Applied Mechanics and Materials Vols. 556-562

Abstract: For images with intensity inhomogeneities that can’t get accurate segmentation results, this paper proposes a variational level set model based on local clustering. First,based on the model of images with intensity inhomogeneities, we use the K-mean clustering algorithm for intensity clustering in a neighborhood of each point of images with intensity inhomogeneities, and define a local clustering criterion function for the image intensities in the neighborhood. Then this local clustering criterion function is then integrated with respect to the neighborhood center to give a global criterion of image segmentation. This criterion defines an energy function as a local intensity fitting term in the level set model. By minimizing this energy, our method is able to get the accurate image segmentation. The image segmentation results prove that our model in the aspect of segmenting images with intensity inhomogeneity is better than piecewise constant (PC) models, and the segmentation efficiency is higher than region-scalable fitting (RSF) model.

Abstract: In this paper, we propose a fast convolution neural network architecture to solve image document recognition problem, and this is a difficult problem because of ambient lighting conditions, and the images are usually noisy, broken or incomplete. We applied to license plate recognition and also analyzed the results of this mapping process and the number of different features.

Abstract: This paper presents an approach of enhance images subjective visual quality, based on image sparse representation. Firstly, comparativing and analysing the performance of the current several popular image denoising methods by two kinds of different content image, and using the K-SVD, MB3D and CSR algorithm, we obtain clean images namely the images noise removing. Then, decomposing the already denoised image into both cartoon and texture component by Morphological Component Analysis (MCA ) method, and superresolution the cartoon part and enhance the contrast of the texture in image. Finally, fusion between the cartoon and the texture gain the desired image.

Abstract: Aiming at the deficiency of large volume and complex installation monitoring system the traditional character recognition system, this paper proposes a character recognition scheme of Android intelligent terminal based on. This paper introduces the whole structure of the system, through the analysis and Research on the character recognition process, introduces the overall design process and recognition system, character recognition system client.

Abstract: The objectives of this paper are to analyze the effectiveness of parameters on sound propagation in a shallow-water environment. The procedure for calculation of transmission loss is only the method to analyze the influence of environmental parameters. The normal mode approach is carried out for the calculation of transmission loss. And it is conducted in the range independent environment Transmission loss for sound propagation in shallow water depends upon many natural variables such as sea surface, water medium, and sea bottom. Analyses are finalized on the results obtained by considering two types of sound channels. The results indicated that acoustic transmission loss in a shallow-water environment is dependent on the source & receiver depths, sea surface, sound speed profile (SSP) in water, sound speed in bottom, density of water & bottom, propagation range and frequency. It is necessary to mention that better transmission was found during the sound velocity increases with depth; whereas the poor transmission occurred in negative gradient channel.

Abstract: In study of image affective semantic classification, one problem is the low classification accuracy caused by low-level redundant features. To eliminate the redundancy, a novel image affective classification method based on attributes reduction is proposed. In this method, a decision table is built from the extraction of image features first. And then valid low-level features are determined through the feature selection process using the rough set attribute reduction algorithm. Finally, the semantic recognition is done using SVM. Experiment results show that the proposed method improves the accuracy in image affective semantic classification significantly.

Abstract: Linear discriminant analysis (LDA) is an important feature extraction method. This paper proposes an improved linear discriminant analysis method, which redefines the within-class scatter matrix and introduces the normalized parameter to control the bias and variance of eigenvalues. In addition, it makes the between-class scatter matrix to weight and avoids the overlapping of neighboring class samples. Some experiments for the improved algorithm presented by us are performed on the ORL, FERET and YALE face databases, and it is compared with other commonly used methods. Experimental results show that the proposed algorithm is the effective.

Abstract: To improve the usability and operability of the hybrid-identification reconnaissance radar for individual use, a voice identification System was designed. By using SPCE061A audio signal microprocessor as the core, a digital signal processing technology was used to obtain Doppler radar signals of audio segments by audio cable. Afterwards, the A/D acquisition was conducted to acquire digital signals, and then the data obtained were preprocessed and adaptively filtered to eliminate background noises. Moreover, segmented FFT transforming was used to identify the types of the signals. The overall design of radar voice recognition for an individual soldier was thereby fulfilled. The actual measurements showed that the design of the circuit improved radar resolution and the accuracy of the radar identification.

Abstract: In order to improve the speed of compressed sensing image reconstruction algorithm, a two step rapid gradient projection for sparse reconstruction in medical image reconstruction is proposed. in traditional gradient projection for sparse reconstruction algorithm, the searching direction is alternate between the negative gradient direction when the direction is ill, the searching speed is slow. Now we search with two step gradient projection, the speed is increased when meets the ill-condition. Compared with the original GPSR algorithm, the TSGPSR algorithm not only accelerate the speed of operation, but also improves the accuracy of the reconstruction. and exhibits higher robustness under different noise intensities.

Abstract: This paper proposes a method to obtain the optimal filter parameter of the non-local mean (NLM) algorithm. The parameter is assumed to be a function of the variance of the additive white Gaussian noise and is adaptive estimated. The initialization of the variance of the additive white Gaussian noise is estimated by Wiener filter. Then the NLM filter is used to adaptively estimate the noise variance. The image denoising is an iterative computation till the parameter convergence. Experiments show that the proposed method can improve the quality of the denoised images efficiently.