Yurun Ma

Plant recognition based on intersecting cortical model

Plant recognition recently becomes more and more attractive in computer vision and pattern recognition. Although some researchers have proposed several methods, their accuracy is not satisfactory. Therefore, a novel method of plant recognition based on leaf image is proposed in the paper. Both shape and texture features are employed in the proposed method Texture feature is extracted by intersecting cortical model, and shape feature is obtained by the representation of center distance sequence. Support vector machine is employed for the classifier. The leaf image is preprocessed to get better quality for extracting features, and then entropy sequence and center distance sequence are obtained by intersecting cortical model and center distance transform, respectively. Redundant data of entropy sequence vector and center distance are reduced by principal component analysis. Finally, feature vector is imported into the classifier for classification. In order to evaluate the performance, several existing methods are used to compare with the proposed method and three leaf image datasets are taken as test samples. The experimental result shows the proposed method gets the better accuracy of recognition than other methods.

Robust unsupervised feature selection via matrix factorization

We proposed a robust unsupervised method to remove redundant and irrelevant features.Both the cluster centers and the sparse representation are predicted.The feature selection and clustering are performed simultaneously.An efficient iterative update algorithm based on ADMM is proposed.Superiority over seven existing methods is established for five data sets. Dimensionality reduction is a challenging task for high-dimensional data processing in machine learning and data mining. It can help to reduce computation time, save storage space and improve the performance of learning algorithms. As an effective dimension reduction technique, unsupervised feature selection aims at finding a subset of features to retain the most relevant information. In this paper, we propose a novel unsupervised feature selection method, called Robust Unsupervised Feature Selection via Matrix Factorization (RUFSM), in which robust discriminative feature selection and robust clustering are performed simultaneously under l2, 1-norm while the local manifold structures of data are preserved. The advantages of this work are three-fold. Firstly, both the latent orthogonal cluster centers and the sparse representation of the projected data points based on matrix factorization are predicted for selecting robust discriminative features. Secondly, the feature selection and the clustering are performed simultaneously to guarantee an overall optimum. Thirdly, an efficient iterative update algorithm, which is based on Alternating Direction Method of Multipliers (ADMM), is used for RUFSM optimization. Compared with several state-of-the-art unsupervised feature selection methods, the proposed algorithm comes with better clustering performance for almost all datasets we have experimented with here.

Graph regularized compact low rank representation for subspace clustering

Low rank representation (LRR) is one of the state-of-the-art methods for subspace clustering and it has been used widely in machine learning, data mining, and pattern recognition. The main objective of LRR is to seek the lowest rank representations for data points based on a given dictionary. However, the current LRR-based approaches have the following drawbacks: 1) the original data, which are used as a dictionary in LRR, usually contain noise and they may not be representative; and 2) the affinity matrix and subspace clustering are obtained in two independent steps; thus, an overall optimum cannot be guaranteed. Therefore, we propose an improved LRR-based approach, called Graph regularized Compact LRR (GCLRR), where dictionary learning and low-rank, low-dimensional representation are achieved simultaneously, and the low-dimensional representation used for subspace clustering captures both the global subspace structure (by the low-rankness) and the local manifold structure (by manifold regularization) of the original data. Finally, the mixed norm l2, 1 is used to measure the dissimilarity between the original data and its low rank approximation to make the model robust. An efficient optimization procedure based on Alternating Direction Method of Multipliers is used for GCLRR optimization. We verified the effectiveness and robustness of the proposed method based on extensive experiments using both synthetic and real data sets, which demonstrated its higher clustering capacity compared with state-of-the-art LRR-based clustering algorithms.

An Effective Approach for Automatic LV Segmentation Based on GMM and ASM

In this paper, we propose a novel approach for automatic left ventricle LV segmentation in cardiac magnetic resonance images CMRI. This algorithm incorporates three key techniques: 1 the mid-ventricular coarse segmentation based on Gaussian mixture model GMM; 2 the mid-slice endo-/epi-cardial initialization based on geometric transformation; 3 the myocardium tracking based on active shape models ASM. Experiment results tested on a standard database demonstrate the effectiveness and competitiveness of the proposed method.

Automatic left ventricle segmentation in cardiac MRI via level set and fuzzy C-means

Magnetic resonance imaging (MRI) has become an important assistant for clinical diagnosis of cardiac diseases which can not only observe the morphological structure of the heart, but also estimate the global and local function of myocardium. It is necessary to segment the left ventricle (LV) for the quantitative analysis of the global and regional cardiac function. However, cardiac MR images are usually intensity inhomogeneity, which results in a considerable challenge in left ventricle segmentation. In this research, we presented a synthetically automatic LV segmentation model on basis of modified level set and fuzzy C-means. We used level set method to delineate the endocardium and estimated the bias field which was used to decrease the intensity inhomogeneity of cardiac image. In addition, the fuzzy C-means algorithm and morphologic segmentation were applied in the corrected MR image to segment the epicardium. For the algorithm evaluation, we tested the short axis cardiac cine MR images published by MICCAI. The experiment results showed that our method obtained a good performance for both the endocardium and the epicardium segmentation. And, it was more effective to delineate epicardium in the corrected image than the original image.

Automatic right ventricle segmentation in cardiac MRI via anisotropic diffusion and SPCNN

Cardiac Magnetic Resonance Image (CMRI) is a significant assistant for the cardiovascular disease clinical diagnosis. The segmentation of right ventricle (RV) is essential for cardiac function evaluation, especially for RV function measurement. Automatic RV segmentation is difficult due to the intensity inhomogeneity and the irregular shape. In this paper, we propose an automatic RV segmentation framework. Firstly, we use the anisotropic diffusion to filter the CMRI. And then, the endocardium is extracted by the simplified pulse coupled neural network (SPCNN) segmentation. At last, the morphologic processors are used to obtain the epicardium. The experiment results show that our method obtains a good performance for both the endocardium and the epicardium segmentation.

Novel approach for automatic segmentation of LV endocardium via SPCNN

Automatic segmentation of Left Ventricle (LV) is an essential task in the field of computer-aided analysis of cardiac function. In this paper, a simplified pulse coupled neural network (SPCNN) based approach is proposed to segment LV endocardium automatically. Different from the traditional image-driven methods, the SPCNN based approach is independent of the image gray distribution models, which makes it more stable. Firstly, the temporal and spatial characteristics of the cardiac magnetic resonance image are used to extract a region of interest and to locate LV cavity. Then, SPCNN model is iteratively applied with an increasing parameter to segment an optimal cavity. Finally, the endocardium is delineated via several post-processing operations. Quantitative evaluation is performed on the public database provided by MICCAI 2009. Over all studies, all slices, and two phases (end-diastole and end-systole), the average percentage of good contours is 91.02%, the average perpendicular distance is 2.24 mm and the overlapping dice metric is 0.86.These results indicate that the proposed approach possesses high precision and good competitiveness.

A New Study on Mammographic Image Denoising using Multiresolution Techniques

Mammography is the most simple and effective technology for early detection of breast cancer. However, the lesion areas of breast are difficult to detect which due to mammograms are mixed with noise. This work focuses on discussing various multiresolution denoising techniques which include the classical methods based on wavelet and contourlet; moreover the emerging multiresolution methods are also researched. In this work, a new denoising method based on dual tree contourlet transform (DCT) is proposed, the DCT possess the advantage of approximate shift invariant, directionality and anisotropy. The proposed denoising method is implemented on the mammogram, the experimental results show that the emerging multiresolution method succeeded in maintaining the edges and texture details; and it can obtain better performance than the other methods both on visual effects and in terms of the Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Structure Similarity (SSIM) values.

MULTIFOCUS IMAGE FUSION BASED ON NONSUBSAMPLED CONTOURLET TRANSFORM AND SPIKING CORTICAL MODEL

In recent years, image fusion has become the focus of image processing. For the fusion problems of the multifocus images with the same scence, this paper proposed a new fusion method based on nonsampled contourlet transform(NSCT). Firstly, source images are decomposed in different scales and directions by NSCT, thus the low frequency subband coefficients and the high frequency subband coefficients are obtained. Secondly, for the low frequency subband coefficients, we present a fusion rule based on the local entropy; while for the high frequency subband coefficients, a fusion rule based on the directional contrast combined with the local area energy is applied. Finally, the fused image is obtained through the inverse NSCT. Compared with the fusion method based wavelet and other fusion methods, the experiments show that this approach can achieve better results than them.

The real-time R-wave detection based on FPGA

R-wave detection is one of the most significant parts in Electrocardiogram (ECG) signal studies and plays an important role in the automatic ECG analysis system. In this research, we design a prototype of portable automatic ECG analysis system based on field programmable gate array (FPGA) using Altera DE2-70 development board. The system includes four parts: 1)Data input, 2)ECG denoising, 3)ECG analysis and R-wave detection, 4) Results display. In this paper, we use the data from the well-known MIT/BIH arrhythmia database. CDF9/7 wavelet filter is used to remove the high-frequency noise and the threshold method is used to detect the R-wave. In addition, In the Quartus II 9.0 development environment, we complete the simulation and synthesis. Experimental results based on the system show that proposed architecture can detect R-wave accurately and the utilization percent of resource is low, just 6%.