Image Threshold Segmentation Research Articles

Automatic multilevel image thresholding segmentation using hybrid bio-inspired algorithm and artificial neural network for histopathology images

Automatic multilevel image thresholding segmentation using hybrid bio-inspired algorithm and artificial neural network for histopathology images

The methods of automatic decoding of agricultural land boundaries

The concept "image boundaries" is proposed to be considered not only as an object of decryption, but also as a direct decryption feature of land plots. The article deals with the theoretical and practical issues of automation of decoding agricultural land based on the selection of their boundaries in digital images. Analysis of ways and methods of decoding in order to select boundaries allows us to conclude about the effectiveness of using image segmentation in the processes of preprocessing and automatic selection of boundaries in a digital image. It is proposed to use the well-known operators of spatial differentiation with subsequent thresholding for image segmentation, such as Roberts, Sobel, and Laplace operators. The visual analysis of the results of digital image processing shows that the most expedient and appropriate way is to use the Laplace operator to solve the problem of identifying land use boundaries. The experimental studies show that the number of selected contours in the image will depend on the measure of the threshold value, which allows the elements to be defined as border points.

Performance analysis of entropy thresholding for successful image segmentation

Performance analysis of entropy thresholding for successful image segmentation

Horizontal and vertical search artificial bee colony for image segmentation of COVID-19 X-ray images

The artificial bee colony algorithm (ABC) has been successfully applied to various optimization problems, but the algorithm still suffers from slow convergence and poor quality of optimal solutions in the optimization process. Therefore, in this paper, an improved ABC (CCABC) based on a horizontal search mechanism and a vertical search mechanism is proposed to improve the algorithm's performance. In addition, this paper also presents a multilevel thresholding image segmentation (MTIS) method based on CCABC to enhance the effectiveness of the multilevel thresholding image segmentation method. To verify the performance of the proposed CCABC algorithm and the performance of the improved image segmentation method. First, this paper demonstrates the performance of the CCABC algorithm itself by comparing CCABC with 15 algorithms of the same type using 30 benchmark functions. Then, this paper uses the improved multi-threshold segmentation method for the segmentation of COVID-19 X-ray images and compares it with other similar plans in detail. Finally, this paper confirms that the incorporation of CCABC in MTIS is very effective by analyzing appropriate evaluation criteria and affirms that the new MTIS method has a strong segmentation performance.

Threshold Segmentation of Magnetic Column Defect Image based on Artificial Fish Swarm Algorithm

Threshold Segmentation of Magnetic Column Defect Image based on Artificial Fish Swarm Algorithm

Identifying the Optimal Threshold for Image Segmentation Using PSO and Its Application to Chronic Wound Assessment

Identifying the Optimal Threshold for Image Segmentation Using PSO and Its Application to Chronic Wound Assessment

RECOGNITION OF OBJECTS WITH THE HELP COMPUTER VISION TECHNOLOGY

Object detection for computer vision is one of the key factors for understanding events. The exact identification of an object against a background where there are a large number of objects of similar shape remains a difficult task today. The military's use of technology to enhance and create vision plays a key role in shaping modern security. Computer vision technologies are used to give safe meaning to everyday sociality, battlefields, and many other areas of society. The article examines the development of military-specific capabilities in the context of the use of computer vision. Object recognition using computer vision technologies is necessary for next-generation military operations management that interacts with the corresponding technologies. Object recognition using computer vision technologies is the basis of most software and artificial intelligence programs. It is predicted that the use of the latest computer vision technologies will increase. Detection of objects is important and necessary in the fields of defense capability, security, military affairs, transport, etc. A study of UAVs was conducted and their limitations were determined. The article presents the image preprocessing algorithm. The image segmentation method is used in the work. Threshold segmentation processes and divides the image into regions according to threshold values. Such a method usually has specific assumptions that depend on the image in question. The fixed threshold method segments the image by setting a custom threshold. This method is usually used in binary images. The formula for determining the label of the area after the marginal transformation for a fixed threshold of image segmentation is given.

Entropy-Based Locally Adaptive Thresholding for Image Segmentation

Entropy-Based Locally Adaptive Thresholding for Image Segmentation

A Multi-Level Thresholding Image Segmentation Method Using Hybrid Arithmetic Optimization and Harris Hawks Optimizer Algorithms

A Multi-Level Thresholding Image Segmentation Method Using Hybrid Arithmetic Optimization and Harris Hawks Optimizer Algorithms

An efficient multilevel thresholding image segmentation method based on the slime mould algorithm with bee foraging mechanism: A real case with lupus nephritis images

To improve the diagnosis of Lupus Nephritis (LN), a multilevel LN image segmentation method is developed in this paper based on an improved slime mould algorithm. The search of the optimal threshold set is key to multilevel thresholding image segmentation (MLTIS). It is well known that swarm-based methods are more efficient than the traditional methods because of the high complexity in finding the optimal threshold, especially when performing image partitioning at high threshold levels. However, swarm-based methods tend to obtain the poor quality of the found segmentation thresholds and fall into local optima during the process of segmentation. Therefore, this paper proposes an ASMA-based MLTIS approach by combining an improved slime mould algorithm (ASMA), where ASMA is mainly implemented by introducing the position update mechanism of the artificial bee colony (ABC) into the SMA. To prove the superiority of the ASMA-based MLTIS method, we first conducted a comparison experiment between ASMA and 11 peers using 30 test functions. The experimental results fully demonstrate that ASMA can obtain high-quality solutions and almost does not suffer from premature convergence. Moreover, using standard images and LN images, we compared the ASMA-based MLTIS method with other peers and evaluated the segmentation results using three evaluation indicators called PSNR, SSIM, and FSIM. The proposed ASMA can be an excellent swarm intelligence optimization method that can maintain a delicate balance during the segmentation process of LN images, and thus the ASMA-based MLTIS method has great potential to be used as an image segmentation method for LN images. The lastest updates for the SMA algorithm are available in https://aliasgharheidari.com/SMA.html.

Discrete fractional-order Caputo method to overcome trapping in local optima: Manta Ray Foraging Optimizer as a case study

Enhancing the exploration and exploitation phases of the metaheuristic (MH) optimization algorithms is the key to avoiding local optima. The Manta ray foraging optimizer is a recently proposed MH optimizer. The MRFO showed a good performance in the simple optimization problems. However, it is trapped into the local optimum in the more elaborated ones due to the original algorithm’s low capability in exploiting the optimal solutions and its convergence. From this principle, in this work, a novel variant of the Manta ray foraging optimizer has been proposed for global optimization problems, engineering design optimization problems, and multi-threshold segmentation. In the proposed approach, the fractional calculus (FC) using Caputo fractional differ-sum operator has been adopted to enhance the manta rays movement in the exploitation phase via utilizing history dependency of FC to boost exploiting the optimal solutions via sharing the past knowledge over the optimization process. Moreover, to avoid premature convergence, the somersault factor has been adaptively tuned. The fractional-order Caputo Manta-Ray Foraging Optimizer (FCMRFO) has been proposed. The proposed algorithm’s sensitivity for the FC coefficients has been tested with ten-dimensional CEC2017 benchmarks. The scalability test of the proposed algorithm has been performed with 30, 50 and 100-dimensional CEC2017. Moreover, CEC2020 benchmarks with dimensions 5 and 20 have been applied for providing an extensive investigation, and the FCMRFO has been compared with recent state-of-the-art algorithms. Through utilizing the non-parametric statistical analysis and ranking test, the FCMRFO confirms its superiority and ability to avoid the local optimum in several cases. For the second part of the study, three constrained engineering design problems have been investigated; then, numerous natural images are applied to appraise the FCMRFO for multilevel threshold image segmentation. By performing several metrics, the FCMRFO proves its quality and efficiency compared to recent well-regarded algorithms in engineering applications and image segmentation.

Enhanced Slime Mould Algorithm for Multilevel Thresholding Image Segmentation Using Entropy Measures.

Image segmentation is a fundamental but essential step in image processing because it dramatically influences posterior image analysis. Multilevel thresholding image segmentation is one of the most popular image segmentation techniques, and many researchers have used meta-heuristic optimization algorithms (MAs) to determine the threshold values. However, MAs have some defects; for example, they are prone to stagnate in local optimal and slow convergence speed. This paper proposes an enhanced slime mould algorithm for global optimization and multilevel thresholding image segmentation, namely ESMA. First, the Levy flight method is used to improve the exploration ability of SMA. Second, quasi opposition-based learning is introduced to enhance the exploitation ability and balance the exploration and exploitation. Then, the superiority of the proposed work ESMA is confirmed concerning the 23 benchmark functions. Afterward, the ESMA is applied in multilevel thresholding image segmentation using minimum cross-entropy as the fitness function. We select eight greyscale images as the benchmark images for testing and compare them with the other classical and state-of-the-art algorithms. Meanwhile, the experimental metrics include the average fitness (mean), standard deviation (Std), peak signal to noise ratio (PSNR), structure similarity index (SSIM), feature similarity index (FSIM), and Wilcoxon rank-sum test, which is utilized to evaluate the quality of segmentation. Experimental results demonstrated that ESMA is superior to other algorithms and can provide higher segmentation accuracy.

A Hybrid Preaching Optimization Algorithm Based on Kapur Entropy for Multilevel Thresholding Color Image Segmentation.

Multilevel thresholding segmentation of color images plays an important role in many fields. The pivotal procedure of this technique is determining the specific threshold of the images. In this paper, a hybrid preaching optimization algorithm (HPOA) for color image segmentation is proposed. Firstly, the evolutionary state strategy is adopted to evaluate the evolutionary factors in each iteration. With the introduction of the evolutionary state, the proposed algorithm has more balanced exploration-exploitation compared with the original POA. Secondly, in order to prevent premature convergence, a randomly occurring time-delay is introduced into HPOA in a distributed manner. The expression of the time-delay is inspired by particle swarm optimization and reflects the history of previous personal optimum and global optimum. To better verify the effectiveness of the proposed method, eight well-known benchmark functions are employed to evaluate HPOA. In the interim, seven state-of-the-art algorithms are utilized to compare with HPOA in the terms of accuracy, convergence, and statistical analysis. On this basis, an excellent multilevel thresholding image segmentation method is proposed in this paper. Finally, to further illustrate the potential, experiments are respectively conducted on three different groups of Berkeley images. The quality of a segmented image is evaluated by an array of metrics including feature similarity index (FSIM), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Kapur entropy values. The experimental results reveal that the proposed method significantly outperforms other algorithms and has remarkable and promising performance for multilevel thresholding color image segmentation.

Recognition Algorithm of Popular Elements of Ethnic Minority Traditional Clothing Based on PCA

Image recognition of ethnic minority costumes is helpful for people to understand, carry forward, and inherit national culture. Taking the minority clothing image as the research object, the image enhancement and threshold segmentation are completed; the principal component features of the minority clothing image are extracted by PCA method; and the image matching degree is obtained according to the principle of minimizing the Euclidean distance. Finally, the calculation process of the PCA method is optimized by a wavelet transform algorithm to realize the recognition of popular elements of minority traditional clothing. The comparative experimental results show that the PCA + BP neural network algorithm is better than the other two recognition algorithms in recognition rate and recognition time.

Defect attention template generation cycleGAN for weakly supervised surface defect segmentation

Surface defect segmentation is very important for the quality inspection of industrial production and is an important pattern recognition problem. Although deep learning (DL) has achieved remarkable results in surface defect segmentation, most of these results have been obtained by using massive images with pixel-level annotations, which are difficult to obtain at industrial sites. This paper proposes a weakly supervised defect segmentation method based on the dynamic templates generated by an improved cycle-consistent generative adversarial network (CycleGAN) trained by image-level annotations. To generate better templates for defects with weak signals, we propose a defect attention module by applying the defect residual for the discriminator to strengthen the elimination of defect regions and suppress changes in the background. A defect cycle-consistent loss is designed by adding structural similarity (SSIM) to the original L1 loss to include the grayscale and structural features; the proposed loss can better model the inner structure of defects. After obtaining the defect-free template, a defect segmentation map can easily be obtained through a simple image comparison and threshold segmentation. Experiments show that the proposed method is both efficient and effective, significantly outperforms other weakly supervised methods, and achieves performance that is comparable or even superior to that of supervised methods on three industrial datasets (intersection over union (IoU) on the DAGM 2007, KSD and CCSD datasets of 78.28%, 59.43%,and 68.83%, respectively). The proposed method can also be employed as a semiautomatic annotation tool combined with active learning.

Improved artificial bee colony algorithm and its application in image threshold segmentation

Improved artificial bee colony algorithm and its application in image threshold segmentation

Real-Time Detection Method for Center and Attitude Precise Positioning of Cross Laser-Pattern

Optical metrology has experienced a fast development in recent years—cross laser-pattern has become a common cooperative measuring marker in optical metrology equipment, such as infrared imaging equipment or visual 3D measurement system. The rapid and accurate extraction of the center point and attitude of the cross-marker image is the first prerequisite to ensure the measurement speed and accuracy. In this paper, a cross laser-pattern is used as a cooperative marker, in view of the high resolution of the cross laser-pattern image in the project and the vulnerability to adverse environmental effects, such as stray light, smoke, water mist and other interference in the environment, resulting in poor contrast, low signal-to-noise ratio (SNR), uneven energy distribution. As a result, a method is proposed to detect the center point and attitude of cross laser-pattern image based on Gaussian fitting and least square fitting. Firstly, the distortion of original image is corrected in real time, the corrected image is smoothed by median filter, and the noise is suppressed while preserving the edge sharpness and detail of the image. In order to adapt to different environments, the maximum inter-class variance method of threshold automatic selection is used to determine the threshold of image segmentation to eliminate the background interference caused by different illumination intensities. To improve the real-time performance of the algorithm, the four cross laser edge pixels are obtained by line search, and then fitted by least square. With the edge lines, the transverse and portrait line of the cross-laser image are separated, then we calculate Gaussian center points of all Gaussian sections of transverse and portrait lines based on Gaussian fitting method, respectively. Based on the traditional line fitting method, the sub-pixel center of the transverse and portrait laser strip images are fitted by removing the Outlying Points, and the center coordinates and attitude information of the cross laser-pattern are calculated by using the center equation of the laser strip, realizing cross laser-pattern center and attitude accurate positioning. The results show that the method is robust, the center positioning accuracy is better than 0.6 pixels, the attitude positioning accuracy is better than ±15” under smoke and water mist environment and the processing speed is better than 0.1 s, which meets the real-time requirements of the project.

A Fuzzy Adaptive Firefly Algorithm for Multilevel Color Image Thresholding Based on Fuzzy Entropy

Multilevel thresholding image segmentation has always been a hot issue of research in last several years since it has a plenty of applications. Traditional exhaustive search method consumes a lot of time for searching the optimal multilevel thresholding, color images contain more information, solving multilevel thresholding will become worse. However, the meta-heuristic search algorithm has unique advantages in solving multilevel threshold values. In this paper, a fuzzy adaptive firefly algorithm (FaFA) is proposed to solve the optimal multilevel thresholding for color images, and the fuzzy Kapur's entropy is considered as its objective function. In the FaFA, a fuzzy logical controller is designed to adjust the control parameters. A total of six satellite remote sensing color images are conducted in the experiments. The performance of the FaFA is compared with FA, BWO, SSA, NaFA and ODFA. Some measure metrics are performed in the experiments. The experimental results show that the FaFA obviously outperforms other five algorithms.

Modified Artificial Ecosystem-Based Optimization for Multilevel Thresholding Image Segmentation

Multilevel thresholding is one of the most effective image segmentation methods, due to its efficiency and easy implementation. This study presents a new multilevel thresholding method based on a modified artificial ecosystem-based optimization (AEO). The differential evolution (DE) is applied to overcome the shortcomings of the original AEO. The main idea of the proposed method, artificial ecosystem-based optimization differential evolution (AEODE), is to employ the operators of the DE as a local search of the AEO to improve the ecosystem of solutions. We used benchmark images to test the performance of the AEODE, and we compared it to several existing approaches. The proposed AEODE achieved a high performance when evaluated by the structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and fitness values. Moreover, the AEODE outperformed the basic version of the AEO concerning SSIM and PSNR by 78% and 82%, respectively, which reserves the best features for each of AEO and DE.

Many-objective multilevel thresholding image segmentation for infrared images of power equipment with boost marine predators algorithm

With the development of power systems, fault diagnosis in infrared images has become increasingly important for ensuring the stability of these systems. In this paper, we propose a multi-objective multilevel threshold image segmentation method based on the boost marine predators algorithm (BMPA) for infrared-image fault diagnosis. As fault points are small, it is difficult to detect the target in an infrared image using existing segmentation methods. To address this, we use 9DKapur as the fitness function and obtain a many-objective optimization problems (MaOPs). Then, we use adaptive weights and opposition-based learning to boost the optimization ability of the MPA and solve the MOP so that a Pareto front is obtained. The DTLZ and WFG test suits are used as benchmarks to evaluate the performance of the BMPA, and electric equipment in infrared images was used to assess the fault-diagnostic ability of the proposed method. The results demonstrate that the BMPA performs better than other optimization algorithms in terms of uniformity measurement, peak signal-to-noise ratio, feature similarity, hypervolume, spacing, and CPU time. On the actual test data, the recall rate and fault detection accuracy of the proposed method were 94.29% and 92.38%, respectively. Insulator faults under various circumstances can be correctly detected in infrared images.