A nonlinear image enhancement algorithm based on single scale retinex was proposed. Unlike classical retinex methods estimate the illumination image in a complex way, the proposed algorithm estimates the illumination ...
详细信息
A nonlinear image enhancement algorithm based on single scale retinex was proposed. Unlike classical retinex methods estimate the illumination image in a complex way, the proposed algorithm estimates the illumination image approximately, and then compensates the approximate estimation in a nonlinear way. Compared with classical retinex methods, the experimental results show that the proposed method can offer better performance not only in visual enhancement but also in fast processing.
A kind of subspace clustering algorithm based on density and grids was proposed. Boundaries between classes are located by partitioning grids in the data space and finding sparse regions. The algorithm uses the search...
详细信息
A kind of subspace clustering algorithm based on density and grids was proposed. Boundaries between classes are located by partitioning grids in the data space and finding sparse regions. The algorithm uses the searching strategy of projected pursuit to find the classes in the subspace. A competitive pruning procedure is utilized to reduce the computational complexity. The experimental results on the benchmark datasets show that the proposed algorithm has advantages in accuracy and computational complexity.
Automated tongue image segmentation in tongue diagnosis system of traditional Chinese medicine is difficult due to two factors: There are lots of pathological details on the surface of tongue, and the shapes of tongue...
详细信息
A novel 3D terrain matching algorithm is presented in this paper. A terrain feature vector map (FVM), composed of local mean and local gradient, is employed to represent the terrain elevation map (TEM). Compared with ...
详细信息
ISBN:
(纸本)9780819469519
A novel 3D terrain matching algorithm is presented in this paper. A terrain feature vector map (FVM), composed of local mean and local gradient, is employed to represent the terrain elevation map (TEM). Compared with traditional matching algorithm using the magnitude of gradient to match, the new algorithm uses each component of the gradient vector to match individually, and it is able to generate two interim matching positions. Different from traditional matching algorithms which usually estimate an optimum matching position under some criterions at the end, the new algorithm fused the two interim matching positions to generate a final matching position or refuse to position in order to increase the matching confidence, which is very important because it is hardly acceptable to employ a mismatched position to correct the error of Inertial Navigation System (INS). Due to the stability of terrain and the high-precision of lidar ranging, the mean of a sensed terrain elevation map (STEM) sized terrain is quite stable. So it is bestowed to accelerate the matching process and to reduce mismatches at different terrain heights. Compared with other mismatch-eliminated methods based on neural network (NN) or support vector machine (SVM), the new method do not need training samples and is more stable and robust. Experimental results show that the proposed algorithm is effective and robust.
The sliding window method will cause the severe unbalanced dataset problem. In this paper, under-sample the majority class method is adopted to solve this problem,and SVM is used to classify the processed data The bet...
详细信息
The sliding window method will cause the severe unbalanced dataset problem. In this paper, under-sample the majority class method is adopted to solve this problem,and SVM is used to classify the processed data The better prediction result of minority class (that is, the signal peptides positive sample set) is ***, we discover that the (-3,-1) rule is helpful to the prediction. So Information content based feature weighting method is proposed This method avoids the blindness of the previous algorithm in dealing with different sites. Experiments show that not only is the correct prediction rate of minority class improved dramatically, but also the correct prediction rate of majority class is kept in a high *** of the unbalanced data processing and the proposed information content based feature weighting method can greatly improve the performance of SVM classifier of signal peptides.
Linear Discriminant Analysis (LDA) is frequently used for dimension reduction and has been successfully utilized in many applications, especially face recognition. In classical LDA, however, the definition of the betw...
详细信息
Due to ear's complex structure, particular position, and preferable stability, ear biometrics has attracted increasingly attention recently. In this paper, we present a new multi-view based ear feature extraction ...
详细信息
Due to ear's complex structure, particular position, and preferable stability, ear biometrics has attracted increasingly attention recently. In this paper, we present a new multi-view based ear feature extraction strategy. We utilize not only front view ear image but backside view ear image to extract 2D ear shape four kinds of rich features for ear recognition. In addition, we utilize multi-view ear images to reconstruct 3D ear shape, and a neural network 3D ear registration method is introduced also. Experimental results and comparison analysis show our multi-view based strategy will be a promising approach for ear biometrics.
Proposed is a novel theory for SAR (synthetic aperture radar) image de-noising based on ICA (independent component analysis) basis images. Firstly, the basis images and the code matrix of the original image are obtain...
详细信息
Proposed is a novel theory for SAR (synthetic aperture radar) image de-noising based on ICA (independent component analysis) basis images. Firstly, the basis images and the code matrix of the original image are obtained using ICA algorithm. Then, pointwise Holder exponent of each basis is computed as a cost criterion for basis enhancement, and then the enhanced basis images are classified into two sets according to a separation rule which means the clean basis can be separated from the original basis. These two procedures are the key points for speckle reduction. Finally, the clean image is obtained by reconstruction on the clean basis and original code matrix. As the results show, the reconstructed image achieves a better visual perception compared to those obtained by other traditional techniques, and a lower value of SD/M (ratio of standard deviation to mean) factor has been calculated demonstrating better image quality.
A computer aided reconstruction and motion analysis method of mitral annulus is presented in this paper. To begin with, the boundary points on mitral annulus are marked by doctors interactively. Since these points are...
详细信息
The technologies of intra prediction and MBAFF were introduced, and a new intra prediction mode based on the characteristics of spatial distribution in interlaced video was proposed. The spatial correlation of five lu...
详细信息
The technologies of intra prediction and MBAFF were introduced, and a new intra prediction mode based on the characteristics of spatial distribution in interlaced video was proposed. The spatial correlation of five luma intra prediction modes in AVS-P2 and the new mode were analyzed. From the analysis result, it can be concluded that the new mode can exploit the spatial correlation better and predict the samples more precisely than the existed ones. The experimental results showed that the average gain in peak signal to noise ratio was above 0.12dB and the average reduction in bit-rate was above 1.77%, so the proposed mode is an effective prediction mode for improvement of coding performance.
暂无评论