but it required a large number of samples for learning and the detection speed is slow.…”

Section: Introductionmentioning

confidence: 99%

A Safety Detection Method on Construction Sites under Fewer Samples

Wang

Chen

et al. 2023

Electronics

View full text Add to dashboard Cite

In order to solve the problem of automatically completing safety detection for construction sites and give an alert based on high-speed image streams, this paper proposes a violation of rules and regulations (VoRR) recognition method on a construction site and gives a matching method by automatically obtaining a few samples. The proposed safety detection method consists of five parts, which are redundant information reduction, classification, feature extraction, matching, inference rule and alarm alert. Compared with existing safety detection methods, the accuracy of the proposed method is increased by more than 9%. It not only has better performance, but also has more functions: reminding and alarming. For the subsequent establishment of an unmanned supervision system model on a construction site, this research will provide a new method of decision support, target detection, and recognition in multiple different scenarios.

show abstract

Hyper-spectral image segmentation using an improved PSO aided with multilevel fuzzy entropy

Cited by 10 publications

References 64 publications

Nature-inspired optimization algorithms and their significance in multi-thresholding image segmentation: an inclusive review

Nature-inspired optimization algorithms and their significance in multi-thresholding image segmentation: an inclusive review

DCCaps-UNet: A U-Shaped Hyperspectral Semantic Segmentation Model Based on the Depthwise Separable and Conditional Convolution Capsule Network

A Safety Detection Method on Construction Sites under Fewer Samples

Contact Info

Product

Resources

About