Existing Segmentation Algorithms Research Articles

A Local Search-Based GeneSIS algorithm for the Segmentation and Classification of Remote-Sensing Images

A local search-based version of the so-called genetic sequential image segmentation (GeneSIS) algorithm is presented in this paper, for the classification of remotely sensed images. The new method combines the properties of the GeneSIS framework with the principles of the region growing segmentation algorithms. Localized GeneSIS operates on a fine-segmented image obtained after preliminary watershed transformation. Segmentation proceeds by iterative expansions emanating from object cores, i.e., connected components of marked watersheds. At each expansion trial, the process involves three successively performed operations: 1) generation of the object’s neighborhood to a specified order; 2) local exploration of the neighborhood through an evolutionary algorithm to identify the best expansion to be merged; and 3) rearrangement of the object neighborhoods. We propose two priority strategies for the selection of the objects to be expanded and two different modes of operation performing either supervised or semisupervised segmentation of the image. The combination of the priority strategies and segmentation modes lead to four different implementations of localized GeneSIS. Due to the local search approach adopted here, the resulting algorithms have considerably lower execution times, while at the same time, they provide comparable classification accuracies compared to those produced by previous GeneSIS variants. Experimental analysis is conducted using a hyperspectral forest image, a multispectral agricultural image, and the Pavia Centre image over an urban area. Comparative results are also provided with existing segmentation algorithms.

Multi-resolution, pattern-based segmentation of very large raster datasets

GIScience 2016 Short Paper Proceedings Multi-resolution, pattern-based segmentation of very large raster datasets J. Jasiewicz 1,2 , J. Niesterowicz 1 , T. F. Stepinski 1 Space Infromatics Lab, University of Cincinnati, 401 Braunstein Hall, Cincinnati, OH 45221-0131, US Email: {niestejk; stepintz}@mail.uc.edu Instititute of Geoecology and Geoinformation, Adam Mickiewicz University, Dziegielowa 27, Poznan, Poland Email: jarekj@amu.edu.pl Abstract We present an algorithm which efficiently segments very large categorical rasters based on patterns of their categories. It operates on a grid of motifels – square blocks of raster cells representing a local pattern. Our algorithm is based on the seeded region growing principle but it uses a novel grid topology and seeds stack with individual thresholds. It has a single free parameter – the spatial scale of a pattern. Algorithm was proven to be robust on land cover data, topographic landforms data, and high resolution color-quantized RGB images. We present a multi-scaled segmentation of NLCD2011 as an example. Potential applications of the new algorithm include ecology, geomorphology, pedology, forestry, agriculture, and urban studies. 1. Introduction Segmentation is the process of partitioning a raster dataset into multiple homogeneous segments. The goal of segmentation is to spatially generalize a raster so it provides more insight and is easier to analyze. The bulk of the existing work (Zhang et al. 2008) has focused on segmentation of images of relatively small scenes. However, segmentation of datasets that originated from remote sensing and cover large, continental or even global-scale areas, are also important, but existing segmentation algorithms are ineffective for such large datasets and the custom algorithms are lacking. Examples of such datasets are the National Land Cover Dataset (NLCD), which covers the conterminous US (CONUS) with the resolution of 30 m, or the SRTM-based DEM, which has a world-wide extent at 90 m resolution. Segmentation of NLCD could yield landscape types – precursors to ecoregions, and segmentation of world-wide DEM could delineate physiographic regions. In this paper we describe a segmentation algorithm especially designed for very large rasters. Specificities of such datastes are as follows. (1) They are the mosaics of multiple datasets, thus it is better to segment a secondary product of uniform quality (for example, a land cover) rather than a montage of primary data of variable quality (for example, a montage of Landsat scenes). (2) They are large; for example, the NLCD consists of ~8 billion cells and has the size of ~16 GB. (3) The goal of the segmentation is to identify regions characterized by patterns which are homogeneous on the scale that is large in comparison to the resolution of the raster, since the need for pattern-based segmentation. To deal with a large size of the input the proposed algorithm is based on the concept of Complex Object-Based Image Analysis (COBIA) (Vatsavai 2013, Stepinski et al. 2015). In COBIA the

An improved intuitionistic fuzzy c-means clustering algorithm incorporating local information for brain image segmentation

The segmentation of brain magnetic resonance (MR) images plays an important role in the computer-aided diagnosis and clinical research. However, due to presence of noise and uncertainty on the boundary between different tissues in the brain image, the segmentation of brain image is a challenging task. Many variants of standard fuzzy c-means (FCM) algorithm have been proposed to handle the noise. Intuitionistic fuzzy c-means (IFCM) algorithm, one of the variants of FCM, is found suitable for image segmentation. It incorporates the advantage of intuitionistic fuzzy sets theory. The IFCM successfully handles the uncertainty but it is sensitive to noise as it does not incorporate any local spatial information. In this paper, we have presented a novel approach, named an improved intuitionistic fuzzy c-means (IIFCM), which considers the local spatial information in an intuitionistic fuzzy way. The IIFCM preserves the image details, is insensitive to noise, and is free of requirement of any parameter tuning. The obtained segmentation results on synthetic square image, real and simulated MRI brain image demonstrate the efficacy of the IIFCM algorithm and superior performance in comparison to existing segmentation methods. A nonparametric statistical analysis is also carried out to show the significant performance of the IIFCM algorithm in comparison to other existing segmentation algorithms.

Improved 3D image segmentation for X-ray tomographic analysis of packed particle beds

Although High Resolution X-ray Micro Tomography (HRXMT) has been developed in the past years for the 3D analysis of multiphase mineral particles in packed particle beds, image analysis of fine and/or high-density/high atomic number particles has been limited by existing segmentation algorithms. In this regard, a feature-based segmentation algorithm has been developed and demonstrated to provide a more accurate image processing method for the analysis of such multiphase particle populations. Based on this improved segmentation algorithm, image analyses of packed particle bed samples were compared to segmentation by traditional 3D watershed segmentation. Also, calculation of particle number using optical microscopy, together with a digital camera, was accomplished to validate feature-based segmentation. Detailed procedures and results for sample preparation, image analysis and validation are presented and discussed.

Segmentation of Lung Nodules in CT Scan Data

Developing an effective computer-aided diagnosis (CAD) system for lung cancer is of great clinical importance and can increase the patient's chance of survival. For this reason, CAD systems for lung cancer have been investigated in a huge number of research studies. Several studies have shown the feasibility and robustness of automated matching of corresponding nodule pairs between follow up examinations. Different image pre-processing and segmentation techniques are used in various research sides to segment different tumors or ulcers from different images. This paper aims to make a review on the existing segmentation algorithms used for CT images of pulmonary nodules and presents a study of the existing methods on automated lung nodule detection. It provides a comparison of the performance of the existing approaches in regards to effective domain results.

BIOMETRIC PERSONAL IDENTIFICATION ON 2D WAVELET TRANSFORM AND CHI-SQUARED MODEL

Iris recognition system consists of image acquisition, iris preprocessing, iris segmentation and feature extraction with comparism (matching) stages. The biometric based personal identification using iris requires accurate iris segmentation for successful identification or recognition. Recently, several researchers have implemented various methods for segmentation of boundaries which will require a modification of some of the existing segmentation algorithms for their proper recognition. Therefore, this research presents a 2D Wavelet Transform and Chi-squared model for iris features extraction and recognition. Circular Hough Transform was used for the segmentation of the iris image. The system localizes the circular iris and pupil region and removes the occluding eyelids and eyelashes. The extracted iris region is normalized using Daugman’s rubber sheet model into a rectangular block with constant dimensions to account for imaging inconsistencies. Finally, the phase data (iris signature) from the 2D wavelet transform data is extracted, forming the biometric template. The chi-squared distance is employed for classification of iris templates and recognition. Implementing this model can enhance identification. Based on the designed system, an FAR (False Acceptances ratio) of 0.00 and an FRR (False Rejection Ratio) of 0.896 was achieved.

DiameterJ: A validated open source nanofiber diameter measurement tool

Despite the growing use of nanofiber scaffolds for tissue engineering applications, there is not a validated, readily available, free solution for rapid, automated analysis of nanofiber diameter from scanning electron microscope (SEM) micrographs. Thus, the goal of this study was to create a user friendly ImageJ/FIJI plugin that would analyze SEM micrographs of nanofibers to determine nanofiber diameter on a desktop computer within 60 s. Additional design goals included 1) compatibility with a variety of existing segmentation algorithms, and 2) an open source code to enable further improvement of the plugin. Using existing algorithms for centerline determination, Euclidean distance transforms and a novel pixel transformation technique, a plugin called “DiameterJ” was created for ImageJ/FIJI. The plugin was validated using 1) digital synthetic images of white lines on a black background and 2) SEM images of nominally monodispersed steel wires of known diameters. DiameterJ analyzed SEM micrographs in 20 s, produced diameters not statistically different from known values, was over 10-times closer to known diameter values than other open source software, provided hundreds of times the sampling of manual measurement, and was hundreds of times faster than manual assessment of nanofiber diameter. DiameterJ enables users to rapidly and thoroughly determine the structural features of nanofiber scaffolds and could potentially allow new insights to be formed into fiber diameter distribution and cell response.

Connectivity-Based Segmentation in Large-Scale 2-D/3-D Sensor Networks: Algorithm and Applications

Efficient sensor network design requires a full understanding of the geometric environment in which sensor nodes are deployed. In practice, a large-scale sensor network often has a complex and irregular topology, possibly containing obstacles/holes. Convex network partitioning, also known as convex segmentation, is a technique to divide a network into convex regions in which traditional algorithms designed for a simple network geometry can be applied. Existing segmentation algorithms heavily depend on concave node detection, or sink extraction from the median axis/skeleton, resulting in sensitivity of performance to network boundary noise. Furthermore, since they rely on the network's 2-D geometric properties, they do not work for 3-D cases. This paper presents a novel segmentation approach based on Morse function, bringing together the notions of convex components and the Reeb graph of a network. The segmentation is realized by a distributed and scalable algorithm, named CONSEL, for CONnectivity-based SEgmentation in Large-scale 2-D/3-D sensor networks. In CONSEL, several boundary nodes first flood the network to construct the Reeb graph. The ordinary nodes then compute mutex pairs locally, generating a coarse segmentation. Next, neighboring regions that are not mutex pairs are merged together. Finally, by ignoring mutex pairs that lead to small concavity, we provide an approximate convex decomposition. CONSEL has a number of advantages over previous solutions: 1) it works for both 2-D and 3-D sensor networks; 2) it uses merely network connectivity information; 3) it guarantees a bound for the generated regions' deviation from convexity. We further propose to integrate network segmentation with existing applications that are oriented to simple network geometry. Extensive simulations show the efficacy of CONSEL in segmenting networks and in improving the performance of two applications: geographic routing and connectivity-based localization.

A new algorithm for segmentation of ultrafast X-ray tomographed gas–liquid flows

The ultrafast electron beam X-ray computed tomography was developed during the last years to obtain detailed data on two-phase flows. In a recent study we investigated different gas–liquid flow regimes in a vertical pipe at the Transient Two-phase Flow test facility (TOPFLOW). The study includes experiments on gas–liquid flows with varied superficial velocities for both phases and different flow directions. The obtained data is required for understanding fundamental physics of two-phase flow phenomena and for the development and validation of CFD codes.To extract quantitative data from the reconstructed three-dimensional data array, a new segmentation algorithm was developed, due the results of existing segmentation algorithms aren't satisfyingly. The originality of this new algorithm bases on a stepwise creation of new bubbles using pixel agglomeration in shrinking steps without defining markers or starting points. The results were compared with threshold and gradient methods using two different bubble phantoms and real two-phase flow measurements. The new algorithm shows the best qualitative and quantitative results.

Semisupervised synthetic aperture radar image segmentation with multilayer superpixels

Image segmentation plays a significant role in synthetic aperture radar (SAR) image processing. However, SAR image segmentation is challenging due to speckle. We propose a semisupervised bipartite graph method for segmentation of an SAR image. First, the multilayer over-segmentation of the SAR image, referred to as superpixels, is computed using existing segmentation algorithms. Second, an unbalanced bipartite graph is constructed in which the correlation between pixels is replaced by the texture similarity between superpixels, to reduce the dimension of the edge matrix. To also improve efficiency, we define a new method, called the combination of the Manhattan distance and symmetric Kullback–Leibler divergence, to measure texture similarity. Third, by the Moore–Penrose inverse matrix and semisupervised learning, we construct an across-affinity matrix. A quantitative evaluation using SAR images shows that the new algorithm produces significantly high-quality segmentations as compared with state-of-the-art segmentation algorithms.

An adaptive vector quantization approach for image segmentation based on SOM network

Image segmentation can be viewed as an unsupervised clustering process of pixels in the image being processed. Existing segmentation algorithms in common use often take single pixel as processing unit and segment an image mainly based on the gray value information of the image pixels. However, the spatially structural information between pixels provides even more important information on the image contents. In order to effectively exploit both the gray value and the spatial information of pixels, this paper presents an adaptive image segmentation approach based on Vector Quantization (VQ) technique. In the method, the image to be segmented is divided into small sub-blocks with each sub-block constituting a vector and the vectors are clustered by using the VQ method to implement the segmentation. The self-organizing map (SOM) neural network is adopted for realizing the VQ algorithm adaptively. In order to resolve the problem of determining the codebook size (i.e., the segment number) for the SOM-based VQ segmentation approach, an adaptive search algorithm for estimating the optimum codebook size is developed by minimizing the ratio of within-class scatter to between-class scatter in the segmentation process. Experiments have been conducted in the work by using real brain MRI images from the Internet Brain Segmentation Repository (IBSR) and some other databases and comparison studies with other algorithms in the state-of-the-art are performed. The experimental results are evaluated both via subjective comparison with human vision and also via quantitative evaluation in terms of the average overlap metric, which shows that the proposed method outperforms the other existing algorithms.

An image segmentation method based on the fusion of vector quantization and edge detection with applications to medical image processing

In the existing segmentation algorithms, most of them take single pixel as processing unit and segment an image mainly based on the gray value information of the image pixels. However, the spatially structural information between pixels of an image provides even more important information of the image. In order to effectively exploit both the gray value and the spatial information of image pixels, this paper proposes a fusion method for image segmentation by jointly utilizing vector quantization and edge detection methods. In the method, the image to be segmented is divided into small sub-blocks with each sub-block constituting a vector and the vectors are classified into two patterns, called the edge pattern and non-edge pattern, by using an edge detection algorithm. The image is then processed further, in which a Boundary Detection (BD) algorithm is developed for extracting the refined boundary curves in the edge pattern vectors and a Vector Quantization (VQ) approach is presented for segmenting the non-edge pattern vectors. In addition, an SOM neural network is proposed for realizing the VQ algorithm adaptively. Finally, a fusion scheme is designed to synthesize the results of VQ and BD to accomplish the segmentation. Simulation experiments and comparison studies have been conducted with applications to medical image processing in the paper, and the results validate the effectiveness of the proposed method.

Improved Color Image Segmentation Algorithm Based on GrabCut

In realistic image processing, it is a problem of image foreground extraction. For a large number of color image processing, an important requirement is the automation of the extraction process. In this paper, by automatically setting foreground seed, we improve the image existing segmentation algorithm; by automatically searching image segmentation region, we accomplish image segmentation with the GrabCut algorithm, which is based on Gaussian Mixture Model and boundary computing. The improved algorithm in this paper can achieve the automation of image segmentation, without user participation in the implementation process, at the same time, it improves the efficiency of image segmentation, and gets a good result of image segmentation in complex background.

Hinging hyperplanes for time-series segmentation.

Division of a time series into segments is a common technique for time-series processing, and is known as segmentation. Segmentation is traditionally done by linear interpolation in order to guarantee the continuity of the reconstructed time series. The interpolation-based segmentation methods may perform poorly for data with a level of noise because interpolation is noise sensitive. To handle the problem, this paper establishes an explicit expression for segmentation from a compact representation for piecewise linear functions using hinging hyperplanes. This expression enables the use of regression to obtain a continuous reconstructed signal and, as a consequence, application of advanced techniques in segmentation. In this paper, a least squares support vector machine with lasso using a hinging feature map is given and analyzed, based on which a segmentation algorithm and its online version are established. Numerical experiments conducted on synthetic and real-world datasets demonstrate the advantages of our methods compared to existing segmentation algorithms.

Investigation of a novel image segmentation method dedicated to forest fire applications**This paper is dedicated to the memory of Dr Olivier Séro-Guillaume (1950–2013), CNRS Research Director.

To face fire it is crucial to understand its behaviour in order to maximize fighting means. To achieve this task, the development of a metrological tool is necessary for estimating both geometrical and physical parameters involved in forest fire modelling. A key parameter is to estimate fire positions accurately. In this paper an image processing tool especially dedicated to an accurate extraction of fire from an image is presented. In this work, the clustering on several colour spaces is investigated and it appears that the blue chrominance Cb from the YCbCr colour space is the most appropriate. As a consequence, a new segmentation algorithm dedicated to forest fire applications has been built using first an optimized k-means clustering in the Cb-channel and then some properties of fire pixels in the RGB colour space. Next, the performance of the proposed method is evaluated using three supervised evaluation criteria and then compared to other existing segmentation algorithms in the literature. Finally a conclusion is drawn, assessing the good behaviour of the developed algorithm.

Shape priors extraction and application for geodesic distance transforms in images and videos

We present a shape prior embedded geodesic distance transform for image and video segmentation. Whilst the existing segmentation algorithms have achieved impressive performance in many examples, they may fail in cases where the quality of the likelihood images is not satisfactory, or where multiple similar objects are in close proximity to one another. To deal with these problems, we embed shape prior knowledge in an image segmentation algorithm based on geodesic distance transform. Different from other segmentation methods, the proposed geodesic distance transform morphology operators consider three factors simultaneously: the geometric distance, weighted gradients, and the distance to the boundary of shape priors. As a result, it provides segmentation in line with the real shape of a particular kind of object. We also propose an effective shape prior extraction method that compute shape priors automatically. The proposed algorithm demonstrates positive results for many challenging images and video sequences in our experiments.

Modified neutrosophic approach to color image segmentation

We improved an image segmentation algorithm based on neutrosophic set (NS) and extended the modified method into color image segmentation. The original NS image segmentation approach transformed the images into NS domain, which is described using three membership sets: T, I, and F. Then two operations, α-mean and β-enhancement operations were employed to reduce the set indeterminacy. Although this method was quite successful in image segmentation application, some drawbacks still exist, such as oversegmentation and fixed α and β parameters. Thus, a new algorithm is proposed to overcome these limitations of the NS-based image segmentation algorithm. Then, the new modified method is extended into color image segmentation. The NS-based image segmentation algorithm is applied to each color channel independently. Then each channel is moved to a matrix column, respectively, to construct the input matrix to the γ-K-means clustering. Experiments are conducted on a variety of images, and our results are compared with those new existing segmentation algorithm. The experimental results demonstrate that the proposed approach can segment the color images automatically and effectively.

Adopting and Implementation of Self Organizing Feature Map for Image Fusion

A different image fusion algorithm based on self organizing feature map is proposed in this paper, aiming to produce quality images. Image Fusion is to integrate complementary and redundant information from multiple images of the same scene to create a single composite image that contains all the important features of the original images. The resulting fused image will thus be more suitable for human and machine perception or for further image processing tasks. The existing fusion techniques based on either direct operation on pixels or segments fail to produce fused images of the required quality and are mostly application based. The existing segmentation algorithms become complicated and time consuming when multiple images are to be fused. A new method of segmenting and fusion of gray scale images adopting Self organizing Feature Maps(SOM) is proposed in this paper. The Self Organizing Feature Maps is adopted to produce multiple slices of the source and reference images based on various combination of gray scale and can dynamically fused depending on the application. The proposed technique is adopted and analyzed for fusion of multiple images. The technique is robust in the sense that there will be no loss in information due to the property of Self Organizing Feature Maps; noise removal in the source images done during processing stage and fusion of multiple images is dynamically done to get the desired results. Experimental results demonstrate that, for the quality multifocus image fusion, the proposed method performs better than some popular image fusion methods in both subjective and objective qualities.

Color image segmentation based on neutrosophy

Neutrosophy studies the origin, nature, scope of neutralities, and their interactions with different ideational spectra. It is an alternative to the existing logics and represents mathematical uncertainty, vagueness, contradiction, and imprecision. Neutrosophy introduces a new concept to represent indeterminacy, which is a new philosophy to extend fuzzy logic. We introduce neutrosophy to color image segmentation and develop a novel unsupervised algorithm. We determine the centers of image clusters by using color information in red, green, and blue (RGB) color space and define neutrosophic indeterminacy by using spatial information in CIE (L*u*v*) color space. By applying neutrosophy, we integrate color and spatial information, as well as global and local information in two color spaces: RGB and CIE, respectively. Most existing segmentation algorithms have the over-segmentation problem, which causes segmentation accuracy to be lower, especially when noisy images are processed. Neutrosophy has noise-tolerant ability. In the experiment section, USC-SIPI image database is used to compare the proposed algorithm with several fuzzy and non-fuzzy color segmentation algorithms. The experiments demonstrate that the proposed algorithm can handle the segmentation tasks well and can even process noisy images with better accuracy. They also show its noise-tolerant ability. The proposed approach is more effective and powerful for color image segmentation, which can find wide applications in related areas.

Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration

We present a bottom-up aggregation approach to image segmentation. Beginning with an image, we execute a sequence of steps in which pixels are gradually merged to produce larger and larger regions. In each step, we consider pairs of adjacent regions and provide a probability measure to assess whether or not they should be included in the same segment. Our probabilistic formulation takes into account intensity and texture distributions in a local area around each region. It further incorporates priors based on the geometry of the regions. Finally, posteriors based on intensity and texture cues are combined using “a mixture of experts” formulation. This probabilistic approach is integrated into a graph coarsening scheme, providing a complete hierarchical segmentation of the image. The algorithm complexity is linear in the number of the image pixels and it requires almost no user-tuned parameters. In addition, we provide a novel evaluation scheme for image segmentation algorithms, attempting to avoid human semantic considerations that are out of scope for segmentation algorithms. Using this novel evaluation scheme, we test our method and provide a comparison to several existing segmentation algorithms.