Search

ACMs have been demonstrated to be highly suitable as image segmentation models for computer vision tasks. Among other ACM, the local region-based models show better performance because they extract the local information regarding intensity in the neighborhood and embed it into the energy minimization function to guide the active contour to the boundary of the desired object. However, the online segmentation of noisy and inhomogeneous is still a challenging task for local region-based ACM models. To overcome this challenge, the paper proposes a novel region-based active contour model, named active contour model with local dilated convolution filter (ACLD). The ACLD integrates local image information in the form of a signed pressure force function. Then, a Gaussian kernel is applied using dilated convolution instead of discrete convolution for regularizing the level set formulation. Finally, instead of using a constant stopping condition, the ACLD automatically stops at the object boundaries. The proposed model shows improved image segmentation results visually combined with less computational time in the case of synthetic and natural images compared with the state-of-the-art models. Further, on the ISIC2017 dataset, the ACLD yields segmentation results with the highest accuracy.

In this paper, we propose a novel image segmentation algorithm that is based on the probability distributions of the object and background. It uses the variational level sets formulation with a novel region based term in addition to the edge-based term giving a complementary functional, that can potentially result in a robust segmentation of the images. The main theme of the method is that in most of the medical imaging scenarios, the objects are characterized by some typical characteristics such a color, texture, etc. Consequently, an image can be modeled as a Gaussian mixture of distributions corresponding to the object and background. During the procedure of curve evolution, a novel term is incorporated in the segmentation framework which is based on the maximization of the distance between the GMM corresponding to the object and background. The maximization of this distance using differential calculus potentially leads to the desired segmentation results. The proposed method has been used for segmenting images from three distinct imaging modalities i.e. magnetic resonance imaging (MRI), dermoscopy and chromoendoscopy. Experiments show the effectiveness of the proposed method giving better qualitative and quantitative results when compared with the current state-of-the-art.

Image inhomogeneity often occurs in real-world images and may present considerable difficulties during image segmentation. Therefore, this paper presents a new approach for the segmentation of inhomogeneous images. The proposed hybrid active contour model is formulated by combining the statistical information of both the local and global region-based energy fitting models. The inclusion of the local region-based energy fitting model assists in extracting the inhomogeneous intensity regions, whereas the curve evolution over the homogeneous regions is accelerated by including the global region-based model in the proposed method. Both the local and global region-based energy functions in the proposed model drag contours toward the accurate object boundaries with precision. Each of the local and global region-based parts are parameterized with weight coefficients, based on image complexity, to modulate two parts. The proposed hybrid model is strongly capable of detecting region of interests (ROIs) in the presence of complex object boundaries and noise, as its local region-based part comprises bias field. Moreover, the proposed method includes a new bias field (NBF) initialization and eliminates the dependence over the initial contour position. Experimental results on synthetic and real-world images, produced by the proposed model, and comparative analysis with previous state-of-the-art methods confirm its superior performance in terms of both time efficiency and segmentation accuracy.

By using local and global image information, a novel active contour method based on the p-Laplace equation for image segmentation is proposed in this paper. The force term in the evolution equation incorporates global, local and edge information of the image. The global and local terms drag the contour towards object boundaries precisely and take care of the contour movement when it is away from the object. Meanwhile, the integration of edge stopping function in this force term ensures the stoppage of contour at object boundaries to avoid boundary leakage problem. The variable exponent p-Laplace energy is used for smoothness of the level set to detect the exact object boundaries in the presence of complex topological changes and deep depression. Finally, the adaptive force and p-Laplace energy term are jointly integrated into a level set by using a simple finite difference scheme to build the final evolution equation for the method. The proposed method has strong capability to accurately segment the images having noise, intensity inhomogeneity, and complex object boundaries. Moreover, the proposed method overcomes the problem arise from contour initialization as the evolution of contour is independent of the initialization of level set function. Experimental results on synthetic, real and medical images along with two publicly available databases validate the robustness and effectiveness of the proposed method.

Activity recognition (AR) methods require the ability to identify activities of crucial parts in a human body. Body segmentation techniques employed in video-based AR methods outlines significance of areas (parts) in a human body image that are essential for the follow-up methods, such as feature extraction. Existing body segmentation techniques generally make use of body modeling with or without its background and essentially entail large training datasets. These techniques cannot cope with the changes that may occur in images over time. For example, illumination and clothing changes are some of the key concerns in practical AR systems. This paper presents a new approach to employ active contour-based model that exhibits robustness to illumination and clothing changes. Existing techniques based on active contours effectively address this problem in still images and hence lack the ability to cope with illumination and changes. We present an optical flow that 1) ensures the smooth working of the model over the data that is used for estimation into contiguous frames, and 2) ensures to place the initial contour within the current frame. Our proposed approach does not depend on prior knowledge about the data and and does not require the training data, hence it is an unsupervised approach. We use the existing effective method curvelet transform to extract prominent features from activity frames. Curvelet transform keeps the line and edge information in an image intact. We employ the linear discriminant analysis (LDA) for dimension space reduction and the hidden Markov model (HMM) for activity recognition. We show that AR using our proposed method for segmentation has the accuracy comparable to those that make use of manual segmentation methods and prove its feasibility in practical AR systems.

This paper describes an interdisciplinary approach to geometry modeling of geospatial boundaries. The objective is to extract surfaces from irregular spatial patterns using differential geometry and obtain coherent directional predictions along the boundary of extracted surfaces to enable more targeted sampling and exploration. Specific difficulties of the data include sparsity, incompleteness, causality and resolution disparity. Surface slopes are estimated using only sparse samples from cross-sections within a geological domain with no other information at intermediate depths. From boundary detection to subsurface reconstruction, processes are automated in between. The key problems to be solved are boundary extraction, region correspondence and propagation of the boundaries via contour morphing. Established techniques from computational physics, computer vision and signal processing are used with appropriate modifications to address challenges in each area. To facilitate boundary extraction, an edge map synthesis procedure is presented. This works with connected component analysis, anisotropic diffusion and active contours to convert unordered points into regularized boundaries. For region correspondence, component relationships are handled via graphical decomposition. FFT-based spatial alignment strategies are used in region merging and splitting scenarios. Shape changes between aligned regions are described by contour metamorphosis. Specifically, local spatial deformation is modeled by PDE and computed using level-set methods. Directional predictions are obtained using particle trajectories by following the evolving boundary. However, when a branching point is encountered, particles may lose track of the wavefront. To overcome this, a curvelet backtracking algorithm has been proposed to recover information for boundary segments without particle coverage to minimize shape distortion.

In this paper, we propose a partial differential equation structure that permits an active contour method to obtain intensity inhomogeneous image segmentation. We consider fitted model comprised of local and global energy functions dictated by the scaled p-Laplace term acting as a length regularization term. A new local model is formulated by taking bias field into the local fitted model, which improves the performance of the proposed method relatively. The scaled p-Laplace equation exhibited as a regularized length term, which is utilized to reduce the impact of noise over level set minimization while guaranteeing the curve not to go through feeble boundaries. Inhomogeneities comprise of unwanted pixel variations called bias field, which change the consequences of the level set-based methods. Thereby, Gaussian distribution is used for the approximation of the bias field, and further bias field is used for bias correction likewise. Moreover, local model has been remodeled by integrating bias field inside their local information; similarly, global model is also established on the pretext of the local model. At last, we demonstrate the results on some complex images to show the strong and exact segmentation results that are conceivable with this new class of dynamic active contour model. We have also performed statistical analysis on mammogram images using accuracy, sensitivity, and Dice index metrics. Results show that the proposed method gets high accuracy, sensitivity, and Dice index values compared to the previous state-of-the-art methods.