Advanced Materials Research Vols. 756-759

Abstract: According to the theoretical analysis of Zadoff-Chu sequence and theoretical derivation.A kind of low complexity implementation method of algorithm in cell search in TD-LTE system is proposed in this paper. Both the theory analysis and simulation results show that the algorithm proposed can reduce computational complexity and this algorithm is feasible and efficient, which gains good performance of cell search in TD-LTE system.

Abstract: Firstly, the structural parameter optimization of the tooth-arrangement multi-fingered dextrous hand is studied. Secondly, as to the shortcomings that the Pareto solution of multi-objective optimization was distributed unevenly in NSGA-II, a non-dominated sorting genetic algorithm based on immune principle is proposed. Lastly, the structural parameter of the medical tooth-arrangement multi-fingered dextrous hand is optimized using the proposed algorithm. The experimental results show that this algorithm can optimize structural parameter of tooth-arrangement multi-fingered dextrous hand very well.

Abstract: MARK tag is a common method in industrial image location. In allusion to the disadvantages of conventional MARK located, such as large numbers of templates training set,no scale and rotation ,harsh conditions and slow processing speed ,a improved matching strategy based on NCC is proposed in this paper. The method search and correct the sole MARK in the template, extract 25 grids normalized feature sequence. Then matching with all contour feature sequences extracted in the target image and finally locate the target MARK. The experiment results show that , the method has much robustness to scale and rotation and can meet the real-time processing requirements

Abstract: The grounding grid of power plants and substations is an important device to ensure the safe and stable operation of electric power system. However, it is difficult to diagnose the fault of grounding grid using traditional method of identification. In recent years, the development of artificial neural network has provided effective ways to solve this problem. In this paper, neural network is used to diagnose fault of the grounding grid, because it has good learning and training characteristics, and performance of fault tolerance. It can search fault localization of the grounding grid. BP Algorithm has the advantage of the optimization accuracy, but there are some drawbacks, the majority of which is easy to fall into local minimum, slow convergence and cause oscillation effect. Genetic algorithm has a strong globe search capability, and can find the global optimal solution with high probability, so it can overcome the shortcomings of the BP algorithm using GA to complete the pre-search. This paper presents a hybrid training algorithm by GA combine with BP to optimize network. Simulation results show that the hybrid method has a fast convergence rate and high diagnostic accuracy for diagnosing the fault of grounding grid; it can be used in fault diagnosis of grounding grid effectively and reliably.

Abstract: This paper is mainly discussing the key technology of label automatic identification system using the indirect fuzzy pattern recognition based on the features of image and the fuzzy theory. This method greatly improves the efficiency and accuracy and the control effect is obvious, so that the quality of the label is guaranteed.

Abstract: When tracking a moving human target,the traditional particle filter algorithm based on color characteristic can't get accurate results in situations like complicated background or frequent brightness change.Due to the problem, this paper put forward a particle filter algorithm based on combination of color characteristics and shape features of the target.Firstly, fusing the above-mentioned two features into the particle filter frame to calculate the particle weights and achieve the human tracking goal through image sequences . The experimental results show that the algorithm can improve the traditional tracking algorithms based on single color feature limitations.And greatly improves the accuracy and effectiveness of the human tracking under complex background

Abstract: In order to effectively separate the target region of the microscopic image of Chinese Herbal Medicine (CHM), and lay the foundation for the subsequent image recognition processing, a microscopic image segmentation method of CHM by using region growing (RG) algorithm is put forward based on the characteristics of the plant microscopic images. Firstly, the CHM microscopic images with different cell structure are regarded as a multi-dimensional matrix to process and established seed label matrix. Secondly, in a given region threshold conditions, the different seed growth points are selected to segmented the different images. Finally, given a fixed growth points, the microscopic images are processed by choosing a different threshold. The experimental results show that CHM image segmentation threshold and seed selection decide the image target extraction. For different CHM images, according to a certain method, the better image segmentation results can be achieved in the case to obtain a suitable threshold value using image information and the seed point adjustment.

Abstract: In this Work, Block PCA Based Method is Used to Build Several Subspaces for each Macaque Face Image and a Similarity Criterion is Proposed to Distinguish Family Properties of Macaques. A Proper Threshold Value is Determined through Statistical Analysis. then, a Series of Experiments are Carried out to Verify the Feasibility of this Approach. the Results Demonstrate that it is Proper to Utilize Similarity Value as Judgment Criterion of Macaque Family Properties and Higher Accurate Rate is Obtained. it can Provide an Effective way for Population Recognition of other Species.

Abstract: Fast and accurate visual tracking of ground buildings can provide unmanned aerial vehicles (UAVs) with rich perceptual information, which is very important for target recognition, navigation and system control. However, when an UAV moves fast, both background and buildings in visual scenes change relatively and rapidly. Consequently, there are no constant features for objects' appearance, which poses great challenges for visual tracking of buildings. In this paper, we first build an image manifold of buildings, which can encode the continuous variation of appearance. We then propose an efficient approach to learn this manifold and obtain more robust feature extraction results. By using a simple tracking framework, we successfully apply the extracted low-dimensional features to real-time building tracking. Experimental results demonstrate the effectiveness of the proposed method.

Abstract: Aimed at the correlation between noise pixels and neighboring pixels, a new method based on the-support vector regression (-SVR) is proposed to remove the salt & pepper noise in corrupted images. The new algorithm first takes a decision whether the pixel under test is noise or not by comparing the block uniformity of the 3x3 window with one of the entire image, secondly adjusts adaptively the size of filtering window which is used to determine the training set according to the number of noise points in the window, thirdly determines the decision function that is used to predict the gray value of the noise pixels by means of training set, finally removes the noises in terms of the decision function based on-SVR. Experimental results clearly indicate that the proposed method has a better filtering effect than the existing methods such as standard mean filter, standard median filter, adaptive median filter by means of visual quality and quanti-tative measures.