A fuzzy rule-based colour image segmentation algorithm

Fuzzy c-means (FCM) algorithm has been widely used in image segmentation. However, the traditional FCM algorithm does not take into account any image spatial information, which makes it very sensitive to noise. In order to make improvements on the basis of FCM, we proposed a fuzzy entropy clustering image segmentation algorithm based on potential two-dimensional histogram. Firstly, the two-dimensional gray histogram is constructed by using the gray value of image pixels and its local spatial uniform gray value, and the potential function is used to map-the mutual influence between image pixels into the data field, so as to describe the interaction between pixels more accurately. Secondly, the kernel function will be used to map the data to a high dimensional space to complete the linear transformation, this makes the data in the original space linearly indivisible become linearly separable or approximately linearly separable, which overcomes the defect that FCM is not suitable for multiple data distributions in some extent. Finally, the iterative formula of image segmentation is obtained by Lagrange multiplier method. Experimental results show that the proposed algorithm has higher correct segmentation rate and stronger robustness.

Interval type-2 possibilistic fuzzy clustering noisy image segmentation algorithm with adaptive spatial constraints and local feature weighting & clustering weighting

Image segmentation is a classic problem in computer image comprehension and related fields. Up to now, there are not any general and valid partition methods which could satisfy different purposes, especially for medical images such as magnetic resonance images, which often corrupted by multiple imaging artifacts, for example intensity inhomogeneity, noise and partial volume effects. In this paper, we propose an improved fuzzy c-means image segmentation algorithm with more accurate results and faster computation. Considering two voxels with the same intensity belonging to the same tissue, we use q intensity levels instead of n intensity values in the objective function of the fuzzy c-means algorithm, which makes the algorithm clusters much faster since q is much smaller than n. Furthermore, a gain field is incorporate in the objective function to compensate for the inhomogeneity. In addition, we use c-means clustering algorithm to initialize the centroids. This can further accelerate the clustering. The test results show that the proposed algorithm not only gives more accurate results but also makes the computation faster.

The maximum fuzzy entropy algorithm is one of the effective methods of image segmentation, researchers often combine maximum fuzzy entropy and genetic algorithm (GA), but the algorithms have the defects of complexity encoding and unstable search, etc. To improve the algorithms, artificial fish school algorithm (AFSA) is introduced to more rapid optimization of maximum fuzzy entropy, this paper proposes a novel maximum fuzzy entropy image segmentation algorithm based on AFSA (AFSA-based MFEISA). Firstly, the histogram of the image and the probability of each gray level are counted up, and then the multiple threshold integer coding is designed and the maximum fuzzy entropy is converted to the objective function of coding, finally, the maximum fuzzy entropy and its corresponding thresholds are obtained by the improved AFSA and the image is segmented. The experimental results show that the proposed algorithm can achieve better segmentation effect than OTSU algorithm and maximum entropy algorithms, at the same time, it not only has more simple and effective coding scheme and better segmentation effect than the algorithms based on fuzzy entropy and GA, etc, but also it shows better stability and convergence.

The increasing availability of high spatial resolution images provides detailed and up-to-date representations of cities. However, ana-lysis of such digital imagery data using traditional pixel-wise approaches remains a challenge due to the spectral complexity of urban areas. Object-Based Image Analysis (OBIA) is emerging as an alternative method to produce landcover information. Standard OBIA approaches rely on ima-ge segmentation which partitions the image into a set of ’crisp’ non-overlapping image-objects. This step regularly requires significant user-interaction to parameterise a functional segmentation model. This paper proposes fuzzy image segmentation which produces fully overlapping image-regions with indeterminate boundaries that serves as alternative framework for the subsequent image classification. The new method uses three stages: (i) fuzzy image segmentation, (ii) feature analysis, and (iii) defuzzification, that were implemented applying Support Vector Machine (SVM) techniques and using open source software. The new method was tested against a benchmark land-cover classification that applied standard crisp image segmentation. Results show that fuzzy image segmentation can produce good thematic accuracy with little user input. It therefore provides a new and automated technique for producing accurate urban land cover data from high spatial resolution imagery.KeywordsSupport Vector MachineImage SegmentationIndependent Component AnalysisSupport Vector Machine ModelIndependent Component AnalysisThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Brain Magnetic Resonance Imaging (MRI) image segmentation is one of the critical technologies of clinical medicine, and is the basis of three-dimensional reconstruction and downstream analysis between normal tissues and diseased tissues. However, there are various limitations in brain MRI images, such as gray irregularities, noise, and low contrast, reducing the accuracy of the brain MRI images segmentation. In this paper, we propose two optimization solutions for the fuzzy clustering algorithm based on local Gaussian probability fuzzy C-means (LGP-FCM) model and anisotropic weight fuzzy C-means (AW-FCM) model and apply it in brain MRI image segmentation. An FCM clustering algorithm is proposed based on AW-FCM. By introducing the new neighborhood weight calculation method, each point has the weight of anisotropy, effectively overcomes the influence of noise on the image segmentation. In addition, the LGP model is introduced in the objective function of fuzzy clustering, and a fuzzy clustering segmentation algorithm based on LGP-FCM is proposed. A clustering segmentation algorithm of adaptive scale fuzzy LGP model is proposed. The neighborhood scale corresponding to each pixel in the image is automatically estimated, which improves the robustness of the model and achieves the purpose of precise segmentation. Extensive experimental results demonstrate that the proposed LGP-FCM algorithm outperforms comparison algorithms in terms of sensitivity, specificity and accuracy. LGP-FCM can effectively segment the target regions from brain MRI images.

not available

Fuzzy c-means clustering algorithm (FCM) is one of the most widely used methods for image segmentation. In order to overcome the sensitivity of FCM to noise in images, we introduce a novel non local adaptive spatial constraint term, which is defined by using the non local spatial information of pixels, into the objective function of FCM and propose an adaptive non local spatial fuzzy image segmentation algorithm (ANLS_FIS). In this method, the non-local spatial information of each pixel plays a different role in image segmentation. ANLS_FIS can effectively deal with noise while preserving the geometrical edges in the image. Experiments on synthetic and real images, especially magnetic resonance (MR) images, show that ANLS_FIS is more robust than the modified FCM algorithms with local spatial constraint.

Possiblistic-Fuzzy C-Means Clustering Approach for the Segmentation of Satellite Images in HSL Color Space

In order to overcome the poor anti-noise performance of traditional fuzzy C-Means (FCM) algorithm in image segmentation, a novel improved FCM algorithm was proposed in this paper based on Particle Swarm Optimization (PSO) algorithm and Markov Random Field (MRF) model, which can make full use of the global searching ability of PSO and the spatial information integrating ability of MRF for image segmentation. In this algorithm, the image segmentation is converted to a PSO optimization problem, in which the fitness function is set up to containing the spatial information based on the spectral value and the neighboring pixels modeled by MRFs. And segmentation results can be iteratively obtained during the PSO iterations according to the newly designed membership function of FCM in which the spatial information is integrated. The experiments herein reported in this paper illustrate the better performance of this algorithm than the traditional FCM algorithm and the PSO algorithm for image segmentation.

Image segmentation is a crucial step in most computer vision tasks. We propose a new unsupervised fuzzy Bayesian image segmentation method using fuzzy Markov random fields (FMRFs). FRMF is known to provide improved segmentation results when compared to the MRF method. Typically, both hard and fuzzy MRF models have two groups of parameters to be estimated: the MRF parameters and class parameters for each pixel in the image. To this date, these two parameters are treated separately, and estimated in an alternating fashion. In this paper, we develop a new method to estimate the parameters defining the Markovian distribution of the measured data, while performing the data clustering simultaneously. This is made possible by defining estimates of the MRF parameters as functions of the class parameters resulting in a cost function that depends only on the class parameters of each pixel. We apply the conjugate gradient method (CGM) to search for the optimizer of the resulting non-linear cost function. We perform computer simulations to illustrate the proposed method and provide a comparison with some of the commonly used methods.

Fuzzy Superpixel-based Image Segmentation

Possibilistic c-means (PCM) algorithm was proposed to overcome the noise sensitivity of fuzzy c-means (FCM). However, the performance of PCM depends heavily on the initialization, and often deteriorates due to the coincident clustering problem. To overcome these problems, we propose a new hybrid clustering algorithm that incorporates an ACO-based clustering into PCM, namely ACOPCM for noisy image segmentation. Our ACOPCM solves the coincident clustering problem using pre-classified pixel information and provides the near optimal initialization of the number of clusters and their centroids. Experimental results demonstrate that our proposed approach achieves higher segmentation accuracy than PCM and hybrid fuzzy clustering approaches.

As an important classifier, fuzzy c-means clustering technique has been widely used in segmentation of image. It is an adaptive segmentation method for plant disease images. However, it has some uncertain factors, when it is used for specific segmentation problem, that are input parameters value. The input parameters include the feature of the date set, the optimal number of cluster, and the degree of fuzziness. These parameters affect the speed and precision of fuzzy clustering segmentation. In this paper, the optimal choice of parameters in a fuzzy c-means algorithm for segmentation of plant disease image was discussed and investigated. Using the pixels gray and means of neighborhood pixels as input feature data; an adapting the FCM algorithm parameters based on fuzzy partition entropy, fuzzy partition coefficient, and compactness measures was used to choose the optimal cluster number; and experiments was used for choosing the degree of fuzziness. The Results show that the optimal clustering number for disease leaf segmentation problem is 4 and the degree of fuzziness is 2.

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] The possibilistic c-means (PCM) was developed as an extension of the fuzzy c-means (FCM) clustering algorithm by abandoning the membership sum-to-one constraint. In the PCM, each cluster is independent of the other clusters and can be processed separately. Because of this separability, the sequential possibilistic one-mean (SP1M) was proposed to find clusters sequentially by running the possibilistic one-mean (P1M) c times. One critical problem in both PCM and SP1M is how to determine the parameter [subscript]. The sequential possibilistic one-mean with adaptive eta (SP1M-AE) was developed to allow [subscript] to change during iterations. In this thesis, a new dynamic adaptation mechanism for the parameter [subscript] in each cluster is inserted into SP1M. The resultant algorithm, called the sequential possibilistic one-mean with dynamic eta (SP1M-DE) is shown to provide superior performance over PCM, SP1M, and SP1M-AE in determining correct clustering results. In this thesis, the family of the SP1M clustering algorithm is also extended to combine local spatial information in an image. The resultant algorithm, called sequential possibilistic local information one-mean (SPLI1M) is shown to have a better performance on image segmentation over the fuzzy local information c-means (FLICM), the possibilistic local information c-means (PLICM), and the family of SP1M without combing local spatial information in image.