Search

Considering a wide range of applications of nonnegative matrix factorization (NMF), many NMF and their variants have been developed. Since previous NMF methods cannot fully describe complex inner global and local manifold structures of the data space and extract complex structural information, we propose a novel NMF method called dual-graph global and local concept factorization (DGLCF). To properly describe the inner manifold structure, DGLCF introduces the global and local structures of the data manifold and the geometric structure of the feature manifold into CF. The global manifold structure makes the model more discriminative, while the two local regularization terms simultaneously preserve the inherent geometry of data and features. Finally, we analyze convergence and the iterative update rules of DGLCF. We illustrate clustering performance by comparing it with latest algorithms on four real-world datasets.

With the three-dimensional (3D) coordinates of objects captured by a sequence of images taken in different views, object reconstruction is a technique which aims to recover the shape and appearance information of objects. Although great progress in object reconstruction has been made over the past few years, object reconstruction in occlusion situations remains a challenging problem. In this paper, we propose a novel method to reconstruct occluded objects based on synthetic aperture imaging. Unlike most existing methods, which either assume that there is no occlusion in the scene or remove the occlusion from the reconstructed result, our method uses the characteristics of synthetic aperture imaging that can effectively reduce the influence of occlusion to reconstruct the scene with occlusion. The proposed method labels occlusion pixels according to variance and reconstructs the 3D point cloud based on synthetic aperture imaging. Accuracies of the point cloud are tested by calculating the spatial difference between occlusion and non-occlusion conditions. The experiment results show that the proposed method can handle the occluded situation well and demonstrates a promising performance.

Purpose: Bioluminescence tomography (BLT) can provide in vivo three-dimensional (3D) images for quantitative analysis of biological processes in preclinical small animal studies, which is superior than the conventional planar bioluminescence imaging. However, to reconstruct light sources under the skin in 3D with desirable accuracy and efficiency, BLT has to face the ill-posed and ill-conditioned inverse problem. In this paper, we developed a new method for BLT reconstruction, which utilized the mathematical strategies of the split Bregman iterative and surrogate functions (SBISF) method., Procedures: The proposed method considered the sparsity characteristic of the reconstructed sources. Thus, the sparsity itself was regarded as a kind of a priori information, and the sparse regularization is incorporated, which can accurately locate the position of the sources. Numerical simulation experiments of multisource cases with comparative analyses were performed to evaluate the performance of the proposed method. Then, a bead-implanted mouse and a breast cancer xenograft mouse model were employed to validate the feasibility of this method in in vivo experiments., Results: The results of both simulation and in vivo experiments indicated that comparing with the L1-norm iteration shrinkage method and non-monotone spectral projected gradient pursuit method, the proposed SBISF method provided the smallest position error with the least amount of time consumption., Conclusions: The SBISF method is able to achieve high accuracy and high efficiency in BLT reconstruction and hold great potential for making BLT more practical in small animal studies.

Purpose: Bioluminescence tomography (BLT) is a promising in vivo optical imaging technique in preclinical research at cellular and molecular levels. The problem of BLT reconstruction is quite ill-posed and ill-conditioned. In order to achieve high accuracy and efficiency for its inverse reconstruction, we proposed a novel approach based on L p regularization with the Split Bregman method., Procedures: The diffusion equation was used as the forward model. Then, we defined the objective function of L p regularization and developed a Split Bregman iteration algorithm to optimize this function. After that, we conducted numerical simulations and in vivo experiments to evaluate the accuracy and efficiency of the proposed method., Results: The results of the simulations indicated that compared with the conjugate gradient and iterative shrinkage methods, the proposed method is more accurate and faster for multisource reconstructions. Furthermore, in vivo imaging suggested that it could clearly distinguish the viable and apoptotic tumor regions., Conclusions: The Split Bregman iteration method is able to minimize the L p regularization problem and achieve fast and accurate reconstruction in BLT.

Image registration is a key problem in a variety of applications, such as computer vision, medical image processing, pattern recognition, etc., while the application of registration is limited by time consumption and the accuracy in the case of large pose differences. Aimed at these two kinds of problems, we propose a fast rotation-free feature-based rigid registration method based on our proposed accelerated-NSIFT and GMM registration-based parallel optimization (PO-GMMREG). Our method is accelerated by using the GPU/CUDA programming and preserving only the location information without constructing the descriptor of each interest point, while its robustness to missing correspondences and outliers is improved by converting the interest point matching to Gaussian mixture model alignment. The accuracy in the case of large pose differences is settled by our proposed PO-GMMREG algorithm by constructing a set of initial transformations. Experimental results demonstrate that our proposed algorithm can fast rigidly register 3-D medical images and is reliable for aligning 3-D scans even when they exhibit a poor initialization.

This paper presents a novel perspective on characterizing the spectral correspondence between the nodes of weighted graphs for image matching applications. The algorithm is based on the principal feature components obtained by stochastic perturbation of a graph. There are three areas of contributions in this paper. First, a stochastic normalized Laplacian matrix of a weighted graph is obtained by perturbing the matrix of a sensed graph model. Second, we obtain the eigenvectors based on an eigen-decomposition approach, where representative elements of each row of this matrix can be considered to be the feature components of a feature point. Third, correct correspondences are determined in a low-dimensional principal feature component space between the graphs. In order to further enhance image matching, we also exploit the random sample consensus algorithm, as a post-processing step, to eliminate mismatches in feature correspondences. The experiments on synthetic and real-world images demonstrate the effectiveness and accuracy of the proposed method.

Optical molecular imaging is a promising technique and has been widely used in physiology, and pathology at cellular and molecular levels, which includes different modalities such as bioluminescence tomography, fluorescence molecular tomography and Cerenkov luminescence tomography. The inverse problem is ill-posed for the above modalities, which cause a nonunique solution. In this paper, we propose an effective reconstruction method based on the linearized Bregman iterative algorithm with sparse regularization (LBSR) for reconstruction. Considering the sparsity characteristics of the reconstructed sources, the sparsity can be regarded as a kind of a priori information and sparse regularization is incorporated, which can accurately locate the position of the source. The linearized Bregman iteration method is exploited to minimize the sparse regularization problem so as to further achieve fast and accurate reconstruction results. Experimental results in a numerical simulation and in vivo mouse demonstrate the effectiveness and potential of the proposed method.

Cerenkov luminescence imaging is an emerging optical technique for imaging the distribution of radiopharmaceuticals in vivo. However, because of the light scattering effect, it cannot obtain optical information from deep internal organs. To overcome this challenge, we established a novel endoscopic Cerenkov luminescence imaging system that used a clinically approved laparoscope and an electron-multiplying charge-coupled device camera. We assessed the performance of the system through a series of in vitro and in vivo experiments. The results demonstrated superior superficial imaging resolution (0.1 mm), a large field of view (500 mm2 with 10 mm imaging distance), and superb imaging sensitivity (imaging 1 μCi) of our system. It captured the weak Cerenkov signal from internal organs successfully and was applied to intraoperative surgical navigation of tumor resection. It offered objective information of the tumor location and tumor residual during the surgical operation. This technique holds great potential for clinical translation.

This paper proposes a novel robust adaptive principal component analysis (RAPCA) method based on intergraph matrix for image registration in order to improve robustness and real-time performance. The contributions can be divided into three parts. Firstly, a novel RAPCA method is developed to capture the common structure patterns based on intergraph matrix of the objects. Secondly, the robust similarity measure is proposed based on adaptive principal component. Finally, the robust registration algorithm is derived based on the RAPCA. The experimental results show that the proposed method is very effective in capturing the common structure patterns for image registration on real-world images.