PyTorchKR Papers

최신 논문

총 4,951편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1307.2971

Accuracy of MAP segmentation with hidden Potts and Markov mesh prior models via Path Constrained Viterbi Training, Iterated Conditional Modes and Graph Cut based algorithms

In this paper, we study statistical classification accuracy of two different Markov field environments for pixelwise image segmentation, considering the labels of the image as hidden states and solving the estimation of such labels as a solution of the MAP equation. The emission distribution is assumed the same in all models, and the difference lays in the Markovian prior hypothesis made over the labeling random field. The a priori labeling knowledge will be modeled with a) a second order anisotropic Markov Mesh and b) a classical isotropic Potts model. Under such models, we will consider three different segmentation procedures, 2D Path Constrained Viterbi training for the Hidden Markov Mesh, a Graph Cut based segmentation for the first order isotropic Potts model, and ICM (Iterated Conditional Modes) for the second order isotropic Potts model. We provide a unified view of all three methods, and investigate goodness of fit for classification, studying the influence of parameter estimation, computational gain, and extent of automation in the statistical measures Overall Accuracy, Relative Improvement and Kappa coefficient, allowing robust and accurate statistical analysis on synthetic and real-life experimental data coming from the field of Dental Diagnostic Radiography. All algorithms, using the learned parameters, generate good segmentations with little interaction when the images have a clear multimodal histogram. Suboptimal learning proves to be frail in the case of non-distinctive modes, which limits the complexity of usable models, and hence the achievable error rate as well. All Matlab code written is provided in a toolbox available for download from our website, following the Reproducible Research Paradigm.

arXiv:1307.4516

Mammogram Edge Detection Using Hybrid Soft Computing Methods

Image segmentation is a crucial step in a wide range of method image processing systems. It is useful in visualization of the different objects present in the image. In spite of the several methods available in the literature, image segmentation still a challenging problem in most of image processing applications. The challenge comes from the fuzziness of image objects and the overlapping of the different regions. Detection of edges in an image is a very important step towards understanding image features. There are large numbers of edge detection operators available, each designed to be sensitive to certain types of edges. The Quality of edge detection can be measured from several criteria objectively. Some criteria are proposed in terms of mathematical measurement, some of them are based on application and implementation requirements. Since edges often occur at image locations representing object boundaries, edge detection is extensively used in image segmentation when images are divided into areas corresponding to different objects. This can be used specifically for enhancing the tumor area in mammographic images. Different methods are available for edge detection like Roberts, Sobel, Prewitt, Canny, Log edge operators. In this paper a novel algorithms for edge detection has been proposed for mammographic images. Breast boundary, pectoral region and tumor location can be seen clearly by using this method. For comparison purpose Roberts, Sobel, Prewitt, Canny, Log edge operators are used and their results are displayed. Experimental results demonstrate the effectiveness of the proposed approach.

arXiv:1307.7800

Efficient Energy Minimization for Enforcing Statistics

Energy minimization algorithms, such as graph cuts, enable the computation of the MAP solution under certain probabilistic models such as Markov random fields. However, for many computer vision problems, the MAP solution under the model is not the ground truth solution. In many problem scenarios, the system has access to certain statistics of the ground truth. For instance, in image segmentation, the area and boundary length of the object may be known. In these cases, we want to estimate the most probable solution that is consistent with such statistics, i.e., satisfies certain equality or inequality constraints. The above constrained energy minimization problem is NP-hard in general, and is usually solved using Linear Programming formulations, which relax the integrality constraints. This paper proposes a novel method that finds the discrete optimal solution of such problems by maximizing the corresponding Lagrangian dual. This method can be applied to any constrained energy minimization problem whose unconstrained version is polynomial time solvable, and can handle multiple, equality or inequality, and linear or non-linear constraints. We demonstrate the efficacy of our method on the foreground/background image segmentation problem, and show that it produces impressive segmentation results with less error, and runs more than 20 times faster than the state-of-the-art LP relaxation based approaches.

arXiv:1307.7793

Multi-dimensional Parametric Mincuts for Constrained MAP Inference

In this paper, we propose novel algorithms for inferring the Maximum a Posteriori (MAP) solution of discrete pairwise random field models under multiple constraints. We show how this constrained discrete optimization problem can be formulated as a multi-dimensional parametric mincut problem via its Lagrangian dual, and prove that our algorithm isolates all constraint instances for which the problem can be solved exactly. These multiple solutions enable us to even deal with `soft constraints' (higher order penalty functions). Moreover, we propose two practical variants of our algorithm to solve problems with hard constraints. We also show how our method can be applied to solve various constrained discrete optimization problems such as submodular minimization and shortest path computation. Experimental evaluation using the foreground-background image segmentation problem with statistic constraints reveals that our method is faster and its results are closer to the ground truth labellings compared with the popular continuous relaxation based methods.

arXiv:1308.2292

Fast image segmentation and restoration using parametric curve evolution with junctions and topology changes

Curve evolution schemes for image segmentation based on a region based contour model allowing for junctions, vector-valued images and topology changes are introduced. Together with an a posteriori denoising in the segmented homogeneous regions this leads to a fast and efficient method for image segmentation and restoration. An uneven spread of mesh points is avoided by using the tangential degrees of freedom. Several numerical simulations on artificial test problems and on real images illustrate the performance of the method.

arXiv:1310.7114

Efficient Information Theoretic Clustering on Discrete Lattices

We consider the problem of clustering data that reside on discrete, low dimensional lattices. Canonical examples for this setting are found in image segmentation and key point extraction. Our solution is based on a recent approach to information theoretic clustering where clusters result from an iterative procedure that minimizes a divergence measure. We replace costly processing steps in the original algorithm by means of convolutions. These allow for highly efficient implementations and thus significantly reduce runtime. This paper therefore bridges a gap between machine learning and signal processing.

arXiv:1306.6269

Active Contour Models for Manifold Valued Image Segmentation

Image segmentation is the process of partitioning a image into different regions or groups based on some characteristics like color, texture, motion or shape etc. Active contours is a popular variational method for object segmentation in images, in which the user initializes a contour which evolves in order to optimize an objective function designed such that the desired object boundary is the optimal solution. Recently, imaging modalities that produce Manifold valued images have come up, for example, DT-MRI images, vector fields. The traditional active contour model does not work on such images. In this paper, we generalize the active contour model to work on Manifold valued images. As expected, our algorithm detects regions with similar Manifold values in the image. Our algorithm also produces expected results on usual gray-scale images, since these are nothing but trivial examples of Manifold valued images. As another application of our general active contour model, we perform texture segmentation on gray-scale images by first creating an appropriate Manifold valued image. We demonstrate segmentation results for manifold valued images and texture images.

arXiv:1311.6054

Q-learning optimization in a multi-agents system for image segmentation

To know which operators to apply and in which order, as well as attributing good values to their parameters is a challenge for users of computer vision. This paper proposes a solution to this problem as a multi-agent system modeled according to the Vowel approach and using the Q-learning algorithm to optimize its choice. An implementation is given to test and validate this method.

arXiv:1311.4296

Reflection methods for user-friendly submodular optimization

Recently, it has become evident that submodularity naturally captures widely occurring concepts in machine learning, signal processing and computer vision. Consequently, there is need for efficient optimization procedures for submodular functions, especially for minimization problems. While general submodular minimization is challenging, we propose a new method that exploits existing decomposability of submodular functions. In contrast to previous approaches, our method is neither approximate, nor impractical, nor does it need any cumbersome parameter tuning. Moreover, it is easy to implement and parallelize. A key component of our method is a formulation of the discrete submodular minimization problem as a continuous best approximation problem that is solved through a sequence of reflections, and its solution can be easily thresholded to obtain an optimal discrete solution. This method solves both the continuous and discrete formulations of the problem, and therefore has applications in learning, inference, and reconstruction. In our experiments, we illustrate the benefits of our method on two image segmentation tasks.

arXiv:1312.0760

Template-Based Active Contours

We develop a generalized active contour formalism for image segmentation based on shape templates. The shape template is subjected to a restricted affine transformation (RAT) in order to segment the object of interest. RAT allows for translation, rotation, and scaling, which give a total of five degrees of freedom. The proposed active contour comprises an inner and outer contour pair, which are closed and concentric. The active contour energy is a contrast function defined based on the intensities of pixels that lie inside the inner contour and those that lie in the annulus between the inner and outer contours. We show that the contrast energy functional is optimal under certain conditions. The optimal RAT parameters are computed by maximizing the contrast function using a gradient descent optimizer. We show that the calculations are made efficient through use of Green's theorem. The proposed formalism is capable of handling a variety of shapes because for a chosen template, optimization is carried with respect to the RAT parameters only. The proposed formalism is validated on multiple images to show robustness to Gaussian and Poisson noise, to initialization, and to partial loss of structure in the object to be segmented.

arXiv:1312.4074

Clustering using Vector Membership: An Extension of the Fuzzy C-Means Algorithm

Clustering is an important facet of explorative data mining and finds extensive use in several fields. In this paper, we propose an extension of the classical Fuzzy C-Means clustering algorithm. The proposed algorithm, abbreviated as VFC, adopts a multi-dimensional membership vector for each data point instead of the traditional, scalar membership value defined in the original algorithm. The membership vector for each point is obtained by considering each feature of that point separately and obtaining individual membership values for the same. We also propose an algorithm to efficiently allocate the initial cluster centers close to the actual centers, so as to facilitate rapid convergence. Further, we propose a scheme to achieve crisp clustering using the VFC algorithm. The proposed, novel clustering scheme has been tested on two standard data sets in order to analyze its performance. We also examine the efficacy of the proposed scheme by analyzing its performance on image segmentation examples and comparing it with the classical Fuzzy C-means clustering algorithm.

arXiv:1312.4746

Co-Sparse Textural Similarity for Image Segmentation

We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation within a convex multilabel optimization framework. As a key ingredient of this method, we introduce a novel textural similarity measure, which builds upon the co-sparse representation of image patches. We propose a Bayesian approach to merge textural similarity with information about color and location. Combined with recently developed convex multilabel optimization methods this leads to an efficient algorithm for both supervised and unsupervised segmentation, which is easily parallelized on graphics hardware. The approach provides competitive results in unsupervised segmentation and outperforms state-of-the-art interactive segmentation methods on the Graz Benchmark.

arXiv:1401.2686

A parameterless scale-space approach to find meaningful modes in histograms - Application to image and spectrum segmentation

In this paper, we present an algorithm to automatically detect meaningful modes in a histogram. The proposed method is based on the behavior of local minima in a scale-space representation. We show that the detection of such meaningful modes is equivalent in a two classes clustering problem on the length of minima scale-space curves. The algorithm is easy to implement, fast, and does not require any parameters. We present several results on histogram and spectrum segmentation, grayscale image segmentation and color image reduction.

arXiv:1401.5891

Hierarchical pixel clustering for image segmentation

In the paper a piecewise constant image approximations of sequential number of pixel clusters or segments are treated. A majorizing of optimal approximation sequence by hierarchical sequence of image approximations is studied. Transition from pixel clustering to image segmentation by reducing of segment numbers in clusters is provided. Algorithms are proved by elementary formulas.

arXiv:1401.5098

Study of Efficient Technique Based On 2D Tsallis Entropy For Image Thresholding

Thresholding is an important task in image processing. It is a main tool in pattern recognition, image segmentation, edge detection and scene analysis. In this paper, we present a new thresholding technique based on two-dimensional Tsallis entropy. The two-dimensional Tsallis entropy was obtained from the twodimensional histogram which was determined by using the gray value of the pixels and the local average gray value of the pixels, the work it was applied a generalized entropy formalism that represents a recent development in statistical mechanics. The effectiveness of the proposed method is demonstrated by using examples from the real-world and synthetic images. The performance evaluation of the proposed technique in terms of the quality of the thresholded images are presented. Experimental results demonstrate that the proposed method achieve better result than the Shannon method.

arXiv:1402.0595

Scene Labeling with Contextual Hierarchical Models

Scene labeling is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in scene labeling frameworks has been widely realized in the field. We propose a contextual framework, called contextual hierarchical model (CHM), which learns contextual information in a hierarchical framework for scene labeling. At each level of the hierarchy, a classifier is trained based on downsampled input images and outputs of previous levels. Our model then incorporates the resulting multi-resolution contextual information into a classifier to segment the input image at original resolution. This training strategy allows for optimization of a joint posterior probability at multiple resolutions through the hierarchy. Contextual hierarchical model is purely based on the input image patches and does not make use of any fragments or shape examples. Hence, it is applicable to a variety of problems such as object segmentation and edge detection. We demonstrate that CHM outperforms state-of-the-art on Stanford background and Weizmann horse datasets. It also outperforms state-of-the-art edge detection methods on NYU depth dataset and achieves state-of-the-art on Berkeley segmentation dataset (BSDS 500).

arXiv:1402.1331

An Estimation Method of Measuring Image Quality for Compressed Images of Human Face

Nowadays digital image compression and decompression techniques are very much important. So our aim is to calculate the quality of face and other regions of the compressed image with respect to the original image. Image segmentation is typically used to locate objects and boundaries (lines, curves etc.)in images. After segmentation the image is changed into something which is more meaningful to analyze. Using Universal Image Quality Index(Q),Structural Similarity Index(SSIM) and Gradient-based Structural Similarity Index(G-SSIM) it can be shown that face region is less compressed than any other region of the image.

arXiv:1302.3283

StructBoost: Boosting Methods for Predicting Structured Output Variables

Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost. StructBoost supports nonlinear structured learning by combining a set of weak structured learners. As SSVM generalizes SVM, our StructBoost generalizes standard boosting approaches such as AdaBoost, or LPBoost to structured learning. The resulting optimization problem of StructBoost is more challenging than SSVM in the sense that it may involve exponentially many variables and constraints. In contrast, for SSVM one usually has an exponential number of constraints and a cutting-plane method is used. In order to efficiently solve StructBoost, we formulate an equivalent $ 1 $-slack formulation and solve it using a combination of cutting planes and column generation. We show the versatility and usefulness of StructBoost on a range of problems such as optimizing the tree loss for hierarchical multi-class classification, optimizing the Pascal overlap criterion for robust visual tracking and learning conditional random field parameters for image segmentation.

arXiv:1402.5805

Automatic Estimation of Live Coffee Leaf Infection based on Image Processing Techniques

Image segmentation is the most challenging issue in computer vision applications. And most difficulties for crops management in agriculture are the lack of appropriate methods for detecting the leaf damage for pests treatment. In this paper we proposed an automatic method for leaf damage detection and severity estimation of coffee leaf by avoiding defoliation. After enhancing the contrast of the original image using LUT based gamma correction, the image is processed to remove the background, and the output leaf is clustered using Fuzzy c-means segmentation in V channel of YUV color space to maximize all leaf damage detection, and finally, the severity of leaf is estimated in terms of ratio for leaf pixel distribution between the normal and the detected leaf damage. The results in each proposed method was compared to the current researches and the accuracy is obvious either in the background removal or damage detection.

arXiv:1403.0240

Particle methods enable fast and simple approximation of Sobolev gradients in image segmentation

Bio-image analysis is challenging due to inhomogeneous intensity distributions and high levels of noise in the images. Bayesian inference provides a principled way for regularizing the problem using prior knowledge. A fundamental choice is how one measures "distances" between shapes in an image. It has been shown that the straightforward geometric L2 distance is degenerate and leads to pathological situations. This is avoided when using Sobolev gradients, rendering the segmentation problem less ill-posed. The high computational cost and implementation overhead of Sobolev gradients, however, have hampered practical applications. We show how particle methods as applied to image segmentation allow for a simple and computationally efficient implementation of Sobolev gradients. We show that the evaluation of Sobolev gradients amounts to particle-particle interactions along the contour in an image. We extend an existing particle-based segmentation algorithm to using Sobolev gradients. Using synthetic and real-world images, we benchmark the results for both 2D and 3D images using piecewise smooth and piecewise constant region models. The present particle approximation of Sobolev gradients is 2.8 to 10 times faster than the previous reference implementation, but retains the known favorable properties of Sobolev gradients. This speedup is achieved by using local particle-particle interactions instead of solving a global Poisson equation at each iteration. The computational time per iteration is higher for Sobolev gradients than for L2 gradients. Since Sobolev gradients precondition the optimization problem, however, a smaller number of overall iterations may be necessary for the algorithm to converge, which can in some cases amortize the higher per-iteration cost.