Unsupervised Joint Image Denoising and Active Contour Segmentation in Multidimensional Feature Space

Hydrological drought refers to an abnormal water shortage caused by precipitation and surface water shortages or a groundwater imbalance. Hydrological drought is reflected in a drop of surface water, decrease of vegetation productivity, increase of temperature difference between day and night and so on. Remote sensing permits the observation of surface water, vegetation, temperature and other information from a macro perspective. This paper analyzes the correlation relationship and differentiation of both remote sensing and surface measured indicators, after the selection and extraction a series of representative remote sensing characteristic parameters according to the spectral characterization of surface features in remote sensing imagery, such as vegetation index, surface temperature and surface water from HJ-1A/B CCD/IRS data. Finally, multi-dimensional remote sensing features such as hydrological drought are built on a intelligent collaborative model. Further, for the Dong-ting lake area, two drought events are analyzed for verification of multi-dimensional features using remote sensing data with different phases and field observation data. The experiments results proved that multi-dimensional features are a good method for hydrological drought.

Multiple sclerosis (MS) one of the chronic Idiopathic disease needs a precise segmentation method to analyze the MS White Matter Lesion (WML) variation with respect the Extended Disability scale (EDSS) value of MS MR brain images. In this work, we use the Active contour segmentation method to segment the MS brain tissue from T2W axial view MS preprocessed MR images. The Active contour segmentation to segment MS affected area using the ITK-SNAP 3D segmentation tool. The segmented MS WML lesion image region to measure the MS lesion affected area volume and calculate the image shape and statistical feature value using Gray Level Co-occurrence Matrix (GLCM). The MS WML volume, shape, and statistical feature are correlated with the different EDSS value of the MS patient data set. The shape, statistical feature parameter, and lesion volume correlation study are very useful to monitoring changes associated with improvement of disability stage from 1–9 category of MS progression. Reproducibility and sensitivity must be enhanced to use the analysis for consecutive monitoring in individuals.

This paper demonstrates how active contour segmentation and optical flow estimation techniques can be combined to create a seamless mosaic of frames from a video sequence. This virtual scene forms the basis of a number of post-production effects such as creating new image trajectories for the shot, or special effects which include new foreground elements. The optical flow method produces highly accurate global motion estimates by drawing upon an appropriate 3D geometrical model of camera motion. The active contour technique has been extended to include user selected edge data to guide crudely specified initial contours to their final location. The resultant rotoscoping tool dramatically improves the performance of traditional tools by using edge chain matching to relocate the active contour in subsequent frames.

This paper presents an automatic tissue segmentation methodology for High-Resolution Ultrasonic Transmission Tomography (HUTT) imagery of biological organs. This method combines a recent segmentation approach: the L-level set active contours algorithm with unsupervised clustering using the agglomerative hierarchical k-means algorithm. The active contours algorithm has been recently explored as a powerful tool for image segmentation since it automatically decomposes a given image into 2L segment classes by utilizing L level set functions and finding the optimal boundaries of the 2L segment classes so that the pixel feature values of each segment are as homogeneous as possible. Unfortunately, the algorithm is often trapped at local minima due to the intrinsic non-convexity of the cost function, especially for noisy data. To overcome this problem, we introduce a multi-stage multi-resolution analysis that optimizes the active contours at successive resolutions of the image data. The resulting segments are then re-clustered by subsequent agglomerative hierarchical k-means clustering that seeks the optimal clusters yielding the minimum within-cluster distance in the feature space. The preliminary studies reported here indicate that this proposed methodology can enhance the accuracy of soft tissue segmentation and provide fully automatic tissue differentiation without any user intervention except for specifying the number of level set functions L.

This paper presents a description of a Bayesian neural network (BNN) automatic target recognition (ATR) algorithm specifically developed to efficiently exploit the correlated relationships between the joint dimensional distribution properties of the multiple features. A multidimensional clustering process is used to define a Parzen estimate which approximates the Bayesian a posteriori decision function, but without limiting constraints regarding multimodal or correlated density function forms in multidimensional feature space. The mathematical derivation is placed in the form of a multilayer neural network, including Kernel function variance adaptation to accommodate small training data sets, and Kernel function tail saturation for robust handling of multidimensional feature data not represented in the training data. The BNN is shown to be a hybrid Bayesian/neural net classifier. It has a robust Bayesian statistical classifier as an initial state, and a feedback learning structure which enables learning corrections localized only to the feature space in the vicinity of the error. In addition, a method is described for integrating scene context information, spatial constraints, and a priori probability information into the BNN classifier. Example uses of the BNN algorithm are discussed for recent programs which obtained multiple feature ATR improvements from using the BNN with multiple frequencies, polarizations, aspect angles, and 3D interferometric SAR features.

This chapter focuses on the division and location of brain deformities such as tumors in magnetic resonance imaging (MRI) through Chan-Vese active contour segmentation. Brain tumor division and identification is a major test in the area of biomedical picture processing. To detect the size and location of the tumor, various techniques are available, but active contour gives accurate knowledge of the region for segmentation. Chan-Vese Active contour method provides independent, robust and more flexible segmentation. In this chapter, firstly we used preprocessing technique in which noise and unused parts of the brain and skull are removed, for this we proposed the skull stripping method. Then, we applied feature extraction to enhance the image intensity and quality, and lastly, used Chan-Vese active contour with a level set image segmentation technique to detect the tumor. The tumor area was calculated after tumor detection.

Active contours are adapted to image segmentation by energy minimization. The energies often exhibit local minima, requiring regularization. Such an a priori can be expressed as a shape prior and used in two main ways: (1) a shape prior energy is combined with the segmentation energy into a trade-off between prior compliance and accuracy or (2) the segmentation energy is minimized in the space defined by a parametric shape prior. Methods (1) require the tuning of a data-dependent balance parameter and methods (1) and (2) are often dedicated to a specific prior or contour representation, with the prior and segmentation aspects often meshed together, increasing complexity. A general framework for category (2) is proposed: it is independent of the prior and contour representations and it separates the prior and segmentation aspects. It relies on the relationship shown here between the shape gradient, the prior-induced admissible contour transformations, and the segmentation energy minimization.

Automatic building extraction is an important topic for many applications such as urban planning, disaster management, 3D building modeling and updating GIS databases. Its approaches mainly depend on two data sources: light detection and ranging (LiDAR) point cloud and aerial imagery both of which have advantages and disadvantages of their own. In this study, in order to benefit from the advantages of each data sources, LiDAR and image data combined together. And then, the building boundaries were extracted with the automated active contour algorithm implemented in MATLAB. Active contour algorithm uses initial contour positions to segment an object in the image. Initial contour positions were detected without user interaction by a series of image enhancements, band ratio and morphological operations. Four test areas with varying building and background levels of detail were selected from ISPRS’s benchmark Vaihingen and Istanbul datasets. Vegetation and shadows were removed from all the datasets by band ratio to improve segmentation quality. Subsequently, LiDAR point cloud data was converted to raster format and added to the aerial imagery as an extra band. Resulting merged image and initial contour positions were given to the active contour algorithm to extract building boundaries. In order to compare the contribution of LiDAR to the proposed method, the boundaries of the buildings were extracted from the input image before and after adding LiDAR data to the image as a layer. Finally extracted building boundaries were smoothed by the Awrangjeb (Int J Remote Sen 37(3): 551–579. https://doi.org/10.1080/01431161.2015.1131868 , 2016) boundary regularization algorithm. Correctness (Corr), completeness (Comp) and accuracy (Q) metrics were used to assess accuracy of segmented building boundaries by comparing extracted building boundaries with manually digitized building boundaries. Proposed approach shows the promising results with over 93% correctness, 92% completeness and 89% quality.

Breast lesion segmentation is an essential step in developing Computer-aided Diagnostic (CAD) system for the early detection of breast cancer. However, accurate lesion segmentation is challenging, since the lesions may have complicated topological structures and different intensity distributions. This paper describes a novel approach for breast lesion segmentation from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using a level set-based active contour model. Its evolution is controlled by specially designed signed pressure function that only accounts for distribution of image background intensity, so solving the weak-edge-passed problem and improving the robustness to segment different lesions. To confirm the proposed approach, it is compared with different methods based on level set. Experiment results show that the proposed method leads to better results. On a total of 38 breast DCE-MRI studies, our method yields a mean difference (MAD) of 7.2561±12.4537 pixels and Jaccard index of 0.8564±0.0493 compared to manual ground truth segmentation.

An active contour segmentation technique for extracting the intima-media layer of the common carotid artery (CCA) ultrasound images employing semiautomatic region of interest identification and speckle reduction techniques is presented in this paper. An attempt has been made to test the ultrasound images of the carotid artery of different subjects with this contour segmentation based on improved dynamic programming method. It is found that the preprocessing of ultrasound images of the CCA with region identification and despeckleing followed by active contour segmentation algorithm can be successfully used in evaluating the intima-media thickness (IMT) of the normal and abnormal subjects. It is also estimated that the segmentation used in this paper results an intermethod error of 0.09mm and a coefficient of variation of 18.9%, for the despeckled images. The magnitudes of the IMT values have been used to explore the rate of prediction of blockage existing in the cerebrovascular and cardiovascular pathologies and also hypertension and atherosclerosis.

Lack of temporal coherence in video segmentation algorithms often leads to flickering or to discrepancies on the segmentation mask boundaries. Active contour video segmentation algorithms can lead to very smooth segmentation masks when they are defined in three dimensions (two spatial and one temporal). In this paper, we will use an active contour method to attract an active surface toward a non-smoothed segmentation mask boundary. This active surface will produce a new segmentation mask which will be smoother than the first one. To achieve this task, we introduce a new region-based term for active contour segmentation in the variational framework. This term attracts the evolving curve to a reference contour. The energy criterion and the evolution equation are defined in n-dimension and we investigate the particular case of two regions. The use of active surfaces to smooth video segmentation masks appears to be a very powerful tool for video postprocessing. The resulting masks are smoother than the original ones, the discrepancies of the segmentation masks are removed and the flickering on the boundary of the segmentation masks are considerably reduced.

Computer vision based human detection systems are gaining much significance in modern security and surveillance systems. Recently, advanced camera sensors like Microsoft Kinect came to the scene and such devices are capable of detecting both color and depth details from a captured scene. This article proposes an intelligent human segmentation system by analyzing both color and depth details retrieved by an RGB-Depth camera. Here the depth data is analyzed first, to create an initial segmentation of human factors from the scene. Since depth analysis have restrictions in identifying accurate edge details, post processing steps are used for refurbishing the missed human portions in the frame. The hair regions are first restored first using Chan-vase active contour detection and the subset of foreground pixels thus obtained after this coarse level segmentation are used as seeds to segment the rest of the image frame using Grow-cut segmentation. An iterative cellular automation is employed here to classify the foreground human region. This final segmentation mask thus generated after Grow-cut segmentation can be used for segmenting human region from the original image frame. Experimental results show that the segmentation is helpful for analyzing the human factors in each frame and can be used for further human tracking or activity recognition.

We propose a new method for performing active contour segmentation based on the statistical prior knowledge of the object to detect. From a binary training set of objects, a statistical map describes the possible shapes of the object by computing the probability for each point to belong to the object. This statistical map is treated as a prior distribution and an energy functional is defined such that the object reaches the most probable shape knowing the model. The optimization is done in the level-set framework. Results on both synthetic and medical images are shown.

The segmentation and identification of neoplasm from brain MR images have gotten enormous consideration in the zone of biomedical research analysis. Segmentation is the way toward parting an image into various sections called segments. The precise segmentation of brain MR images into different units assumes a significant job in the early analysis and treatment of carcinoma. In this chapter, an active contour Chan-Vese segmentation algorithm is used. This algorithm comprises two energies, of which one power diminishes the form and the other expansion of the shape. These two energies get adjusted when the chapter arrives at the furthest point of our ideal item, which brings about total segmentation. The proposed design comprises five fundamental steps: preprocessing, creation of an introductory mask, giving the most extreme number of cycles(iterations), application of Chan-Vese active contour approach for the finding of the tumor, and extraction of its region. The competence of the proposed design has been tested on various brain MR images. We have found that the proposed methodology can detect and extract the tumor and its area.

In this work, a novel system, which works on a multidimensional feature space and detects the prominent signal components on the spectrum with high recall and precision, is presented. The boundary hiper planes are determined by using Support Vector Machine (SVM) classifier in the multidimensional feature space. The solution to the class training set imbalance problem is investigated with multiple SVM classifiers system. By balancing the training sets by random selections, the detection performance is raised. The features that are used in the proposed system are evaluated by Forward Feature Selection algorithm with two different selection criteria. The implemented system is compared to three different thresholding based detection system and it is observed that it has better performance than thresholding based systems. It is shown with proper test sets that it can perform high performance prominent component detection highly independent of training data.