Unsupervised Image Segmentation Algorithm Research Articles

Ensemble CART surrogate-assisted automatic multi-objective rough fuzzy clustering algorithm for unsupervised image segmentation

Multi-objective clustering algorithms (MOCAs) are popular in unsupervised image segmentation due to their merit of meeting multiple segmentation requirements and the prospect of automatically estimating the number of clusters. However, most of them suffer from high time costs and are easily to be influenced by the uncertainty when handling real complex images. To address these issues, we propose an ensemble classification and regression tree (CART) surrogate-assisted automatic multi-objective rough fuzzy clustering (ECS-AMRFC) algorithm for unsupervised image segmentation. Firstly, a cluster medoid-based encoding scheme is employed to represent solutions with different number of clusters and meanwhile lessen the length of encoding. Then, we design an ensemble CART as the surrogate model to significantly reduce the computational burden. Moreover, a surrogate model management strategy is proposed to accelerate the optimization and enhance the quality of surrogate modeling. To handle the uncertainty in data, we extend the rough fuzzy clustering into MOCAs and construct three complementary objective functions to seek proper cluster medoids from multiple perspectives. In addition, the Gaussian kernel is introduced into the objective functions to handle image pixels that cannot separate linearly in the feature space. Finally, a kernelized rough fuzzy clustering validity index is defined to automatically select the optimal solution with no requirements of any prior knowledge. Experiments show that ECS-AMRFC not only identifies appropriate number of clusters on different kinds of images, but also obtains better segmentation results than state-of-the-art rough fuzzy clustering algorithms and automatic MOCAs.

Unsupervised leaf segmentation in complex backgrounds using mutual information minimization

Leaf segmentation is crucial for plant recognition, especially for tree species identification. In natural environments, leaf segmentation can be very challenging due to the lack of prior information about leaves and the variability of backgrounds. In typical applications, supervised algorithms often require pixel-level annotation of regions, which can be labour-intensive and limited to identifying plant species using pre-labelled samples. On the other hand, traditional unsupervised image segmentation algorithms require specialised parameter tuning for leaf images to achieve optimal results. Therefore, this paper proposes an unsupervised leaf segmentation method that combines mutual information with neural networks to better generalise to unknown samples and adapt to variations in leaf shape and appearance to distinguish and identify different tree species. First, a model combining a Variational Autoencoder (VAE) and a segmentation network is used as a pre-segmenter to obtain dynamic masks. Secondly, the dynamic masks are combined with the segmentation masks generated by the mask generator module to construct the initial mask. Then, the patcher module uses the Mutual Information Minimum (MIM) loss as an optimisation objective to reconstruct independent regions based on this initial mask. The process of obtaining dynamic masks through pre-segmentation is unsupervised, and the entire experimental process does not involve any label information. The experimental method was performed on tree leaf images with a naturally complex background using the publicly available Pl@ntLeaves dataset. The results of the experiment showed that compared to existing excellent methods on this dataset, the IoU (Intersection over Union) index increased by 3.9%.

An unsupervised image segmentation algorithm for coronary angiography

Computer visual systems can rapidly obtain a large amount of data and automatically process them with ease. These characteristics constitute advantages for the application of such systems in the automatic analysis of medical images, as well as in processing technology. The precision of image segmentation, which plays a critical role in computer visual systems, directly affects the quality of processing results. Coronary angiographs feature various background colors, complex patterns, and blurry edges. The image areas containing blood vessels cannot be precisely segmented through regular methods. Therefore, this study proposed an unsupervised learning algorithm that uses regional parameter expansion (RPE). This method was derived from the flood fill algorithm, which can effectively segment image areas containing blood vessels despite a complex background or uneven light and shadow. An optimal cover tree (OCT) algorithm was proposed for the establishment of coronary arteries and the estimation of vessel diameter. Through the region growing method, spanning trees were used to record the cover length of adjacent connections, thereby establishing vessel paths, and the length can be used to track changes in vessel diameter.

A novel approach for unsupervised image segmentation fusion of plant leaves based on G-mutual information

Plant leaf segmentation has a very important role in most plant identification methods. Tree leaves segmentation in images with complex background is very difficult when there is no prior information about the leaves and backgrounds. In practice, the parameters of unsupervised image segmentation algorithms must be set for each image to get the best results. In this paper, to overcome this problem, fusion of the results of five leaf segmentation algorithms (fuzzy c-means, SOM and k-means in various color spaces or different parameters) is applied. To fuse the results of these segmentations, new equations for mutual information (g-mutual information equations) based on the g-calculus are introduced to find the best consensus segmentation. The results of the mentioned primary clustering algorithms are considered as a new feature vector for each pixel. To reduce the time complexity, a fast method is employed using truth table containing different feature vectors. To evaluate this new approach, a leaf image database with natural scenes, taken from Pl@ntLeaves database, is generated to have different positions and orientations. In addition, a widely used database is used to compare the proposed method with other methods. The experimental results presented in this paper show that the use of g-calculus in fusion of image segmentations improves the evaluation parameters.

Natural image segmentation based on mutual information

Natural image segmentation plays an important role in the fields of image processing and computer vision. Image segmentation based on clustering is an important method in unsupervised image segmentation algorithms. But there are two problems with this type of approach. First, feature extraction is generally pixel-based, which results in poor segmentation results and boundary fitting. In order to solve this problem, it is proposed to introduce super pixel to be segmented image preprocessing. Second, the number of partitions is difficult to determine. Aiming at this problem, an energy difference based on mutual information is proposed, which can automatically determine the number of partitions. The experimental results on the standard database show that the proposed algorithm overcomes the above problems and achieves better experimental results.

A study of a clothing image segmentation method in complex conditions using a features fusion model

According to a priori knowledge in complex conditions, this paper proposes an unsupervised image segmentation algorithm to be used for clothing images that combines colour and texture features. First, block truncation encoding is used to divide the traditional three-dimensional colour space into a six-dimensional colour space so that more fine colour features can be obtained. Then, a texture feature based on the improved local binary pattern (LBP) algorithm is designed and used to describe the clothing image with the colour features. After that, according to the statistical appearance law of the object region and background information in the clothing image, a bisection method is proposed for the segmentation operation. Since the image is divided into several subimage blocks, bisection image segmentation will be accomplished more efficiently. The experimental results show that the proposed algorithm can quickly and effectively extract effective clothing regions from complex circumstances without any artificial parameters. The proposed clothing image segmentation method will play an important role in computer vision, machine learning applications, pattern recognition and intelligent systems.

Unsupervised SAR image segmentation based on kernel TMFs with belief propagation

The triplet Markov field (TMF) model has achieved promising results in synthetic aperture radar (SAR) image segmentation. Focusing on the simple likelihood modelling of an SAR image and the effective optimisation of the TMF model, an unsupervised SAR image segmentation algorithm based on kernel TMF with belief propagation is proposed in this study. Instead of complex speckle noise statistical models in a spatial domain, a piecewise constant likelihood model in the kernel mapped space is used in the TMF model by mapping the SAR image data into a higher dimension space via a kernel function. The max-product belief propagation algorithm is used to realise effective optimisation of the proposed kernel TMF model. Experiments on both simulated and real SAR images demonstrate the effectiveness of the proposed algorithm.

Efficient clustering approach for adaptive unsupervised colour image segmentation

This study proposes a clustering-based colour image segmentation approach consisting of a novel initialisation technique. Colour image segmentation transforms image pixels into regions and a prerequisite for image analysis and computer vision applications. Therefore, colour image segmentation is considered one of the most important processes in image understanding and pattern recognition. This study presents an efficient and adaptive unsupervised approach based on bottom-up red–green–blue (RGB) colour histogram search approach to achieve colour image segmentation. Firstly, the RGB histogram is processed through a double-scan procedure to determine significant modes in each histogram. In the next step, each mode is processed through a bottom-up histogram search approach, completing RGB triplet. The RGB triplets are utilised as the cluster centroids, clustering the pixels into regions and producing the final segmented image. The authors proposed method was compared with several other unsupervised image segmentation algorithms with an extensive experiment performed on various image segmentation evaluation benchmarks. Experimental results show that the proposed algorithm outperforms state-of-the-art algorithms both in terms of features integrity and execution speed.

Unsupervised image segmentation using the Deffuant–Weisbuch model from social dynamics

Unsupervised image segmentation algorithms aim at identifying disjoint homogeneous regions in an image and have been subject to considerable attention in the machine vision community. In this paper, a popular theoretical model with its origins in statistical physics and social dynamics, known as the Deffuant–Weisbuch model, is applied to the image segmentation problem. The Deffuant–Weisbuch model has been found to be useful in modelling the evolution of a closed system of interacting agents characterised by their opinions or beliefs, leading to the formation of clusters of agents who share a similar opinion or belief at steady state. In the context of image segmentation, this paper considers a pixel as an agent and its colour property as its opinion, with opinion updates as per the Deffuant–Weisbuch model. Apart from applying the basic model to image segmentation, this paper incorporates adjacency and neighbourhood information in the model, which factors in the local similarity and smoothness properties of images. Convergence is reached when the number of unique pixel opinions, i.e., the number of colour centres, matches the pre-specified number of clusters. Experiments are performed on a set of images from the Berkeley image segmentation dataset, and the results are analysed both qualitatively and quantitatively, which indicate that this simple and intuitive method is promising for image segmentation. To the best of the knowledge of the author, this is the first work where a theoretical model from statistical physics and social dynamics has been successfully applied to image processing.

New quartile-based region merging algorithm for unsupervised image segmentation using color-alone feature

This study concerns the image segmentation problem and the use of a color-alone feature for reducing the system complexity. On the basis of the color-based mathematical morphology method, the similarity measure between neighboring regions can be obtained as the solution of a ranking problem. To avoid the creation of a false color and false segmentation, a hybrid ordering approach was used instead of vectorized and marginal ordering approaches. Ordering methods that use black as the reference color to sort pixels face a problem: the scope of distance measurement is not optimal. To avoid this problem, we present a scheme for selecting a global reference color. Moreover, for determining orders of color vectors, the hue–saturation–intensity color distance was used instead of the Euclidean distance. The aforementioned scheme involves segmentation that is in accord with human visual perception. Quartile analysis indicated that threshold determination for region-merging showed less sensitivity to context variations of images. To evaluate the algorithm, it was experimentally compared with two typical segmentation schemes on the basis of four quantitative indices.

Color Image Segmentation via Improved K-Means Algorithm

Data clustering techniques are often used to segment the real world images. Unsupervised image segmentation algorithms that are based on the clustering suffer from random initialization. There is a need for efficient and effective image segmentation algorithm, which can be used in the computer vision, object recognition, image recognition, or compression. To address these problems, the authors present a density-based initialization scheme to segment the color images. In the kernel density based clustering technique, the data sample is mapped to a high-dimensional space for the effective data classification. The Gaussian kernel is used for the density estimation and for the mapping of sample image into a high- dimensional color space. The proposed initialization scheme for the k-means clustering algorithm can homogenously segment an image into the regions of interest with the capability of avoiding the dead centre and the trapped centre by local minima phenomena. The performance of the experimental result indicates that the proposed approach is more effective, compared to the other existing clustering-based image segmentation algorithms. In the proposed approach, the Berkeley image database has been used for the comparison analysis with the recent clustering-based image segmentation algorithms like k-means++, k-medoids and k-mode.

Bayesian image segmentation fusion

Image segmentation fusion can output a final consensus segmentation which in general is better than those of unsupervised image segmentation algorithms. In this paper, the image segmentation fusion is firstly formalized as a combinatorial optimization problem in terms of information theory. Then a Bayesian image segmentation fusion (BISF) model is proposed for a good consensus segmentation. We treat all the segmentation algorithms (or the same algorithm with different parameters) as new features and the segmentations of algorithms as values of the new features, which simplifies image segmentation fusion problems in computation complexity. Based on this idea, a generative model BISF is designed to sample the segmentation according to the discrete distribution, and the inference for BISF and the corresponding algorithm are illustrated in detail. At last, extensive empirical results demonstrate that BISF significantly outperforms other image segmentation fusion algorithms and the popular image segmentation algorithms or algorithms with different parameters in terms of popular indices.

Unsupervised SAR Image Segmentation Based on Conditional Triplet Markov Fields

Conditional random field (CRF) has been widely used in optical image and remote sensing image segmentation because of the advantage of directly modeling the posterior distribution and capturing arbitrary dependencies among observations. However, for nonstationary SAR images, applications of CRF often fail because of their nonstationary property. The triplet Markov field (TMF) model is well appropriate for nonstationary SAR image processing, owing to the introduction of an auxiliary field which reflects the nonstationarity. Therefore, we introduce an auxiliary field to describe the nonstationarity of the posterior distribution and propose an unsupervised SAR image segmentation algorithm based on a conditional TMF (CTMF) framework which combines the advantages of both CRF and TMF. The proposed CTMF framework explicitly takes into account the nonstationary property of SAR images, directly models the posterior distribution, and considers the interactions among the observed data. Experimental results on real SAR images validate the effectiveness of the algorithm proposed in this letter.

Unsupervised SAR Image Segmentation Based on Triplet Markov Fields With Graph Cuts

The triplet Markov fields (TMF) model is suitable for dealing with nonstationary synthetic aperture radar (SAR) images. Existing optimization approaches for the TMF model cannot balance segmentation accuracy and computational efficiency. Focusing on efficient optimization of the TMF model, we propose an unsupervised SAR image segmentation algorithm based on TMF with graph cuts (GCs) in this letter. Considering the existence of two label fields in the TMF model, an iterative optimization strategy under the criterion of maximum a posteriori is proposed, which iteratively estimates one label field with the other fixed. GCs are is used to find the optimal estimation of each label field. GCs optimization and parameter estimation using iterative conditional estimation perform iteratively, leading to an unsupervised segmentation algorithm. Experiments on simulated and real SAR images demonstrate that the proposed algorithm can obtain accurate segmentation results with reasonable computational cost.

Mutual Information Criterion-Based Optimal Scale Selection for Image Denoising and Segmentation

Scale-spaces play an important role in many computer vision tasks. Automatic scale selection is at the foundation of multi- scale image analysis, but its performance is still very subjective and emp irical. To automatically select the appropriate scale for a particular issue, a scale selection model based on information theory is pr oposed in this paper. The proposed model utilizes mutual information as a measuring criterion of similarity for the optimal scale selectio n in multi-scale analysis, with applications to image denoising and segmentation. Firstly, we focus on the morphological operator based scale selection to image denoising. This technique does not require the prior knowledge of the noise variance and can effectively eliminate the variation of illumination. Secondly, we develop a clustering based unsupervised image segmentation algorithm by recursively pruning the Huffman coding tree. The proposed clustering algorithm can preserve the maximum amount of information at a specific clustering number from the information-theoretical point of view. Finally, for the feasibility of the proposed algorithms, its theor etical properties are analyzed mathematically and its performance is tested by a series of experiments, which demonstrate that it yields the optimal scale for our developed image denoising and segmentation algorithms.

Automated two-dimensional K-means clustering algorithm for unsupervised image segmentation

This paper introduces the Automated Two-Dimensional K-Means (A2DKM) algorithm, a novel unsupervised clustering technique. The proposed technique differs from the conventional clustering techniques because it eliminates the need for users to determine the number of clusters. In addition, A2DKM incorporates local and spatial information of the data into the clustering analysis. A2DKM is qualitatively and quantitatively compared with the conventional clustering algorithms, namely, the K-Means (KM), Fuzzy C-Means (FCM), Moving K-Means (MKM), and Adaptive Fuzzy K-Means (AFKM) algorithms. The A2DKM outperforms these algorithms by producing more homogeneous segmentation results.

A spectral and texture-based unsupervised segmentation algorithm for human settlements land-cover extraction

It is crucial to evaluate human settlements to maintain human-based social development. To accurately extract human settlements land-cover information, this article focuses on the unsupervised image segmentation in high-resolution, remotely sensed imagery. J-based segmentation (JSEG) algorithm can offer good segmentation results, but it is highly dependent on image merging thresholds. In this article, a combined, unsupervised image segmentation algorithm is proposed, in which an initial segmentation result is first produced by JSEG and then the image texture is extracted for later region merging. The experiments on the high-resolution imagery show that, when compared with the results obtained by the original JSEG algorithm and eCognition, the proposed algorithm improves the segmentation accuracy.

Unsupervised Natural Image Segmentation Using Mean Histogram Features

A new histogram feature based natural image segmentation algorithm has been proposed. The proposed scheme uses histogram based new color texture extraction method which inherently combines color texture features rather then explicitly extracting it. A non parametric Bayesean clustering is employed to make the segmentation framework fully unsupervised where no a priori knowledge about the number and types of regions are required. The performance of the proposed method have been demonstrated by various experiments using images of natural scenes. The experimental results indicates that superior segmentation results can be obtained through the proposed unsupervised natural image segmentation algorithm.

Comparative analysis of modern automated algorithms image segmentation

Unsupervised image segmentation algorithms based on-mean clustering, expectation-maximization, mean-shift, normalized graph cut, weighted aggregation, statistical region merging, JSEG, HGS and ROI-SEG are considered. The results of segmentation obtained by mentioned algorithms on textural, satellite and natural images are presented. The analysis of quality and segmentation speed of each algorithm realization is performed

컬러영상 분할기법을 이용한 치아 플라그 영역 검출

In this study, we propose the unsupervised image segmentation algorithm to estimate dental plaque accumulations on digital imaging with methylene blue disclosed plaque. With this aim, RGB color plane is mapped into HSI coordinates and the circular histogram of Hue is reconstructed by applying Otsu’s threshold level. The histogram distribution on Saturation features is also analyzed by maximizing the variance between a plaque candidate and non-plaque one. The dental plaque regions are resolved by applying the composite decision logics based on the threshold level of Hue and Saturation.