Advanced Materials Research Vols. 433-440

Abstract: Research of moving object detection and tracking is an interesting subject in computer vision. To improve the accuracy of shaded moving object detection, this article introduced a novel method for shaded moving object detection. This method is based on fuzzy sets and establishes association between object’s color information and spatial information through fuzzy logic to detect moving object and remove the shadow of it. When utilizing this method to process indoor and outdoor image sequences with moving object, this method can accurately detect the moving object and remove the shadow of it. In comparison experiment, this method showed more accuracy and robustness.

Abstract: Selective forwarding attacks in wireless sensor networks may corrupt some mission critical applications such as military surveillance and critical facilities monitoring. They are very difficult to be detected and distinguished from normal packet drops in wireless sensor networks. We propose an improved sequential mesh test based detection scheme in this paper. The scheme extracts a small quantity of samples to run the test, instead of regulating the total times of test in advance. We show through experiments that our scheme can provide higher detection accurate rate and lower false alarm rate than the existing detection schemes. Meanwhile, less communication and computation power are required to detect the selective forwarding attacks.

Abstract: Brain, an amazing organ of human body comprises electrical signal that can be helpful for interaction between various brain regions. Functional Magnetic resonance Imaging (fMRI) is a specialized type of Magnetic Resonance Imaging scan. Though nature of fMRI data posses various challenges in the analysis. But, even after all challenges too, it is used as an effective method to diagnose various disease and the relationships between various brain regions. In this paper, we have proposed a model that will result a better fMRI data analysis. The effective interactions among the brain regions can be explored using dynamic causal modeling (DCM) that will help us to understand the functionality of brain up to some extent. Bayesian networks can be used for causal discovery purpose in support with markov blanket which can be evaluated with the help of evaluation metrics.

Abstract: We propose a practical cartoon image retrieval scheme to retrieve cartoon images efficiently. The proposed scheme transfers each cartoon image to a color sequence using straightforward 8 rules. Subsequently, using the color sequences to compare the cartoon images, namely color sequences comparison. We succeed in transferring the cartoon image retrieval problem to sequences comparison. Thus the computational complexity is decreased obviously. Our system keeps both advantages of the content based cartoon image retrieval system (similarity-based retrieval) and a text based cartoon image retrieval system (very rapid and mature).

Abstract: With the help of the study on mathematical theory and its progress and the development of the computer techniques, digital image processing technology has more and more been applied in each field. The pattern recognition judges unknown things by substituting machine for human eyes, which has a high application value. Thus, it becomes the major branch in image processing fields. The character recognition technology has developed rapidly because of its broad application prospect. Until now, it has been applied successfully in OCR and vehicle license plate recognition. However, it has certain difficulty for the pattern recognition to meet the specific requirements related to specific work scenes. This essay discusses several Eigen value selecting approaches and analyzes the advantages and disadvantages of each. For the template matching methods with penalty factors, in design, character recognition algorithm based on the principal component analysis is realized where scattering matrix between classes is as produced matrix.

Abstract: Citizen widely and orderly participating in social and political life is the inevitable requirement of socialist democracy. And it is also one of the conditions of political development toward the track of modernization and democratization. China is in the initial stage of socialism, there are still many constraints in the political participation of citizens. Regarding this problem, we should view from political, economic, and cultural perspective etc. Only in this way, we can help expand the political participation of Chinese citizen, really promoting the construction of democratic politics.

Abstract: This paper introduced some significant applications of aurora images, listed the main factors of choosing wavelet basis in image compression coding and analyzed the influence of aurora image compression effect caused by different wavelet basis were experimentally. The results of two kinds of significant wavelet transform algorithms EZW and SPIHT were analyzed, compared and also experimentally improved.

Abstract: This article draws a visual map of hot-topics in the area of higher education in China by CiteSpace software since 1998, Which is based on the key words to the essays of higher education on Chinese Social Science Citation Index. Further, it analyzes the ideology behind the change of discourse and social causes, with 12 years history of Chinese higher education changes.

Abstract: This paper proposes a novel method for vehicle detection and tracking using a vehicle-mounted monocular camera in an intelligent vehicle system. Speed-based Adaptive Perception Zone (APZ) is first defined to ensure that the vehicle minimizes the spatial extent of the region it perceives according to its own speed. Vehicle candidates are generated using brake lights detection through color segmentation method and verified by a rule-based clustering approach. A tracking-by-detection scheme based on Harris-SIFT feature matching is then used to learn the template of the detected vehicle on line, localize and track the corresponding vehicle in live video. Our system was validated in real conditions in our prototype vehicle with state-of-the-art performance, equivalent and sometimes surpassing other methods recently published.

Abstract: Analytic hierarchy process (AHP) and fuzzy theory which is defined as fuzzy analytic hierarchy process (FAHP) has been widely used for a variety of applications including evaluation and decision-making. In the study, the method based on FAHP is proposed to evaluate students’ grade statistics system, where analytic hierarchy process is a common method and is applied for various sectors for analyzing qualitative criteria to weight the alternatives, and the merit of using fuzzy approach is to express the distribution of evaluation values of each index. On the basis of describing evaluation indexes for students’ grade statistics system, and the evaluation model of students’ grade statistics system is created based on analytic hierarchy process and fuzzy theory. Finally, the case is adopted to testify the effectiveness of the proposed method.