Explore the vast range of titles available.

Evolutionary Computation Methods (ECMs) are proposed as stochastic search methods to solve complex optimization problems where classical optimization methods are not suitable. Most of the proposed ECMs aim to find the global optimum for a given function. However, from a practical point of view, in engineering, finding the global optimum may not always be useful, since it may represent solutions that are not physically, mechanically or even structurally realizable. Commonly, the evolutionary operators of ECMs are not designed to efficiently register multiple optima by executing them a single run. Under such circumstances, there is a need to incorporate certain mechanisms to allow ECMs to maintain and register multiple optima at each generation executed in a single run. On the other hand, the concept of dominance found in animal behavior indicates the level of social interaction among two animals in terms of aggressiveness. Such aggressiveness keeps two or more individuals as distant as possible from one another, where the most dominant individual prevails as the other withdraws. In this paper, the concept of dominance is computationally abstracted in terms of a data structure called “competitive memory” to incorporate multimodal capabilities into the evolutionary operators of the recently proposed Cluster-Chaotic-Optimization (CCO). Under CCO, the competitive memory is implemented as a memory mechanism to efficiently register and maintain all possible optimal values within a single execution of the algorithm. The performance of the proposed method is numerically compared against several multimodal schemes over a set of benchmark functions. The experimental study suggests that the proposed approach outperforms its competitors in terms of robustness, quality, and precision.

In the field of image processing, there are several problems where an efficient search of the solutions has to be performed within a complex search domain to find an optimal solution. Multi-thresholding which is a very important image segmentation technique is one of them. The multi-thresholding problem is simply an exponential combinatorial optimization process which traditionally is formulated based on complex objective function criterion which can be solved using only nondeterministic methods. Under such circumstances, there is also no unique measurement which quantitatively judges the quality of a given segmented image. Therefore, researchers are solving those issues by using Nature-Inspired Optimization Algorithms (NIOAs) as alternative methodologies for the multi-thresholding problem. This study presents an up-to-date review on all most important NIOAs employed in multi-thresholding based image segmentation domain. The key issues which are involved during the formulation of NIOAs based image multi-thresholding models are also discussed here.

This paper presents an efficient image encryption scheme based on permutation followed by diffusion, where both of these phases use 2-d Sine logistic modulation map (SLMM) with different initial values. In addition, diffusion uses another map as 1-d Logistic chaotic map (LCM). The initial values of these chaotic maps are obtained from an external key of 64 bytes along with 32-byte hash value from the corresponding plain-image to incorporate plain-text sensitivity. Initially, confusion of the plain-image is implemented by applying row-level and column-level permutations. Then, this permuted image is used for subsequent diffusion, applied on block-level considering block size of 64 bytes. This diffusion process is accomplished by overlaying with chaotic matrix derived from LCM, followed by substitution of those overlaid bytes by DNA encoding along with SLMM to attain an encrypted image with an entropy nearly 8. Furthermore, all the chaotic values generated from the aforementioned maps are highly sensitive on the key as well as on the plain-image. This scheme is thoroughly verified on different sized plain-images with modern statistical analyses to prove the robustness of this scheme. Eventually, comparison with other schemes reinforces its competence and suitability to implement it in real-time system.

Deep Learning-based algorithms have shown that they are the best at segmenting, processing, detecting, and classifying medical images. U-Net is a famous Deep Learning (DL) approach for these applications. U-Net conducts four down-samplings before the concatenate process, resulting in low resolution. The dense U-Net design overcomes this problem, but the huge semantic gap between low-level and high-level down-sampling and up-sampling features remains a key concern. This work designed Sharp Dense U-Net, an improved U-Net architecture for nucleus segmentation, to solve these constraints. In the down-sampling path, dense and transition operations are used instead of max pooling and convolution to extract more informative information. In the up-sampling path, a new up-sampling layer, merging, and dense blocks reconstitute high-resolution images. Sharpening spatial filters take the place of skip connections to stop feature mismatches between the decoder and encoder paths. The proposed model is trained on the combined dataset and obtains dice coefficients, IoU, and accuracy of 0.6856, 0.5248, and 84.49, respectively. For nucleus segmentation from histopathology images, the Sharp Dense U-Net model is better than the U-Net, Dense U-Net, SCPP-Net, and LiverNet.

Plant image analysis is a significant tool for plant phenotyping. Image analysis has been used to assess plant trails, forecast plant growth, and offer geographical information about images. The area segmentation and counting of the leaf is a major component of plant phenotyping, which can be used to measure the growth of the plant. Therefore, this paper developed a convolutional neural network-based leaf counting model called LC-Net. The original plant image and segmented leaf parts are fed as input because the segmented leaf part provides additional information to the proposed LC-Net. The well-known SegNet model has been utilised to obtain segmented leaf parts because it outperforms four other popular Convolutional Neural Network (CNN) models, namely DeepLab V3+, Fast FCN with Pyramid Scene Parsing (PSP), U-Net, and Refine Net. The proposed LC-Net is compared to the other recent CNN-based leaf counting models over the combined Computer Vision Problems in Plant Phenotyping (CVPPP) and KOMATSUNA datasets. The subjective and numerical evaluations of the experimental results demonstrate the superiority of the LC-Net to other tested models.

Cancer is one of the most critical disease. In particular, Leukemia is the most common type of cancer which produces an excessive quantity of leucocytes, replacing normal blood cells. Early detection of leucocytes cells can save human life. Recently, researchers have contributed to the development of computer assisted pathology techniques to automatically detect cancer at early stage. Commonly, assisted pathology systems are based on artificial vision techniques to identify cancer cells in the human body. Blood image segmentation techniques for Leukemia have been proposed based on automatic thresholding schemes involving traditional clustering methods. However, traditional clustering methods are sensitive to initial cluster positions, where the incorrect centering values results into false positive cancer diagnosis. On the other hand, Nature-Inspired Optimization Algorithms (NIOA) are stochastic search methods for finding the optimal solution for complex multimodal functions where traditional optimization approaches are not suitable to operate. Since blood image segmentation is considered as a complex computational task, NIOA methods yield an interesting alternative to proper blood cell segmentation. In this paper, the Stochastic Fractal Search (SFS) algorithm is implemented in order to provide non-false positive segmented outcomes for Leukemia identification. In the experimental study, the proposed approach is compared against traditional clustering methods as well as some NIOAs techniques. The numerical results indicate that SFS, provide superior results in terms of accuracy, time complexity, and quality parameters.

Flower pollination algorithm (FPA) is a new bio-inspired optimization algorithm, which has shown an effective performance on solving many optimization problems. However, the effectiveness of FPA significantly depends on the balance achieved by the exploration and exploitation evolutionary stages. Since purely exploration procedure promotes non-accurate solutions, meanwhile, purely exploitation operation promotes sub-optimal solutions in the presence of multiple optima. In this study, three global search and two local search strategies have been designed to improve balance among evolutionary stages, increasing the efficiency and robustness of the original FPA methodology. Additionally, some parameter adaptation techniques are also incorporated in the proposed methodology. The modified FPA has been successfully applied for histopathological image segmentation problem. The experimental and computational effort results indicate its effectiveness over existing swarm intelligence algorithms and machine learning methods.

Partitional clustering-based image segmentation is one of the most significant approaches. K -means is the conventional clustering techniques even though very sensitive to noise and easy convergences to local optima depending on the initial cluster centers. In addition, the computational time of K -means algorithm is also very high due to the repetitive distance calculation between pixels and cluster centers. In order to solve these problems, this paper presents a Histogram-based Fast and Robust Crisp Image Clustering (HFRCIC) technique. Local spatial information is often introduced to an objective function to improve the noise robustness of the clustering technique. At first, the local spatial information has been introduced into HFRCIC by incorporating morphological reconstruction which assures noise-immunity as well as image detail-preservation. Then clustering has been executed depending on gray levels in the place of pixels of the image. As result, the execution time is low as the number of gray levels is usually much smaller than the number of pixels in the image. Due to the random initialization of centers, HFRCIC easily stuck into local optima as HFRCIC is greedy in nature and an efficient local optimizer. Therefore, Nature-Inspired Optimization Algorithms (NIOA) are successfully employed to overcome the problem within reasonable computational time. Here, Stochastic Fractal Search (SFS) has been employed to find the optimal cluster centers. The experimental study has been performed over synthetic images, real-world images and white the gray level conversion of RGB imaged for white blood cell (WBC) segmentation. Visual and numerical results indicate the superiority of the proposed HFRCIC with SFS(HFRCIC-SFS) over state-of-the-art image segmentation algorithms and NIOA-based crisp image clustering techniques.

Pathological color image segmentation is an exigent procedure due to the existence of imperceptibly correlated, and indistinct multiple regions of concern. Multi-level thresholding has been introduced as one of the most significant image segmentation procedures for pathological analysis. However, finding an optimal set of threshold values is an extremely time-consuming task, and crucially depends on the objective function criterion. In order to solve these problems, this paper presents a multi-level hematology color image thresholding approach with the assistance of a two-stage strategy called Eagle Strategy coupled with Whale Optimization Algorithm (ES-WOA), analyzing the performance over five well-known objective functions, namely; Kapur’s entropy, Fuzzy entropy, Tsallis’ entropy, Otsu’s method, and Cross entropy. A rigorous comparative study is performed among classical WOA and existing eagle strategy based optimization algorithms, considering a set of hematology color images, and common performance indexes evaluated by each objective function tested. Experimental results indicate that proposed ES-WOA in combination with Tsallis’ entropy outperforms the rest of tested algorithms in terms of computational effort, image segmentation quality, and robustness. For example, ES-WOA with Tsallis’ produces segmented images with average Peak Signal-to-Noise Ratio (PSNR) values 16.0371, 17.9975, 21.1353, and 23.0759 for threshold values 2, 3, 4, and 5, respectively, which are superior to other tested methods. Additionally, the numerical results are statistically validated using a nonparametric approach to eliminate the random effect in the obtained results.

Since the beginning of the twenty-first century, the Cuckoo Search (CS) algorithm has emerged as one of the robust, flexible, fast, and easily implementable techniques for the global search to solve many complex problems over continuous spaces. CS operates like other Nature-Inspired Algorithms (NIOA) whose effectiveness significantly depends on the exploration and exploitation phases. CS already proofs its efficiency in solving real-world optimization problems in various application domains. In this study, the author tries to enhance the efficiency of the CS by incorporating six different mutation strategies of Differential Evolution (DE). The performance of the proposed CS variants has been investigated over Multi-level thresholding based image segmentation field as it is considered one of the dominant image segmentation techniques of the recent era. It is known that computation of the optimal set of thresholds is significantly influenced by the considered objective function, and it can be trapped into local optima. On the other hand, the computational time of Multi-level thresholding increases exponentially when the number of threshold points increases. To overcome these problems, this study introduces CS variants over this segmentation field, where Masi entropy is maximized to find the optimal threshold points. The experiment has been conducted on various color pathology images. The results of such a comparative study provide valuable insight and information to develop efficient CS variants using optimal or adaptive mutation strategies of DE.