Unsupervised multiscale segmentation of color images

This paper proposes a new multiresolution technique for color image representation and segmentation, particularly suited for noisy images. A decimated wavelet transform is initially applied to each color channel of the image, and a multiresolution representation is built up to a selected scale 2^J. Color gradient magnitudes are computed at the coarsest scale 2^J, and an adaptive threshold is used to remove spurious responses. An initial segmentation is then computed by applying the watershed transform to thresholded magnitudes, and this initial segmentation is projected to finer resolutions using inverse wavelet transforms and contour refinements, until the full resolution 2⁰ is achieved. Finally, a region merging technique is applied to combine adjacent regions with similar colors. Experimental results show that the proposed technique produces results comparable to other state-of-the-art algorithms for natural images, and performs better for noisy images.     

Unsupervised segmentation of color-texture regions in images andvideo

A method for unsupervised segmentation of color-texture regions in images and video is presented. This method, which we refer to as JSEG, consists of two independent steps: color quantization and spatial segmentation. In the first step, colors in the image are quantized to several representative classes that can be used to differentiate regions in the image. The image pixels are then replaced by their corresponding color class labels, thus forming a class-map of the image. The focus of this work is on spatial segmentation, where a criterion for “good” segmentation using the class-map is proposed. Applying the criterion to local windows in the class-map results in the “J-image,” in which high and low values correspond to possible boundaries and interiors of color-texture regions. A region growing method is then used to segment the image based on the multiscale J-images. A similar approach is applied to video sequences. An additional region tracking scheme is embedded into the region growing process to achieve consistent segmentation and tracking results, even for scenes with nonrigid object motion. Experiments show the robustness of the JSEG algorithm on real images and video     

Automatic cervical cell segmentation and classification in Pap smears

Cervical cancer is one of the leading causes of cancer death in females worldwide. The disease can be cured if the patient is diagnosed in the pre-cancerous lesion stage or earlier. A common physical examination technique widely used in the screening is Papanicolaou test or Pap test. In this research, a method for automatic cervical cancer cell segmentation and classification is proposed. A single-cell image is segmented into nucleus, cytoplasm, and background, using the fuzzy C-means (FCM) clustering technique. Four cell classes in the ERUDIT and LCH datasets, i.e., normal, low grade squamous intraepithelial lesion (LSIL), high grade squamous intraepithelial lesion (HSIL), and squamous cell carcinoma (SCC), are considered. The 2-class problem can be achieved by grouping the last 3 classes as one abnormal class. Whereas, the Herlev dataset consists of 7 cell classes, i.e., superficial squamous, intermediate squamous, columnar, mild dysplasia, moderate dysplasia, severe dysplasia, and carcinoma in situ. These 7 classes can also be grouped to form a 2-class problem. These 3 datasets were tested on 5 classifiers including Bayesian classifier, linear discriminant analysis (LDA), K-nearest neighbor (KNN), artificial neural networks (ANN), and support vector machine (SVM). For the ERUDIT dataset, ANN with 5 nucleus-based features yielded the accuracies of 96.20% and 97.83% on the 4-class and 2-class problems, respectively. For the Herlev dataset, ANN with 9 cell-based features yielded the accuracies of 93.78% and 99.27% for the 7-class and 2-class problems, respectively. For the LCH dataset, ANN with 9 cell-based features yielded the accuracies of 95.00% and 97.00% for the 4-class and 2-class problems, respectively. The segmentation and classification performances of the proposed method were compared with that of the hard C-means clustering and watershed technique. The results show that the proposed automatic approach yields very good performance and is better than its counterparts.     

Automatic joint classification and segmentation of whole cell 3D images

We present a machine learning tool for automatic texton-based joint classification and segmentation of mitochondria in MNT-1 cells imaged using ion-abrasion scanning electron microscopy (IA-SEM). For diagnosing signatures that may be unique to cellular states such as cancer, automatic tools with minimal user intervention need to be developed for analysis and mining of high-throughput data from these large volume data sets (typically ). Challenges for such a tool in 3D electron microscopy arise due to low contrast and signal-to-noise ratios (SNR) inherent to biological imaging. Our approach is based on block-wise classification of images into a trained list of regions. Given manually labeled images, our goal is to learn models that can localize novel instances of the regions in test datasets. Since datasets obtained using electron microscopes are intrinsically noisy, we improve the SNR of the data for automatic segmentation by implementing a 2D texture-preserving filter on each slice of the 3D dataset. We investigate texton-based region features in this work. Classification is performed by k-nearest neighbor (k-NN) classifier, support vector machines (SVMs), adaptive boosting (AdaBoost) and histogram matching using a NN classifier. In addition, we study the computational complexity vs. segmentation accuracy tradeoff of these classifiers. Segmentation results demonstrate that our approach using minimal training data performs close to semi-automatic methods using the variational level-set method and manual segmentation carried out by an experienced user. Using our method, which we show to have minimal user intervention and high classification accuracy, we investigate quantitative parameters such as volume of the cytoplasm occupied by mitochondria, differences between the surface area of inner and outer membranes and mean mitochondrial width which are quantities potentially relevant to distinguishing cancer cells from normal cells. To test the accuracy of our approach, these quantities are compared against manually computed counterparts. We also demonstrate extension of these methods to segment 3D images obtained using electron tomography.     

Unsupervised category modeling, recognition, and segmentation in images

Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category; (2) learning a region-based structural model of the category in terms of these properties; and (3) detection, recognition and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree-union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark datasets demonstrates the robustness and high accuracy of the learned category models, when only a few training examples are used for learning without any human supervision.     

Unsupervised multiresolution segmentation for images with low depthof field

Unsupervised segmentation of images with low depth of field (DOF) is highly useful in various applications. This paper describes a novel multiresolution image segmentation algorithm for low DOF images. The algorithm is designed to separate a sharply focused object-of-interest from other foreground or background objects. The algorithm is fully automatic in that all parameters are image independent. A multi-scale approach based on high frequency wavelet coefficients and their statistics is used to perform context-dependent classification of individual blocks of the image. Unlike other edge-based approaches, our algorithm does not rely on the process of connecting object boundaries. The algorithm has achieved high accuracy when tested on more than 100 low DOF images, many with inhomogeneous foreground or background distractions. Compared with he state of the art algorithms, this new algorithm provides better accuracy at higher speed     

Unsupervised segmentation of textured images by edge detection inmultidimensional feature

An algorithm for unsupervised texture segmentation is developed that is based on detecting changes in textural characteristics of small local regions. Six features derived from two, two-dimensional, noncausal random field models are used to represent texture. These features contain information about gray-level-value variations in the eight principal directions. An algorithm for automatic selection of the size of the observation windows over which textural activity and change are measured has been developed. Effects of changes in individual features are considered simultaneously by constructing a one-dimensional measure of textural change from them. Edges in this measure correspond to the sought-after textural edges. Experiments results with images containing regions of natural texture show that the algorithm performs very well     

Unsupervised statistical segmentation of nonstationary images using triplet Markov fields

Recent developments in statistical theory and associated computational techniques have opened new avenues for image modeling as well as for image segmentation techniques. Thus, a host of models have been proposed and the ones which have probably received considerable attention are the hidden Markov fields (HMF) models. This is due to their simplicity of handling and their potential for providing improved image quality. Although these models provide satisfying results in the stationary case, they can fail in the nonstationary one. In this paper, we tackle the problem of modeling a nonstationary hidden random field and its effect on the unsupervised statistical image segmentation. We propose an original approach, based on the recent triplet Markov field (TMF) model, which enables one to deal with nonstationary class fields. Moreover, the noise can be correlated and possibly non-Gaussian. An original parameter estimation method which uses the Pearson system to find the natures of the noise margins, which can vary with the class, is also proposed and used to perform unsupervised segmentation of such images. Experiments indicate that the new model and related processing algorithm can improve the results obtained with the classical ones.     

Morphological segmentation and classification of underground pipe images

Visual inspection based on closed circuit television surveys is used widely in North America to assess the condition of underground pipes. Although the human eye is extremely effective at recognition and classification, it is not suitable for assessing pipe defects in thousand of miles of pipeline because of fatigue, subjectivity, and cost. In this paper, simple, robust, and efficient image segmentation and classification algorithm for the automated analysis of scanned underground pipe images is presented. The experimental results demonstrate that the proposed algorithm can precisely segment and classify pipe cracks, holes, laterals, joints and collapse surface from underground pipe images     

Unsupervised segmentation of dual-polarization SAR images based on amplitude and texture characteristics

A new approach for the unsupervised segmentation of dual-polarization Synthetic Aperture Radar (SAR) images based on statistics of both the amplitude variations and the textural characteristics of the data is presented. A co-polarized amplitude image and a cross-polarized amplitude image are used in this study. It is a two-step process. In the first step, these images are filtered once to suppress the speckle noise while preserving the contrast associated with edges and subtle details. The feature vector composed of the two filtered image pixels is assumed to have a joint Gaussian distribution. A scanning window is used to discover clusters at each position. A merging procedure follows to combine these clusters based on the Mahalanobis distance measure, into a number appropriate for the image. A Bayes maximum likelihood classifier is then applied. In the second step, we adopt the second-order Gaussian Markov random field (GMRF) models for image textures in the original un-filtered images. Segments assigned to each class in the first step are examined for possible sub-division into groups, based on textural characteristics. Two segments are considered texturally similar if the ratio of the pseudo-likelihoods of the image before and after merging is close to one.     

Unsupervised segmentation of ultrasonic liver images by multiresolution fractal feature vector

The feasibility of selecting fractal feature vector based on multiresolution analysis to segment suspicious abnormal regions of ultrasonic liver images is described in this paper. The proposed feature extraction algorithm is based on the spatial-frequency decomposition and fractal geometry. Segmentation of various liver diseases reveals that the fractal feature vector based on multiresolution analysis is trustworthy. A quantitative characterization based on the proposed unsupervised segmentation algorithm can be utilized to establish an automatic computer-aided diagnostic system. As well, to increase the visual interpretation capability of ultrasonic liver image for junior physicians, off-line learning software is developed to investigate the visual criteria.     

Effective segmentation and classification for HCC biopsy images

Accurate grading for hepatocellular carcinoma (HCC) biopsy images is important to prognosis and treatment planning. In this paper, we propose an automatic system for grading HCC biopsy images. In preprocessing, we use a dual morphological grayscale reconstruction method to remove noise and accentuate nuclear shapes. A marker-controlled watershed transform is applied to obtain the initial contours of nuclei and a snake model is used to segment the shapes of nuclei smoothly and precisely. Fourteen features are then extracted based on six types of characteristics for HCC classification. Finally, we propose a SVM-based decision-graph classifier to classify HCC biopsy images. Experimental results show that 94.54% of classification accuracy can be achieved by using our SVM-based decision-graph classifier while 90.07% and 92.88% of classification accuracy can be achieved by using k-NN and SVM classifiers, respectively.     

Unsupervised classification of SAR images using normalized gamma process mixtures

We propose an image prior for the model-based nonparametric classification of synthetic aperture radar (SAR) images that allows working with infinite number of mixture components. In order to enclose the spatial interactions of the pixel labels, the prior is derived by incorporating a conditional multinomial auto-logistic random field into the Normalized Gamma Process prior. In this way, we obtain an image classification prior that is free from the limitation on the number of classes and includes the smoothing constraint into classification problem. In this model, we introduced a hyper-parameter that can control the preservation of the important classes and the extinction of the weak ones. The recall rates reported on the synthetic and the real TerraSAR-X images show that the proposed model is capable of accurately classifying the pixels. Unlike the existing methods, it applies a simple iterative update scheme without performing a hierarchical clustering strategy. We demonstrate that the estimation accuracy of the proposed method in number of classes outperforms the conventional finite mixture models.     

Unsupervised segmentation method for cuboidal cell nuclei in histological prostate images based on minimum cross entropy

This paper presents a novel segmentation method for cuboidal cell nuclei in images of prostate tissue stained with hematoxylin and eosin. The proposed method allows segmenting normal, hyperplastic and cancerous prostate images in three steps: pre-processing, segmentation of cuboidal cell nuclei and post-processing. The pre-processing step consists of applying contrast stretching to the red (R) channel to highlight the contrast of cuboidal cell nuclei. The aim of the second step is to apply global thresholding based on minimum cross entropy to generate a binary image with candidate regions for cuboidal cell nuclei. In the post-processing step, false positives are removed using the connected component method. The proposed segmentation method was applied to an image bank with 105 samples and measures of sensitivity, specificity and accuracy were compared with those provided by other segmentation approaches available in the specialized literature. The results are promising and demonstrate that the proposed method allows the segmentation of cuboidal cell nuclei with a mean accuracy of 97%.     

A new automated segmentation and classification of mammogram images

Multimedia Tools and Applications - Early-stage recognition of lesions is the better probable manner for fighting against breast cancer to find a disease with the highest ratio of malignancy around...     

Unsupervised multi-class segmentation of SAR images using fuzzy triplet Markov fields model

Triplet Markov fields (TMF) model proposed recently is suitable for nonstationary image segmentation. For synthetic aperture radar (SAR) image segmentation, TMF model can adopt diverse statistical models for SAR data related to diverse radar backscattering sources. However, TMF model does not take into account the inherent imprecision associated with SAR images. In this paper, we propose a statistical fuzzy TMF (FTMF) model, which is a fuzzy clustering type treatment of TMF model, for unsupervised multi-class segmentation of SAR images. This paper contributes to SAR image segmentation in four aspects: (1) Nonstationarity of the statistical distribution of SAR intensity/amplitude data is taken into account to improve the spatial modeling capability of fuzzy TMF model. (2) Mean field theory is generalized to deal with planar variables to derive prior probability in fuzzy TMF model, which resolves the problem in Gibbs sampler in terms of computation cost. (3) A fuzzy objective function with regularization by Kullback–Leibler information of fuzzy TMF model is constructed for SAR image segmentation. The introduction of fuzziness for the belongingness of SAR image pixel makes fuzzy TMF model be able to retain more information from SAR image. (4) Fuzzy iterative conditional estimation (ICE) method, as an extension of the general ICE method is proposed to perform the model parameters estimation. The effectiveness of the proposed algorithm is demonstrated by application to simulated data and real SAR images.     

Unsupervised classification of multispectral Landsat images with multidimensional particle swarm optimization

This article proposes a novel unsupervised classification approach for automatic analysis of multispectral Landsat images. The automatic classification of the information in multidimensional (MD) Landsat data space by dynamic clustering is addressed as an optimization problem and two recently proposed heuristic techniques based on Particle Swarm Optimization (PSO) are applied to determine the optimal (number of) clusters in a given input data space: distance metric and a proper validity index function. The first technique, the so-called MD-PSO, re-forms the native structure of swarm particles (agents) in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Fractional global best formation (FGBF) basically collects all promising dimensional components and fractionally creates an artificial global best (aGB) agent that has the potential to be a better ‘guide’ than the swarm’s native global best position (gbest) agent. In this study, the proposed dynamic clustering approach based on MD-PSO and FGBF techniques is applied to automatically classify the colour-coded representations of the multispectral (MD) Landsat data. The approach has been applied to real-world multispectral data and it provided quite encouraging results compared to the traditional K-means and ISODATA (iterative self-organizing data analysis) clustering methods. The proposed unsupervised technique determines the true number of classes within Landsat data for optimal classification performance while preserving spatial resolution and textural information in the classification map.     

Improved classification and segmentation of hyperspectral images using spectral warping

This letter describes a method to increase hyperspectral image classification accuracy (CA) and segmentation accuracy (SA) using spectral warping, which is a nonlinear transformation that warps the frequency content of a signal. In the proposed approach, the frequency content corresponding to spectral data for the hyperspectral image was nonlinearly transformed along the spectral axis using warping. Classification and segmentation algorithms were estimated for the transformed spectral values to show the impact of warping. Experimental results are provided for different values of the warping parameter and it is shown that applying spectral warping increases CA and SA for appropriate warping parameters.     

Unsupervised segmentation of noisy and inhomogeneous images using global region statistics with non-convex regularization

Improving the segmentation of magnetic resonance (MR) images remains challenging because of the presence of noise and inhomogeneous intensity. In this paper, we present an unsupervised, multiphase segmentation model based on a Bayesian framework for both MR image segmentation and bias field correction in the presence of noise. In our model, global region statistics are utilized as segmentation criteria in order to classify regions with similar mean intensities but different variances. Additionally, we propose an edge indicator function based on a guided filter (instead of a Gaussian filter) that can preserve the underlying edges of the image obscured by noise. The proposed edge indicator function is integrated with non-convex regularization to overcome the influence of noise, resulting in more accurate segmentation. Furthermore, the proposed model utilizes a Markov random field to model the spatial correlation between neighboring pixels, which increases the robustness of the model under high-noise conditions. Experimental results demonstrate significant advantages in terms of both segmentation accuracy and bias field correction for inhomogeneous images in the presence of noise.     

分类与分割相结合的JPEG图像隐写分析

目的 隐写分析研究现状表明,与秘密信息的嵌入过程相比,图像内容和统计特性差异对隐写检测特征分布会造成更大的影响,这导致图像隐写分析成为了一个"相同类内特征分布分散、不同类间特征混淆严重"的分类问题。针对此问题,提出了一种更加有效的JPEG图像隐写检测模型。方法 通过对隐写检测常用的分类器进行分析,从降低隐写检测特征类内离散度的角度入手,将基于图像内容复杂度的预分类和图像分割相结合,根据图像内容复杂度对图像进行分类、分割,然后分别对每一类子图像提取高维富模型隐写检测特征,构建分类器进行训练和测试,并通过加权融合得到最终的检测结果。结果 在实验部分,对具有代表性的隐写检测特征集提取了两类可分性判据,对本文算法的各类别、区域所提取特征的可分性均得到明显提高,证明了模型的有效性。同时在训练、测试图像库匹配和不匹配的情况下,对算法进行了二分类测试,并与其他算法进行了性能比较,本文算法的检测性能均有所提高,性能提升最高接近10%。结论 本文算法能够有效提高隐写检测性能,尤其是在训练、测试图像库统计特性不匹配的情况下,本文算法性能提升更加明显,更适合于实际复杂网络下的应用。