Earticle

Super Resolution (SR) reconstruction is a procedure of attaining the High resolution (HR) images from a set of noisy and blurred low resolution (LR) observations. In this paper a novel SR algorithm is proposed by developing a fuzzy based Bicubic interpolation algorithm to improve the resolution of the image. The algorithm significantly improves the resolution, quality and enhances the color information of the reconstructed image when compared with the other existing methods.

Based on fuzzy one-class support vector machine (SVM) and least squares (LS) one-class SVM, we propose an LS fuzzy one-class SVM to deal with the class imbalanced problem. The LS fuzzy one-class SVM applies a fuzzy membership to each sample and attempts to solve the modified primal problem. Hence, we just need to solve a system of linear equations as opposed solving the quadratic programming problem (QPP) in fuzzy one-class SVM, which leads to an extremely simple and fast algorithm. Numerical experiments on several benchmark data sets demonstrate the feasibility and effectiveness of the proposed algorithm.

In the field of wireless communication systems, the use of multiple antennas at the transmitter and receiver side has gained a huge popularity over the past few decades, due to its tremendous performance enhancing capabilities. Such systems are known as MIMO (Multiple-Input Multiple-Output) systems and can be classified into three main categories; Spatial Multiplexing, Spatial Diversity and Beam forming techniques. The objective of this paper is to evaluate the error rate performance of MIMO transmission modes through Nakagami-m fading channels. The ZF (Zero Forcing), MMSE (Minimum Mean-Square-Error) channel equalization algorithm; STTC (Space Time Trellis Codes), OSTBC (Orthogonal Space Time Block Codes), MRC (Maximal Ratio Combining) and Beamforming methods are analyzed. The QPSK modulation technique is used to evaluate the bit error rate (BER) performances under different SNR scenarios. The results described in this paper suggest considerable improvement in the system performance by incorporating different MIMO techniques in order to improve the wireless transmission link quality.

In this paper, we propose a novel algorithm to deal with the problem of visual tracking in some challenging situations, which is based on sparse representation and multi-scale block. To build target templates, we select distinguishable features between the target and background in each frame of video sequences, dictionary is built by the multi-scale block of target templates. Then, particle filter generates filter distribution in the next frame, the moving target is framed by affine transformation. To describe the current state of the target, we calculate posterior probability for each particle. Finally, the templates are updated online. The experimental results show that the proposed algorithm is superior in accuracy than the classical tracking algorithm, and it has better robustness against to the target posture changes, partial occlusion and illumination variations.

Generally for improving contrast in digital images, HE is the method that commonly used but in result it gives unnatural artifacts like intensity saturation, over-enhancement and noise amplification. To overcome these problems there was a need to partition the image histogram, at first image histogram was partitioned into two parts and then different transformation functions were applied on each partition. After that image histogram was partitioned into many partitions and same process was applied with some additional features. DHE is the multi histogram method and CLAHE is the extension of AHE. These methods are compared to HE and found that both methods give better result than HE but DHE method also gives better result than CLAHE.

Aiming at properties of remote sensing image data such as high-dimension, nonlinearity and massive unlabeled samples, a kind of probability least squares support vector machine (PLSSVM) classification method based on hybrid entropy and L1 norm was proposed. Firstly, hybrid entropy was designed by combining quasi-entropy with entropy difference, which was used to select the most “valuable” samples to be labeled from massive unlabeled sample set. Secondly, a L1 norm distance measuring was used to further select and remove outliers and redundant data from the sample set to be labeled. Finally, based on originally labeled samples and screened samples, PLSSVM was gained through training. Experimental results on classification of ROSIS hyperspectral remote sensing images show that the overall accuracy and Kappa coefficient of the proposed classification method reach higher accuracy respectively. The proposed method can obtain higher classification accuracy with few training samples, which is much applicable to classification problem of remote sensing images.

Fingerprint-based recognition systems have been widely deployed in numerous civilian and government applications. However, the fingerprint recognition systems can be deceived by commonly used sensors with the artificially fake fingerprint made using materials like gelatin or silicon. In this paper, spoof fingerprint detection is considered as a two-class classification problem and co-occurrence matrix is constructed from image gradients to extract features. In feature extraction process, the quantization operation is firstly applied with the fingerprint images. Secondly, the horizontal and vertical differences at each pixel are calculated. Thirdly, the differences of large absolute values are truncated into a reduced range. Finally, the co-occurrence matrix is constructed from the truncated differences, and the elements of the co-occurrence matrix are directly used as features. The features are separately utilized to train support vector machine classifiers on two databases. The experimental results have demonstrated that the proposed method outperform the state-of-the-arts.

It is hard to segmentation brain MR images for the bias fields. In this paper, a new fuzzy anisotropic diffusion function is presented to reduce the effect of the noise. We use Legendre polynomial functions to reconstruct the bias field, which make the entropy of the recovered image be smallest. But it needs to compute a lot of parameters to reconstruct the bias. The traditional method uses the gradient descending method to compute the parameters. The method plunges into local best easily. In order to deal with this problem, Particle swarm optimization (PSO) method is analyzed. A new particle swarm technique is proposed that incorporates initial location information and use mutate operation make the particles away from local maxima. The experiments show that the new method can get accurate result robustly.