Figure 3 - available from: Multimedia Tools and Applications
This content is subject to copyright. Terms and conditions apply.
Source publication
![Figure 1: Berkeley segmentation benchmark [14] (a) original images, and...](publication/308487029/figure/fig2/AS:409715482873858@1474695191237/Berkeley-segmentation-benchmark-14-a-original-images-and-b-to-f-region_Q320.jpg)
In the field of image analysis, segmentation is one of the most important preprocessing steps. One way to achieve segmentation is the use of threshold selection, where each pixel that belongs to a determined class, based on the mutual visual characteristics, is labeled according to the selected threshold. In this work, a combination of two pioneer...
Similar publications
This paper proposes the use of hybrid multilevel thresholding and harmony search algorithm (HSA) methods for segmenting the image of the tongue. The Otsu thresholding algorithm aided by the HSA optimization algorithm is used to look for optimal solution in order to produce the best threshold based on the inserted class. Parameters used there are th...
Citations
... In a wireless communication network, removing a critical node can result in network disconnection and a steep rise in latency. Considering the dynamic nature of wireless communication, finding critical nodes is not an offline problem, and the computational overhead of using optimization methods [37,38] can substantially decrease the lifetime of the network. Although substituting classification algorithms with optimization methods can confront computational complexity, the imbalance problem (where only 15% of nodes are critical ones) can result in a high false-positive rate. ...
The energy efficiency of wireless sensor networks (WSNs) as a key feature of the Internet of Things (IoT) and fifth-generation (5G) mobile networks is determined by several key characteristics, such as hop count, user’s location, allocated power, and relay. Identifying important nodes, known as critical nodes, in IoT networks that involve a massive number of interconnected devices and sensors significantly affects these characteristics. However, it also requires a significant computational overhead and energy consumption. To address this issue, we introduce a novel supervised active learning method for identifying critical nodes in IoT networks aimed at enhancing the energy efficiency of WSNs in 5G environments. Our experimental results, designed to closely replicate varied and complex IoT network scenarios focusing on mission-critical multi-hop IoT applications, demonstrate the proposed method’s capability to improve adaptability and computational efficiency. These results suggest a strong potential for mission-critical applications in real-world large-scale multi-hop WSN environments in 5G, as well as massively distributed IoT.
... From the previous analysis, the advantages of the ABHGS algorithm should be further verified on CEC 2017 benchmark functions, compared with several state-of-the-art advanced algorithms. These modified algorithms are adaptive weights levy-assisted SSA (WLSSA), 94 chaotic mutative MFO (CLSGMFO), 95 efficient boosted GWO (OBLGWO), 96 weighted DE (WDE), 97 improved GWO (IGWO), 98 the hybrid algorithm of SCA and DE (SCADE), 99 cloud bat algorithm (CBA). 100 Tables 6 and 7 show the experimental results between ABHGS and eight advanced algorithms on CEC 2017 functions. ...
The domains of contemporary medicine and biology have generated substantial high-dimensional genetic data. Identifying representative genes and decreasing the dimensionality of the data can be challenging. The goal of gene selection is to minimize computing costs and enhance classification precision. Therefore, this article designs a new wrapper gene selection algorithm named artificial bee bare-bone hunger games search (ABHGS), which is the hunger games search (HGS) integrated with an artificial bee strategy and a Gaussian bare-bone structure to address this issue. To evaluate and validate the performance of our proposed method, ABHGS is compared to HGS and a single strategy embedded in HGS, six classic algorithms, and ten advanced algorithms on the CEC 2017 functions. The experimental results demonstrate that the bABHGS outperforms the original HGS. Compared to peers, it increases classification accuracy and decreases the number of selected features, indicating its actual engineering utility in spatial search and feature selection.
... The IWO in IWBA contributes to strengthening the exploration ability and an inertial weight algorithm based on Lagrange interpolation helps to balance the exploration and exploitation ability. Dehshibi et al. (2017) designed a hybrid bio-inspired learning algorithm (BFHS) by combining the bacterial foraging algorithm, harmony search algorithm, and learning automata. BFHS adopted two objective functions named Otsu and Kapur entropy to determine the best threshold. ...
... Eleven real-life images has been evaluated and compared to the algorithms CS, DE, jDE, ABC, and PSO. In 2017, Dehshibi et al. [16]implemented a new BFHS hybrid algorithm with otsu's and kapur entropy criterions utilizing two set (standard and satellite) of images. Research findings show that the algorithm's ability to select multiple thresholds is important, as compared to the other algorithms that address the same problem. ...
In a variety of image processing applications, multilevel thresholding image segmentation has gotten a lot of interest. When traditional approaches are utilised, however, the process of obtaining the ideal threshold values takes time. Despite the fact that Hybrid metaheuristic methods can be used to overcome these limits, such approaches may be ineffective when dealing with a local solution. The present study proposes a multi-level image thresholding based hybridization strategy based Sine-Cosine Crow Search Algorithm(SCCSA) to make more efficient image segmentation. The main limitation of the classical Crow Search Algorithm (CSA) is that search agents sometimes do not produce the best solutions. To update a solution to the best solution, each search agent can use Sine-Cosine Algorithm (SCA) movements to update its position accordingly. This ensures a good balance between two goals (exploration and exploitation) would improve the efficiency of the search algorithm. The optimal threshold values are searched by the chosen objective functions of the otsu’s and kapur’s entropy approaches. The hybrid algorithm is evaluated in 12 standard image sets and then compared with the performance of other state-of-the-art algorithms such as ICSA, SCA, CSA and ABC. Experimental results showed that, in different metrics of the output such as objective function values, PSNR, STD values, Mean, SSIM, FSIM and CPU time, the proposed algorithm is consistently higher than other algorithms. In addition, the wilcoxon test is performed using the proposed algorithm to detect the significant differences between the other algorithms. The findings indicated that the proposed SCCSA succeeds with other well-known algorithms and has dominance over robust, accurate and convergent values.
... Although the algorithm used the Otsu method and random localization to increase efficiency and speed, the proposed algorithm provided better results than other algorithms. This paper companies Harmony Search (HS), Bacterial Foraging (BF), and Learning Automata (LA) algorithms to solve the threshold selection problem using Otsu and Kapur methods [48]. The proposed method avoids typical sensitivity, such as the exception maximization (EM) algorithm. ...
This paper studied the multilevel threshold image segmentation-based metaheuristics optimization methods and their applications. Image segmentation is a common problem in the image processing domain, and it is an essential process in image analysis, directly impacting image analysis results. Thresholding is one of the most manageable and extensively utilized methods for handling image segmentation problems. In this paper, four main parts are given; (1) We present the main procedures and definitions of the multilevel threshold image segmentation problem. The standard fitness function and the evaluation criteria are also given to facilitate the problem representation for the new researchers in this domain. (2) All the related works that have used optimization methods in solving the multilevel threshold image segmentation problems are presented in more detail, focusing on the image segmentation problem and its solutions. The given related works are outlined according to the used algorithms. (3) Comprehensive results and analysis of several well-known optimization algorithms are conducted to solve the multilevel threshold image segmentation problems. These comparative methods include Aquila Optimizer (AO), Whale Optimization Algorithm (WOA), Salp Swarm Algorithm (SSA), Arithmetic Optimization Algorithm (AOA), Particle Swarm Optimizer (PSO), Marine Predators Algorithm (MPA), Krill Herd Algorithm (KHA), Multi-verse Optimizer (MVO), and Gray Wolf Optimizer (GWO). Eight standard benchmark images are used to test the comparative methods. The results are evaluated using three standard measures: fitness function, PeakSignal-to-Noise Ratio (PSNR), and the Structural Similarity Index (SSIM). (4) Discussion, open challenging, and new trends are given to help the scholars in future research get near the common problems and defect in that domain. The collected data in this review has been taken from google scholar using the stander search method. The main keywords that have been used in the search are multilevel, threshold, image, segmentation, optimization, and algorithm. We covered all the published papers in detail according to the given information, focusing on finding the common problems that still need further investigation. Furthermore, future research directions based on recently evolving designs are outlined, which should undoubtedly aid current researchers and practitioners and pave the way for new researchers interested in multilevel threshold image segmentation to seek their research in the field.
... Inspired by recent reinforcement learning achievements [13] and attempts at informative sample selection to improve machine learning performance, we propose a novel transfer learning strategy based on partially supervised reinforcement learning in which the SoftMax confidence score is used to select informative samples and discard negative transfers. ...
Many samples are necessary to train a convolutional neural network (CNN) to achieve optimum performance while maintaining generalizability. Several studies, however, have indicated that not all input data in large datasets are informative for the model, and using them for training can degrade the model's performance and add uncertainty. Furthermore, in some domains, such as medicine, there is insufficient labelled data to train a deep learning model from scratch, necessitating the use of transfer learning to fine-tune a pretrained model in another domain. This paper proposes a transfer learning strategy based on partially supervised reinforcement learning (RL) to address these concerns by selecting the most informative samples while avoiding negative transfers from the dataset. We conducted several experiments on the benchmark image classification databases MNIST, Fashion-MNIST, and CIFAR-10 to create a fair test harness for assessing the performance of the proposed strategy, which can be extended to explore other domains in the future. The results show that the proposed strategy outperforms the classical training methods.
... China's IVD market started late, but grew faster [5] . From 2008 to 2012, the growth rate of China's in vitro testing market is significantly higher than the global average and the annual compound growth rate will remain at about 16 %. ...
... Discontinuities, interclass variations, peaks, and valleys in the histogram are used to determine adaptive multilevel thresholds (T 1:N ). Various adaptive multilevel thresholding techniques are available in the literature [39][40][41][42][43]. This reported work uses Otsu's method [42,43], which is a widely used technique in computer vision and image processing applications. ...
Computed tomography (CT) is one of the most common and beneficial medical imaging schemes, but the associated high radiation dose injurious to the patient is always a concern. Therefore, postprocessing-based enhancement of a CT reconstructed image acquired using a reduced dose is an active research area. Amoeba- (or spatially variant kernel-) based filtering is a strong candidate scheme for postprocessing of the CT image, which adapts its shape according to the image contents. In the reported research work, the amoeba filtering is customized for postprocessing of CT images acquired at a reduced X-ray dose. The proposed scheme modifies both the pilot image formation and amoeba shaping mechanism of the conventional amoeba implementation. The proposed scheme uses a Wiener filter-based pilot image, while region-based segmentation is used for amoeba shaping instead of the conventional amoeba distance-based approach. The merits of the proposed scheme include being more suitable for CT images because of the similar region-based and symmetric nature of the human body anatomy, image smoothing without compromising on the edge details, and being adaptive in nature and more robust to noise. The performance of the proposed amoeba scheme is compared to the traditional amoeba kernel in the image denoising application for CT images using filtered back projection (FBP) on sparse-view projections. The scheme is supported by computer simulations using fan-beam projections of clinically reconstructed and simulated head CT phantoms. The scheme is tested using multiple image quality matrices, in the presence of additive projection noise. The scheme implementation significantly improves the image quality visually and statistically, providing better contrast and image smoothing without compromising on edge details. Promising results indicate the efficacy of the proposed scheme.
... In hybrid methods (Talbi 2002), EAs are combined with heuristic rules or classical constrained search methods. This approach includes (1) combination of two methods like Otsu and Kapur with bacterial foraging and harmony search algorithm (Dehshibi et al. 2016); (2) simulated binary crossover and DE with polynomial mutation are combined (Lin et al. 2016); (3) PSO combined with GA (Garg 2016) and (4) hybrid firefly algorithm (HFA) combines FA and DE advantages and they can be executed in parallel to promote information sharing among the offspring and thus enhancing searching efficiency. 4. Decoder approaches (Jacquin et al. 2016;Koziel and Michalewicz 1999;Prestwich et al. 2015) uses mapping of feasible solution search space onto sample space where nature inspired algorithms (NIAs) can get better outcomes; 5. Multi-objective (vector) optimization approaches (Deb 2000;Jiang and Yang 2016a, b;Mezura-Montes et al. 2008;Silva et al. 2014) transforms a constraint optimization problem into vector problems with two or more objectives. ...
Almost all engineering optimization problems in the real world are constrained by nature. Swarm intelligence is a bio-inspired technique based on studying and observing fireflies, ants, birds, and fish in nature. Firefly algorithm (FA) is the most prominent swarm based metaheuristic algorithm used for solving a global optimization problem. This paper presents two new constrained optimization algorithms: (1) firefly algorithm with extended oracle penalty method (FA-EOPM) and (2) modified augmented Lagrangian with firefly algorithm (MAL-FA). These proposed algorithms are applied for solving classic thirteen benchmark constraint problems as well as a few good engineering problem designs. The efficiency, effectiveness, and performance of MAL-FA and FA-EOPM algorithms are estimated on the basis of statistical analysis such as best optimal value, worst value, mean value, p value and standard deviation value of the existing methods. The experimental results show that the proposed MAL-FA algorithm offers better outcomes for most of the cases in terms of the number of function evaluations compared to various optimization algorithms.
... In 2016, a novel 2D K-L divergence and modified PSO based segmentation algorithm has been suggested using modified PSO approach [36]. In order to deal with multi-level image segmentation problem various hybrid approaches have been offered in the literature such as gravitational search algorithm and genetic algorithm [37], a hybrid differential evolution [38], a hybrid bio-inspired learning algorithm [39], social spiders optimization and flower pollination algorithm [40], and hybrid particle swarm algorithm with learning strategy based optimal image thresholding method [41]. Successively, numerous multiobjective image thresholding approaches have also been proposed by many researcher to obtain the accurate segmentation. ...
In this paper, a new well-organized fusion-based 3D Otsu energy thresholding prototypical for multilevel color image segmentation by means of lightning search algorithm (LSA) has been projected. Although, 3D Otsu works by means of between-class variances over the help of 3-D histogram but the performance is not satisfactory. As a result, the energy curve model is implemented, that works on contextual information of an image. However, using the concept of energy curve for 3D Otsu produces better result, but at the cost of complexity and also correspondingly the complication level for pick out appropriate thresholds is high. To overcome this limitation, the concept of LSA optimization algorithm is introduced. LSA is a fresh optimization process encouraged by the winding characteristics of lightening through a thunderstorm. In this paper, LSA is used to shorten the delinquent of comprehensive exploration for finding the finest thresholds. In addition to this, to enhance the quality of multi-level segmented image the concept of fusion based on local contrast is introduced. In this paper, 1D, 2D and 3D-Otsu methods using numerous optimization algorithms are implemented with energy curve and fusion based approach and compared with proposed fusion based energy 3D Otsu method using LSA algorithm. Experimental outputs demonstrate that the proposed Fusion-Energy-3D Otsu-LSA algorithm is outperforms and it can be established by comparing the well-known fidelity constraints of an image.
