Color Image Segmentation Research Articles

A context sensitive energy thresholding based 3D Otsu function for image segmentation using human learning optimization

In this paper, a novel context-based 3D Otsu algorithm using human learning optimization (HLO) is proposed for multilevel color image segmentation. The performance of 3D Otsu algorithm is reported to be poor while dealing with between-class variances through the aid of three-dimensional histogram. To overcome this problem, the concept of context thresholding has been exploited to derive pixel intensity values and spatial information. The nature of spatial context and histogram of an image is very similar. The use of energy curve for 3D Otsu gives satisfactory results but it is more time-consuming during the process of threshold selection. HLO is a recently developed meta-heuristic optimization algorithm that involves the use of learning operators developed by mimicking human learning mechanisms. In this paper, in order to avoid an exhaustive search to obtain optimal thresholds, HLO is used. Experimental studies reported in this paper demonstrate that the proposed method is better than the histogram-based 1D Otsu, 2D Otsu, and 3D Otsu methods. These claims have been confirmed by comparing fidelity parameters such as mean error (ME), mean squared error (MSE), peak signal-to-noise ratio (PSNR), feature similarity index (FSIM), structure similarity index (SSIM) and entropy.

Oppositional symbiotic organisms search optimization for multilevel thresholding of color image

Selection of optimal threshold is the most crucial issue in threshold-based segmentation. In case of color image, this task is become challenging, because conventional color image segmentation has computational complexity and also it suffers from lack of accuracy. Various techniques such as threshold based, region growing, edge detection, graph cut, pixel classification, neural network, active contour, gray level co-occurrence matrix are proposed so far for image segmentation in the literature. Out of them, threshold-based segmentation is popular for its simplicity. To address the problem of color image segmentation, we propose an enhanced version of metaheuristic optimization algorithm called Opposition based Symbiotic Organisms Search (OSOS) to solve multilevel image thresholding technique for color image segmentation by introducing opposition based learning concepts to accelerate the convergence rate and enhance the performance of standard symbiotic organisms search (SOS). The performance of the proposed OSOS based algorithm is investigated thoroughly and compared with some existing techniques like Cuckoo Search (CS), BAT algorithm (BAT), artificial bee colony (ABC) and particle swarm optimization (PSO). The comparison is made by applying the algorithm to a set of color images taken from a well-known benchmark dataset (Berkeley Segmentation Dataset (BSDS)) and some of the color images collected for the COCO dataset. It is observed from the results that the performance of the OSOS based algorithm is promising with respect to standards SOS and others in terms of the values of objective functions as well as the values of some well-defined quality metrics such as peak signal-to-noise ratio (PSNR), structure similarity index (SSIM) and feature similarity index (FSIM). The results of the proposed algorithm may encourage the scientists and engineers to apply it into pattern recognition problems.

Color image segmentation using proximal classifier and quaternion radial harmonic Fourier moments

Segmentation involves separating an object from the background in a given image. Image segmentation has a variety of applications and has received considerable attention in multimedia application and computer vision. Although numerous approaches have been introduced, image segmentation is still far from being solved due to most of image segmentation algorithms are often so complicated and some unsatisfactory results appear frequently. Therefore, developing a suitable technique of image segmentation is still a challenging problem. In this article, a novel color image segmentation will be introduced based on quaternion radial harmonic Fourier moments (QRHFMs) and proximal classifier. Firstly, the image feature of pixel-level is represented by the accurate and invariant QRHFMs holistically as a vector field, which can describe sufficiently the image pixel information due to take into account the relationship among different color channels. Secondly, the image feature from pixel-level is utilized as the input of the proximal classifier with consistency (PCC), which not only has lower computation time but also has better generalization compared to traditional support vector machines classifiers. Then, we choose the training samples by Tsallis entropy thresholding to train PCC classification model. Finally, the color image is classified by the trained PCC classification model. Our algorithm can make full use of the accurate and robust local image feature, as well the quickness and generalization ability of PCC classifier. A series of experimental results shows that this algorithm has better segmentation performance than the state-of-the-art method from the literature.

An implementation of novel genetic based clustering algorithm for color image segmentation

The color image segmentation is one of most crucial application in image processing. It can apply to medical image segmentation for a brain tumor and skin cancer detection or color object detection on CCTV traffic video image segmentation and also for face recognition, fingerprint recognition etc. The color image segmentation has faced the problem of multidimensionality. The color image is considered in five-dimensional problems, three dimensions in color (RGB) and two dimensions in geometry (luminosity layer and chromaticity layer). In this paper the, L*a*b color space conversion has been used to reduce the one dimensional and geometrically it converts in the array hence the further one dimension has been reduced. The a*b space is clustered using genetic algorithm process, which minimizes the overall distance of the cluster, which is randomly placed at the start of the segmentation process. The segmentation results of this method give clear segments based on the different color and it can be applied to any application.

Color image segmentation based on SLIC and watershed algorithm

In order to overcome the problem of over-segmentation caused by traditional watershed algorithm, a color image segmentation algorithm based on simple linear iterative clustering (SLIC) and watershed algorithm is proposed to achieve an ideal segmentation effect. Firstly, the algorithm calculates the number of super-pixels pre-segmented by image complexity, and uses SLIC to super-pixel segmentation preprocessing of the original image to reduce the redundant information in subsequent processing. Then, an adaptive threshold calculation method is proposed to process the gradient image of the preprocessed image in order to effectively remove noise and obtain more complete contour information. Finally, the watershed segmentation algorithm is used to segment the image extracted by the minimum value marker. Experiments on a large number of images show that the proposed algorithm can effectively suppress the over-segmentation problem caused by the traditional watershed algorithm, and is superior to the traditional algorithm in the comparison of LCE and GCE, and the segmentation quality is improved.

Dragonfly Algorithm with Opposition-Based Learning for Multilevel Thresholding Color Image Segmentation

Multilevel thresholding is a very active research field in image segmentation, and has been successfully used in various applications. However, the computational time will increase exponentially as the number of thresholds increases, and for color images which contain more information this is even worse. To overcome the drawback while maintaining segmentation accuracy, a modified version of dragonfly algorithm (DA) with opposition-based learning (OBLDA) for color image segmentation is proposed in this paper. The opposition-based learning (OBL) strategy simultaneously considers the current solution and the opposite solution, which are symmetrical in the search space. With the introduction of OBL, the proposed algorithm has a faster convergence speed and more balanced exploration–exploitation compared with the original DA. In order to clearly demonstrate the outstanding performance of the OBLDA, the proposed method is compared with seven state-of-the-art meta-heuristic algorithms, through experiments on 10 test images. The optimal threshold values are calculated by the maximization of between-class variance and Kapur’s entropy. Meanwhile, some indicators, including peak signal to noise ratio (PSNR), feature similarity index (FSIM), structure similarity index (SSIM), the average fitness values, standard deviation (STD), and computation time are used as evaluation criteria in the experiments. The promising results reveal that proposed method has the advantages of high accuracy and remarkable stability. Wilcoxon’s rank sum test and Friedman test are also performed to verify the superiority of OBLDA in a statistical way. Furthermore, various satellite images are also included for robustness testing. In conclusion, the OBLDA algorithm is a feasible and effective method for multilevel thresholding color image segmentation.

A novel local contrast fusion-based fuzzy model for color image multilevel thresholding using grasshopper optimization

The segmentation process is considered the significant step of an image processing system due to its extreme inspiration on the subsequent image analysis. Out of various approaches, thresholding is one of the most popular schemes for image segmentation. In segmentation, image pixels are arranged in various regions based on their intensity levels. In this paper, a straightforward and efficient fusion-based fuzzy model for multilevel color image segmentation using grasshopper optimization algorithm (GOA) has been proposed. Thresholding based segmentation lacks accuracy in segmenting the ambiguous images due to their complex characteristics, uncertainties and inherent fuzziness. However, the fuzzy entropy resolves these problems, but it is unable for segmenting at higher levels and also the complexity level for selecting suitable thresholds is high. The selection of metaheuristic GOA reduces this problem by selecting optimal threshold values. Therefore, to increase the quality of the segmented image, a simple and effective multilevel thresholding method is exploited by using the concept of fusion which is based on the local contrast. Experimental outputs demonstrate that fusion-based multilevel thresholding is better than most specific segmentation methods and can be validated by comparing the different numerical parameters. Experiments on standard daily-life color and satellite images are conducted to prove the effectiveness of the proposed scheme.

Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

Field Imaging and Volumetric Reconstruction of Riprap Rock and Large-Sized Aggregates: Algorithms and Application

Riprap rock and large-sized aggregates have been used extensively in geotechnical and hydraulic engineering. They essentially provide erosion control, sediment control, and scour protection. The sustainable and reliable use of riprap materials demands efficient and accurate evaluation of their large particle sizes, shapes, and gradation information at both quarry production lines and construction sites. Traditional methods for assessing riprap geometric properties involve subjective visual inspection and time-consuming hand measurements. As such, achieving the comprehensive in-situ characterization of riprap materials still remains challenging for practitioners and engineers. This paper presents an innovative approach for characterizing the volumetric properties of riprap by establishing a field imaging system associated with newly developed color image segmentation and three-dimensional (3-D) reconstruction algorithms. The field imaging system described in this paper with its algorithms and field application examples is designed to be portable, deployable, and affordable for efficient image acquisition. The robustness and accuracy of the image segmentation and 3-D reconstruction algorithms are validated against ground truth measurements collected in stone quarry sites and compared with state-of-the-practice inspection methods. The imaging-based results show good agreement with the ground truth and provide improved volumetric estimation when compared with currently adopted inspection methods. Based on the findings of this study, the innovative imaging-based system is envisioned for full development to provide convenient, reliable, and sustainable solutions for the onsite Quality Assurance/Quality Control tasks relating to riprap rock and large-sized aggregates.

Angle estimation between plant parts for grasp optimisation in harvest robots

For many robotic harvesting applications, position and angle between plant parts is required to optimally position the end-effector before attempting to approach, grasp and cut the product. A method for estimating the angle between plant parts, e.g. stem and fruit, is presented to support the optimisation of grasp pose for harvest robots. The hypothesis is that from colour images, this angle in the horizontal plane can be accurately derived under unmodified greenhouse conditions. It was hypothesised that the location of a fruit and stem could be inferred in the image plane from sparse semantic segmentations. The paper focussed on 4 sub-tasks for a sweet-pepper harvesting robot. Each task was evaluated under 3 conditions: laboratory, simplified greenhouse and unmodified greenhouse. The requirements for each task were based on the end-effector design that required a 25° positioning accuracy. In Task I, colour image segmentation for classes back-ground, fruit and stem plus wire was performed, meeting the requirement of an intersection-over-union > 0.58. In Task II, the stem pose was estimated from the segmentations. In Task III, centres of the fruit and stem were estimated from the output of previous tasks. Both centre estimations In Tasks II and III met the requirement of 25 pixel accuracy on average. In Task IV, the centres were used to estimate the angle between the fruit and stem, meeting the accuracy requirement of 25° for 73% of the cases. The work impacted on the harvest performance by increasing its success rate from 14% theoretically to 52% in practice under unmodified conditions.

ICQPSO‐based multilevel thresholding scheme applied on colour image segmentation

This study proposes an improved cooperative quantum-behaved particle swarm optimisation (ICQPSO) algorithm to find multiple threshold levels for colour images with multilevel Renyi entropy (MRE). In the proposed method, the context vector of each particle is updated each time dynamically when a cooperation operation is completed with other particles. The improved search ability and optimisation performance of ICQPSO algorithm with MRE (hence called MRE-ICQPSO) extensively investigated with other well known nature-inspired algorithms such as Levi flight-guided firefly, cuckoo search, artificial bee colony, and beta differential evolution. The proposed method is applied to the Berkley segmentation dataset with 300 distinct colour images to show the effective performance of the algorithm in terms of fidelity parameters and computation time.

A Color Image Segmentation Method Based on Region Salient Color and Fuzzy C-Means Algorithm

This paper proposes a color image segmentation method based on region salient color and the fuzzy C-means (FCM) algorithm. The method first uses the convex hull theory based on Harris corner detection to detect the object of the image. Thus, the object and the background can be separated. Then, the quantized color histogram can be studied in the HSV color space. By calculating the number of the peak values of both the object and the background histograms, the quantity of the regional salient colors can be obtained. The quantity is the number of the clustering centroids of FCM algorithm. Finally, the FCM algorithm and the noise correction algorithm can be used in the object and the background, respectively. The obtained segmented image consists of the object and the background segmentation. It proves that the method in this paper is an effective segmentation method based on the experiments made by use of Berkeley segmentation dataset. According to the experimental results, it can be concluded that the proposed algorithm has the highest segmentation accuracy and the shortest computing time among the algorithms mentioned in this paper. The algorithm can achieve high-quality, stable and accurate color image segmentation results.

Improved level set model based on bias information with application to color image segmentation and correction

Compared with gray images, color images provide richer information stored in different channels, which increases the segmentation complexity. In this paper, we integrate the level set method, the split Bregman method with the illumination and reflectance estimation (IRE) model to propose an improved level set model. With the bias field added, the proposed model can jointly segment color images and correct the intensity inhomogeneity by removing the estimated bias fields. The energy functional is given with the level set formulation, which is made up of the weighted length term and the data fitting term. The split Bregman method is employed to minimize the energy functional with special form, so that the algorithm efficiency is significantly improved. Various types of color medical and natural images are segmented and corrected by the proposed model. Experimental results demonstrate that our model has a satisfactory application in segmenting and correcting color images. Comparison results with the IRE model validate that our model is superior to the IRE model in terms of segmentation and correction. Research on parameter sensitivity illustrates that our model is not sensitive to most parameters such that the parameters can be chosen flexibly. Besides, our model is robust to noises and initial contours.

Spatial context cross entropy function based multilevel image segmentation using multi-verse optimizer

In this paper, a context-sensitive energy curve based cross-entropy method for multilevel color image segmentation is proposed. In thresholding approaches, pixels are arranged in various regions based on their intensity level. The main challenge generally faced in multilevel thresholding is the selection of best threshold values for the pixel division. However, the combination of the energy curve and the minimum cross entropy (Energy-MCE) scheme provides appropriate thresholds for a multilevel approach, but the computational cost for selecting optimal thresholds is high. Therefore, the selection of meta-heuristic optimization algorithms reduces this cost and generates optimal thresholds. A multi-verse optimizer (MVO) algorithm based on Energy-MCE thresholding approach is proposed to search the accurate and near-optimal thresholds for segmentation. Tests on natural images showed that the proposed method achieves better performance than the well-known optimization techniques in many challenging cases or images, such as identifying weak objects and revealing fine structures of complex objects while the added computational cost is minimal.

Masi Entropy for Satellite Color Image Segmentation Using Tournament-Based Lévy Multiverse Optimization Algorithm

A novel multilevel threshold segmentation method for color satellite images based on Masi entropy is proposed in this paper. Lévy multiverse optimization algorithm (LMVO) has a strong advantage over the traditional multiverse optimization algorithm (MVO) in finding the optimal solution for the segmentation in the three channels of an RGB image. As the work advancement introduces a Lévy multiverse optimization algorithm which uses tournament selection instead of roulette wheel selection, and updates some formulas in the algorithm with mutation factor. Then, the proposal is called TLMVO, and another advantage is that the population diversity of the algorithm in the latest iterations is maintained. The Masi entropy is used as an application and combined with the improved TLMVO algorithm for satellite color image segmentation. Masi entropy combines the additivity of Renyi entropy and the non-extensibility of Tsallis entropy. By increasing the number of thesholds, the quality of segmenttion becomes better, then the dimensionality of the problem also increases. Fitness function value, average CPU running time, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Feature Similarity Index (FSIM) were used to evaluate the segmentation results. Further statistical evaluation was given by Wilcoxon's rank sum test and Friedman test. The experimental results show that the TLMVO algorithm has wide adaptability to high-dimensional optimization problems, and has obvious advantages in objective function value, image quality detection, convergence performance and robustness.

A Chaotic Electromagnetic Field Optimization Algorithm Based on Fuzzy Entropy for Multilevel Thresholding Color Image Segmentation.

Multilevel thresholding segmentation of color images is an important technology in various applications which has received more attention in recent years. The process of determining the optimal threshold values in the case of traditional methods is time-consuming. In order to mitigate the above problem, meta-heuristic algorithms have been employed in this field for searching the optima during the past few years. In this paper, an effective technique of Electromagnetic Field Optimization (EFO) algorithm based on a fuzzy entropy criterion is proposed, and in addition, a novel chaotic strategy is embedded into EFO to develop a new algorithm named CEFO. To evaluate the robustness of the proposed algorithm, other competitive algorithms such as Artificial Bee Colony (ABC), Bat Algorithm (BA), Wind Driven Optimization (WDO), and Bird Swarm Algorithm (BSA) are compared using fuzzy entropy as the fitness function. Furthermore, the proposed segmentation method is also compared with the most widely used approaches of Otsu’s variance and Kapur’s entropy to verify its segmentation accuracy and efficiency. Experiments are conducted on ten Berkeley benchmark images and the simulation results are presented in terms of peak signal to noise ratio (PSNR), mean structural similarity (MSSIM), feature similarity (FSIM), and computational time (CPU Time) at different threshold levels of 4, 6, 8, and 10 for each test image. A series of experiments can significantly demonstrate the superior performance of the proposed technique, which can deal with multilevel thresholding color image segmentation excellently.

Simultaneous segmentation and correction model for color medical and natural images with intensity inhomogeneity

In this paper, a new level set formulation that can simultaneously segment and correct color images is proposed by combining the illumination and reflectance estimation (IRE) model, the level set method and the split Bregman method. The advantages of our model are mainly summarized in three aspects. First, our model can effectively extract the intensity change information in the images, regarded as the bias field. Based on the accurate segmentation results, our model can correct the inhomogeneous color images by removing the estimated bias field from the original images. Second, the application of the split Bregman method accelerates the iterative process and computational speed, making our model more efficient. Third, the use of the edge detection function in the energy functional makes it easier for our model to detect the target boundary. Perfectly absorbing the above three advantages, our model is applied to segment color medical and natural images with intensity inhomogeneity. Experimental results demonstrate that our model can accurately segment color images and get satisfactory correction images with intensity homogeneity. In addition, numerical comparison results further indicate that the performance of our model for segmentation and correction is significantly superior to the IRE model.

Color Image Segmentation using Region Growth and Merge Improved Technique

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Color Image Segmentation of Seed Images Based on Self-Organizing Maps (SOM) Neural Network

This paper presents a threshold color image segmentation methodology based on Self-Organizing Maps (SOM) Neural Network. The objective of segmentation methodology is to determine the minimum number of color features in six seed lines ("nh1", "nh2", "nh3", "nh4", "nh5" y "nh6") of seed castor (Ricinus comunnis L.) images for future seed characterization. Seed castor lines are characterized for pigmentation regions that not allow an optimum segmentation process. In some cases, seed pigmentation regions are similar to background make difficult their segmentation characterization. Methodology proposes to segment the seed image in a SOM-based idea in an increasing way until to some of SOM neuron not have allocated none of the image pixels. Several experiments were carried out with others two standard test images ("House" and "Girl") and results are presented both visual and numerical way.

Can We Accurately Identify Peritoneal Metastases Based on Their Appearance? An Assessment of the Current Practice of Intraoperative Gastrointestinal Cancer Staging.

Peritoneal lesions are common findings during operative abdominal cancer staging. The decision to perform biopsy is made subjectively by the surgeon, a practice the authors hypothesized to be imprecise. This study aimed to describe optical characteristics differentiating benign peritoneal lesions fromperitoneal metastases. The study evaluated laparoscopic images of 87 consecutive peritoneal lesions biopsied during staging laparoscopies for gastrointestinal malignancies from 2014 to 2017. A blinded survey assessing these lesions was completed by 10 oncologic surgeons. Three senior investigators categorized optical features of the lesions. Computer-aided digital image processing and machine learning was used to classify the lesions. Of the 87 lesions, 28 (32%) were metastases. Onexpert survey, surgeons on the average misidentified 36 ± 19% of metastases. Multivariate analysis identified degree of nodularity, border transition, and degree of transparency as independent predictors of metastases (each p < 0.03), with an area under the receiver operating characteristics curve (AUC) of 0.82 (95% confidence interval [CI], 0.72-0.91). Image processing demonstrated no difference using image color segmentation, but showed a difference in gradient magnitude between benign andmetastatic lesions (AUC, 0.66; 95% CI 0.54-0.78; p = 0.02). Machine learning using a neural network with a tenfold cross-validation obtained an AUC of only 0.47. To date, neither experienced oncologic surgeons nor computerized image analysis can differentiateperitoneal metastases from benign peritoneal lesionswith an accuracy that is clinically acceptable. Although certain features correlate with the presence of metastases, a substantial overlap in optical appearance exists between benign and metastatic peritoneal lesions. Therefore, this study suggested the need to perform biopsy for all peritoneal lesions during operative staging, or at least to lower the threshold significantly.