Reduced set density estimator for object segmentation based on shape probabilistic representation

In this paper, a nonparametric statistical shape model based on shape probabilistic representation is proposed for object segmentation. Given a set of training shapes, Cremers et al.’s probabilistic method is adopted to represent the shape, and then principal components analysis (PCA) on shape probabilistic representation is computed to capture the variation of the training shapes. To encode complex shape variation in training set, reduced set density estimator is used to model nonlinear shape distributions in a finite-dimensional subspace. This statistical shape prior is integrated to convex segmentation functional to guide the evolving contour to the object of interest. In addition, in contrast to the commonly used signed distance functions, PCA on shape probabilistic representation needs less number of eigenmodes to capture certain details of the training shapes. Numerical experiments show promising results and the potential of the model for object segmentation.     

3D Shape Inferencing and Modeling for Video Retrieval

We present a geometry-based indexing approach for the retrieval of video databases. It consists of two modules: 3D object shape inferencing from video data and geometric modeling from the reconstructed shape structure. A motion-based segmentation algorithm employing feature block tracking and principal component split is used for multi-moving-object motion classification and segmentation. After segmentation, feature blocks from each individual object are used to reconstruct its motion and structure through a factorization method. The estimated shape structure and motion parameters are used to generate the implicit polynomial model for the object. The video data is retrieved using the geometric structure of objects and their spatial relationship. We generalize the 2D string to 3D to compactly encode the spatial relationship of objects.     

Multiscale autoregressive models and wavelets

The multiscale autoregressive (MAR) framework was introduced to support the development of optimal multiscale statistical signal processing. Its power resides in the fast and flexible algorithms to which it leads. While the MAR framework was originally motivated by wavelets, the link between these two worlds has been previously established only in the simple case of the Haar wavelet. The first contribution of this paper is to provide a unification of the MAR framework and all compactly supported wavelets as well as a new view of the multiscale stochastic realization problem. The second contribution of this paper is to develop wavelet-based approximate internal MAR models for stochastic processes. This will be done by incorporating a powerful synthesis algorithm for the detail coefficients which complements the usual wavelet reconstruction algorithm for the scaling coefficients. Taking advantage of the statistical machinery provided by the MAR framework, we will illustrate the application of our models to sample-path generation and estimation from noisy, irregular, and sparse measurements     

Coherent multiscale image processing using dual-tree quaternion wavelets

The dual-tree quaternion wavelet transform (QWT) is a new multiscale analysis tool for geometric image features. The QWT is a near shift-invariant tight frame representation whose coefficients sport a magnitude and three phases: two phases encode local image shifts while the third contains image texture information. The QWT is based on an alternative theory for the 2-D Hilbert transform and can be computed using a dual-tree filter bank with linear computational complexity. To demonstrate the properties of the QWT's coherent magnitude/phase representation, we develop an efficient and accurate procedure for estimating the local geometrical structure of an image. We also develop a new multiscale algorithm for estimating the disparity between a pair of images that is promising for image registration and flow estimation applications. The algorithm features multiscale phase unwrapping, linear complexity, and sub-pixel estimation accuracy.     

Structure-prior deep neural network for lane detection

Lane detection is an important task of road environment perception for autonomous driving. Deep learning methods based on semantic segmentation have been successfully applied to lane detection, but they require considerable computational cost for high complexity. The lane detection is treated as a particular semantic segmentation task due to the prior structural information of lane markings which have long continuous shape. Most traditional CNN are designed for the representation learning of semantic information, while this prior structural information is not fully exploited. In this paper, we propose a recurrent slice convolution module (called RSCM) to exploit the prior structural information of lane markings. The proposed RSCM is a special recurrent network structure with several slice convolution units (called SCU). The RSCM could obtain stronger semantic representation through the propagation of the prior structural information in SCU. Furthermore, we design a distance loss in consideration of the prior structure of lane markings. The lane detection network can be trained more steadily via the overall loss function formed by combining segmentation loss with the distance loss. The experimental results show the effectiveness of our method. We achieve excellent computation efficiency while keeping decent detection quality on lane detection benchmarks and the computational cost of our method is much lower than the state-of-the-art methods.     

SAR图像压缩的多尺度自回归滑动平均模型方法

本文研究在无需SAR图像先验知识条件下,基于多尺度自回归滑动平均MARMA模型的SAR图像压缩方法.该方法首先对SAR图像建立MARMA模型,依据MARMA模型对原始图像进行预测,然后对预测的残量进行数据压缩.将此方法用于实际SAR图像压缩,并将基于MARMA模型和多尺度自回归MAR模型的压缩结果与相应的JPEG结果进行比较和分析,说明基于MARMA模型的SAR图像压缩方法既能达到较高的压缩比,又能取得较好的保真度,是一种很有潜力的压缩方法.     

Vegetation segmentation based on variational level set using multi-channel local wavelet texture and color

The existing spectrum index-based methods for detecting vegetation coverage suffer from an over-dependence on spectrum. To address these issues, this paper proposes a graph cut-based variational level set segmentation algorithm that combines multi-channel local wavelet texture (MCLWT) and color. First, the prior color is generated by automatic estimation based on the mathematical morphology with a color histogram. Then, local wavelet texture features are extracted using a multi-scale and orientation Gabor wavelet transformation followed by local median and entropy filtering. Next, in addition to the energy of color, that of MCLWT is integrated into the variational level set model based on kernel density estimation. Consequently, all energies are integrated into the graph cut-based variational level set model. Finally, the proposed energy functional is made convex to obtain a global optimal solution, and a primal-dual algorithm with global relabeling is adopted to accelerate the evolution of the level sets. A comparison of the segmentation results from our proposed algorithm and other state-of-the-art algorithms showed that our algorithm effectively reduces the over-dependence on color and yields more accurate results in detecting vegetation coverage.     

Effect of Number of Coupled Structures on the Segmentation of Brain Structures

This paper reports the effect of the coupling information on the performance of model-based segmentation of the brain structures from magnetic resonance images (MRI). We have developed a three-dimensional, nonparametric, entropy-based, and multi-shape method that benefits from coupling of the shapes. The proposed method uses principal component analysis (PCA) to develop shape models that capture structural variability and integrates geometrical relationship among different structures into the algorithm by coupling them (limiting their independent deformations). At the same time, to allow variations of the coupled structures, it registers each structure individually when building the shape models. It defines an entropy-based energy function which is minimized using quasi-Newton algorithm. Probability density functions (pdf) are estimated iteratively using nonparametric Parzen window method. In the optimization algorithm, analytical derivatives are used for maximum speed and accuracy. Sample results are given for the segmentation of caudate, thalamus, putamen, pallidum, hippocampus, and amygdala illustrating superior performance of the proposed method compared to the most similar method in the literature. The similarity of the results obtained by the proposed method with the expert segmentation is 4% to 12% higher than that of the most similar method. Experimental studies show that the proposed coupling method, which regulates shape variability during segmentation, improves accuracy of the results of the proposed method by 6% and those of the other method by 1%. In addition, the more the structures are used in the coupling process, the more accurate the results are obtained.     

An orthogonal wavelet representation of multivalued images

A new orthogonal wavelet representation of multivalued images is presented. The idea for this representation is based on the concept of maximal gradient of multivalued images. This concept is generalized from gradients toward linear vector operators in the image plane with equal components along rows and columns. Using this generalization, the pyramidal dyadic wavelet transform algorithm using quadrature mirror filters is modified to be applied to multivalued images. This results in a representation of a single image, containing multiscale detail information from all component images involved. This representation leads to multiple applications ranging from multispectral image fusion to color and multivalued image enhancement, denoising and segmentation. In this paper, the representation is applied for fusion of images. More in particular, we introduce a scheme to merge high spatial resolution greylevel images with low spatial resolution multivalued images to improve spatial resolution of the latter while preserving spectral resolution. Two applications are studied: demosaicing of color images and merging of multispectral remote sensing images.     

Hidden Markov Bayesian texture segmentation using complex wavelet transform

The authors propose a multiscale Bayesian texture segmentation algorithm that is based on a complex wavelet domain hidden Markov tree (HMT) model and a hybrid label tree (HLT) model. The HMT model is used to characterise the statistics of the magnitudes of complex wavelet coefficients. The HLT model is used to fuse the interscale and intrascale context information. In the HLT, the interscale information is fused according to the label transition probability directly resolved by an EM algorithm. The intrascale context information is also fused so as to smooth out the variations in the homogeneous regions. In addition, the statistical model at pixel-level resolution is formulated by a Gaussian mixture model (GMM) in the complex wavelet domain at scale 1, which can improve the accuracy of the pixel-level model. The experimental results on several texture images are used to evaluate the algorithm.     

Multiscale curvature-based shape representation using B-splinewavelets

This paper presents a new multiscale curvature-based shape representation technique with application to curve data compression using B-spline wavelets. The evolution of the curve is implemented in the B-spline scale-space, which enjoys a number of advantages over the classical Gaussian scale-space, for instance, the availability of fast algorithms. The B-spline wavelet transforms are used to efficiently estimate the multiscale curvature functions. Based on the curvature scale-space image, we introduce a coarse-to-fine matching algorithm which automatically detects the dominant points and uses them as knots for curve interpolation.     

Neighbor-constrained segmentation with level set based 3-D deformable models

A novel method for the segmentation of multiple objects from three-dimensional (3-D) medical images using interobject constraints is presented. Our method is motivated by the observation that neighboring structures have consistent locations and shapes that provide configurations and context that aid in segmentation. We define a maximum a posteriori (MAP) estimation framework using the constraining information provided by neighboring objects to segment several objects simultaneously. We introduce a representation for the joint density function of the neighbor objects, and define joint probability distributions over the variations of the neighboring shape and position relationships of a set of training images. In order to estimate the MAP shapes of the objects, we formulate the model in terms of level set functions, and compute the associated Euler-Lagrange equations. The contours evolve both according to the neighbor prior information and the image gray level information. This method is useful in situations where there is limited interobject information as opposed to robust global atlases. In addition, we compare our level set representation of the object shape to the point distribution model. Results and validation from experiments on synthetic data and medical imagery in two-dimensional and 3-D are demonstrated.     

A Kernel PCA Shape Prior and Edge Based MRF Image Segmentation

We introduce both shape prior and edge information to Markov random field (MRF) to segment target of interest in images.Kernel Principal component analysis (PCA) is performed on a set of training shapes to obtain statistical shape representation.Edges are extracted directly from images.Both of them are added to the MRF energy function and the integrated energy function is minimized by graph cuts.An alignment procedure is presented to deal with variations between the target object and shape templates.Edge information makes the influence of inaccurate shape alignment not too severe,and brings result smoother.The experiments indicate that shape and edge play important roles for complete and robust foreground segmentation.     

Binary partition tree as an efficient representation for imageprocessing, segmentation, and information retrieval

This paper discusses the interest of binary partition trees as a region-oriented image representation. Binary partition trees concentrate in a compact and structured representation a set of meaningful regions that can be extracted from an image. They offer a multiscale representation of the image and define a translation invariant 2-connectivity rule among regions. As shown in this paper, this representation can be used for a large number of processing goals such as filtering, segmentation, information retrieval and visual browsing. Furthermore, the processing of the tree representation leads to very efficient algorithms. Finally, for some applications, it may be interesting to compute the binary partition tree once and to store it for subsequent use for various applications. In this context, the paper shows that the amount of bits necessary to encode a binary partition tree remains moderate.     

基于小波变换的指纹全局方向场重建简

从大型指纹库识别不完整或局部指纹仍然是今天的一大挑战。在此文中,我们研究利用小波变换用于指纹方向场重建问题。特别的,我们提出了一种基于小波的多尺度方法从局部的指纹重建全局拓扑表达。然后提出基于结合参数模型和非参数模型来描述重建问题,我们提供了一般表达式可用于所有有效的反变换模型的解决方案。这种方案允许我们分割保护存在的方向场同时预测丢失的未知部分的结构。我们还开发了基于脊线拓扑特征的一些先验信息来估计丢失的方向结构的算法。我们的统计实验表明我们提出的基于模型的算法能有效的恢复指纹的方向场并应用于指纹匹配,这样重大的提高了局部指纹识别其他模块性能。     

Color image segmentation using adaptive color quantization and multiresolution texture characterization

This paper presents a new hybrid color image segmentation approach, which attempts two different transforms for texture representation and extraction. The 2-D discrete wavelet transform that can express the variance in frequency and direction of textures, and the contourlet transform that represents boundaries even more accurately are applied in our algorithm. The whole segmentation algorithm contains three stages. First, an adaptive color quantization scheme is utilized to obtain a coarse image representation. Then, the tiny regions are combined based on color information. Third, the proposed energy transform function is used as a criterion for image segmentation. The motivation of the proposed method is to obtain the complete and significant objects in the image. Ultimately, according to our experiments on the Berkeley segmentation database, our techniques have more reasonable and robust results than other two widely adopted image segmentation algorithms, and our method with contourlet transform has better performance than wavelet transform.     

Continuous medial representation for anatomical structures

The m-rep approach pioneered by Pizer et al. (2003) is a powerful morphological tool that makes it possible to employ features derived from medial loci (skeletons) in shape analysis. This paper extends the medial representation paradigm into the continuous realm, modeling skeletons and boundaries of three-dimensional objects as continuous parametric manifolds, while also maintaining the proper geometric relationship between these manifolds. The parametric representation of the boundary-medial relationship makes it possible to fit shape-based coordinate systems to the interiors of objects, providing a framework for combined statistical analysis of shape and appearance. Our approach leverages the idea of inverse skeletonization, where the skeleton of an object is defined first and the object's boundary is derived analytically from the skeleton. This paper derives a set of sufficient conditions ensuring that inverse skeletonization is well-posed for single-manifold skeletons and formulates a partial differential equation whose solutions satisfy the sufficient conditions. An efficient variational algorithm for deformable template modeling using the continuous medial representation is described and used to fit a template to the hippocampus in 87 subjects from a schizophrenia study with sub-voxel accuracy and 95% mean overlap.