Advanced Materials Research Vols. 926-930

Abstract: Low similarity and unreasonable design now appeared in distracters generation of English words in the process of learning English words. This paper proposed a new algorithm to solve this problem by researching Edit Distance and LCS algorithm. Comparing with traditional algorithms, the accuracy of similarity has been improved in this algorithm. Finally, combined with words’ part of speech, we generated more reasonable distracters in the experiments.

Abstract: Soccer video analysis is attracting much attention. In this paper, we propose a modified conditional random field (CRF) model to extract the highlights of an entire soccer video. Highlight extraction in soccer video is essentially a kind of timing annotation problems, so the commonly used CRF model is adopted to solve this problem in this paper. Meanwhile, Boolean function is normally used as feature function in the CRF model, which will result in a hard association between observed variables and highlight variables. By introducing Bayesian network to model the observed variables and replacing the original feature function with posterior probability calculated with Bayesian network, hard association is transformed into soft association, which makes the model more close to the actual situation. Experimental results show that the proposed algorithm has achieved good results.

Abstract: This paper proposes a football object extraction method based on image segmentation algorithm in football video. The football segmentation Interactive operation method with the advantages of high accuracy segmentation, can be applied to other ball games Object (such as volleyball, soccer) segmentation and extraction. In the next step of the study, in a Step to improve the extraction method of the football video frames in image segmentation accuracy ,Application of football and the extracted from football video segment retrieval system for target tracking, to provide an effective method for basketball video clip retrieval.

Abstract: Aiming at image denoising problem, some researchers put forward bilateral filtering algorithm. The algorithm makes weighting for spatial distance and pixel intensity difference. It introduces pixel weighting kernel function on the Gaussian locality smoothing mode, which is more favorable to keep the image margin detail. This paper tries the new improvement on the foundation of bilateral filter technique. It adopts coherent values scanning to treat energy center corresponding apparent dip as smoothing discontinuous geologic body direction. The directivity dramatically reduces, and it is easy to be generalized to non-planar geometrical morphology lineup. And it adopts the method based on waveform self-adaption mode on coherent values estimation. The estimated depending on the time dip and coherent values property are more reliable and physical significance. When calculating pixel value similarity weight, it uses discontinuous geologic body direction sampling point mean or median to replace calculate point. It is much easier to suppress random noise and more effective to keep geologic feature.

Abstract: On the analysis of the disadvantage of traditional Failure Mode and Effect Analysis (FMEA), an improved FMEA based on fuzzy set theory and Analytical Hierarchy Process (AHP) is proposed. In this method, the fuzzy language set and the fuzzy number of Severity (S), Occurrence (O) and Detection (D) are firstly set up, then failure modes are evaluated, and finally the weights of S, O and D are determined by AHP. So, risk priorities of the failure modes can be determined by calculating the modified Risk Priority Number (RPN). Improved FMEA could provide a method for the company to evaluate the reliability analysis of products.

Abstract: Abstract. In this paper, we used three-layer BP network with a single hidden layer, and to design the structure of BP networks and set the parameters. We used the way of increasing the number of the hidden layer neurons and comparing the training errors and training number of the BP neural network to determine the number of the hidden layer neurons.Again, according to the acoustic emission data from the acquisition system and the designed BP neural network, we extract characteristic parameters of the corresponding crack acoustic emission signal,and to screen out seven acoustic emission parameter which the most represent crack characteristic by investigating each characteristic parameters' sensitivity of characterizing the crack condition, and according to the experiment data of the seven crack characteristic parameters to identify the crack state.

Abstract: The circle-end-face centering device which is in the base of image processing accomplishes the center of the cylinders end face by digital image processing. Through edge extraction and doing the matching in the calculation of the least square method, the coordinate of the central of the circle can be calculated. At last, the drill will be moved to the central of the circle and do the punching by the actuator. This equipment is in the high accuracy and speed compared with the traditional way and the concentric circle laser of marking with the center. Meanwhile, the actuator consists of the programmable logic controller, touch panel and servo drivers which is in the high stability and accuracy. Certainly it is easy to be controlled by the method.

Abstract: A new algorithm is proposed for interest point detection based on monogenic signal theory in this paper. The detection of stable and informative image points is one of the most important problems in modern computer vision. Phase congruency is a dimensionless measure that remains invariant to changes in image illumination and contrast. A monogenic phase congruency function is constructed using the characteristics to detect interest points in image. The experiment results indicate that different kinds of interest points can be detected and located with good precision, thus the proposed method can be applied over wide classes of images.

Abstract: This paper is based on Nagel-Schreckenberg cellular automata model as the foundation, in the open boundary conditions, the traffic vehicle redirecting probability and before lane changing rules get to intersection will produce certain effect to interference with intersection , and so as to builds up the nonsingular cellular automata model. Through the research to redirecting probability, lane changing rules and the settings of traffic lights play a part in traffic flow characteristics, and points out the influence of phase change point position ,and at the same time, traffic lights timing differences can reduce vehicle interference to increase traffic flow, at the same time, play a analysis the critical redirecting probability of traffic flow in controlling significance, and points out the relationship between the critical point of Lane changing probability and traffic flow influence ,and lane-changing rules is correspond to the basic line of vehicles running.

Abstract: This paper compares and analyzes the common recognition method and technology of irregular graphics and image, and its application to specific graphics recognition. In this paper, the application system realizes the image histogram processing, threshold value processing and edge processing, realizes the binary image, and then compared with database information, recognizing the need of graphic information, but also the graphic information such as encryption and decryption. The system is practical, the application scope is very broad, and has good popularization value.