Applied Mechanics and Materials Vols. 198-199

Abstract: Chan-Vese model is one of classical active contour models for segmentation based on level set methods. It is the region-based model but in some cases it is still sensitive to the location of initial contours. The image thresholding is a simple but effective tool to separate objects from the background. In this paper, we integrate these two techniques and propose a new method to improve the initialization for Chan-Vese Model. First analyze the distribution of image gray level histogram and find the optimum threshold values, then set the model’s initial contours with thresholds and construct energy functional, lastly iterate the functional formulations until convergence to the object boundary. The method is tested on the plaque images and gives considerable increase in performance.

Abstract: In order to improve the efficiency of enterprise management, the information management system uses Windows XP as the development platform, JSP as development technology and SSH as development framework to realize functions including basic information management, security management, operation management, financial management, item management and user management. The system can be used in different platform and improve operational benefit effectively.

Abstract: The traditional image magnify method usually have some defects on details. This paper gives a new infrared image magnification and enhancement method which is based on wavelet reconstruction and gradation segment. In this method, first of all, make wavelet transform on the image, get the high-frequency coefficient. Apply the Newton differential algorithm enhance the high-frequency coefficient as the high-frequency part of the magnified image, treat the original image as the low-frequency part , make the wavelet reconstruction ,then get the magnified image. To enhance the magnified image, according to the double gray threshold, segment the image into high gray segment corresponding to target, low gray segment corresponding to background, and middle gray segment corresponding to transition sector. Then, make linear extension to them respectively; the result is the magnified image. Experiments indicate, this method is effective on distinguishing high-energy target from low-energy target (the low-energy target is the primary one) and displaying the details of image(edge profile of the bomb).

Abstract: In this research we undertake a study of image compression based on the discrete cosine transform(DCT) and discrete wavelet transform(DWT). Then a hybrid color image compression algorithm based on DCT and DWT is proposed. This algorithm is implemented through transform the color image using DWT in the YCbCr space first, and then DCT in the low frequency, adopt huffman coding, RLE and arithmetic coding in the encoded mode. In experiments, the results outperform the only DCT and the only DWT typically higher in peak signal-to-noise ratio and have better visual quality.

Abstract: Considering the uncertainty of calculation results by using single feature as measurement of target recognition and identification, this paper discussed the multi-features fusion technology in infrared image recognition classification. The invariant of the singular value and invariant moment feature of infrared target image were used to make fusion. According to Dempster-Shafer Theory, the basic probability assignment was calculated first, and the fusion data was used to make specification decision based on the corresponding rules in the decision-making level. The test result shows that the multi-features fusion method has a better stability, accuracy and reliability in target recognition applications. It can raise the accuracy and fault tolerance ability of infrared image recognition system. So it will have great application value to raise the guidance accuracy of infrared imaging terminal guidance system.

Abstract: According to the comparability between the process of the multi-sensor information fusion and the human information disposal, the psycho-physical factor and its effect on the uncertainties of driving behavior are considered. The psycho-physical integrated cognitive topological structure is researched, and the cognitive activity chain of driving task-centralization is studied in the multi-resource information fusion, as well as discussed the driving decision-making behavior and the running mechanism of vehicle. The aim of researching the driving cooperative mechanism can offer the he theory guidance for the microscopic simulation and the intelligent vehicle development of intelligent transportation systems.

Abstract: This paper first gives the definition of interval type-2 fuzzy sets,then investigates interval type-2 interpolative fuzzy reasoning under Triangular type membership functions. Two interpolative fuzzy reasoning algorithms responding to interval type-2 fuzzy inference models in the line of type-1 interpolative fuzzy reasoning algorithms are proposed.

Abstract: Chinese Word segmenter is the basis for all subsequent applications of natural language processing. The Corpus-based statistic method has become the predominant method. However, the training corpora are not enough especially in certain areas. Therefore, we introduce some global features and context features in order to get almost the same performance only with much smaller scale corpus. The experiments results show that our approach significantly outperforms the original feature sets in the same training data. Meanwhile, the time-consuming of model training is also reduced. In addition, these features do not depend on classifiers, so our method can easily be changed to other models.

Abstract: It is widely acknowledged that the software of Creator can be used to establish a stationary model of a traffic environment. While, when the model is too large and the details are too complicated, especially those with 10000 or even 100000 items, the editing and modifying of the model becomes very difficult. To solve the problem, setting the nodes in the OpenFlight database can be one of the good ways. The paper gives a way of setting the nodes through practice on the base of building the model of the traffic testing field. After validation, the way of setting nodes can not only satisfy the technical requirement such as LOD, but also can simplify the editing and using of the model builder.

Abstract: Image segmentation is an important problem of digital image processing and also a common difficult problem. In this paper, a new image thresholding method based on parzen-window estimation and Tsallis entropy is proposed. The method used Parzen-window technology to estimate the spatial probability distribution of image gray level values，then combined with the Tsallis entropy to construct a new criterion function, and at last searched the optimal global threshold in the scope of gray level to maximum the criterion function. This new method has some advantages, such as high accuracy to image segmentation, fine stability comparing with the traditional Tsallis entropy method.