Applied Mechanics and Materials Vols. 738-739

Abstract: There have been specified the principal tasks of the image preparation for the face recognition and criteria of the image quality evaluation. There has been proposed a method of the face tracking in a video stream, a search criterion of the similar images formulated and the current estimators of the contrasting effect and image sharpness analyzed. The method of lighting compensation and the angle control method on the basis of POSIT algorithm have been studied.

Abstract: The existing 3D reconstruction techniques rarely can be easily used in people's daily life, and the traditional registration algorithms have the drawback of massive calculation. In this paper it presented a registration algorithm of body point cloud based on RGB images and Range images. First, it used kinect to obtain the RGB images and Range images from different perspectives. Then it extracted the pairs of 2D feature points on RGB images using scale-invariant feature transform (SIFT) and random sample consensus (RANSAC) algorithm application for the coarse registration and used the improved iterative closest point (ICP) algorithm for the fine registration. Second, it eliminated the background information and the noise points of the model edges. Finally it completed the registration process. Experimental results show that the algorithm can accurately accomplish the body point clouds registration using the low-cost instrument and has a relatively high efficiency.

Abstract: Research on evaluation for steganalysis based on image lags back the development of Information Hiding which will hinder the development of it. The evaluation system for steganalysis based on image which includes index system, testing system and comprehensive testing system is proposed. The common steganalysis tools are evaluated using the system, whose feasibility is proved both in theory and experiment.

Abstract: The Candide face model and the Face Action Coding System (FACS) are introduced in the paper. The relations of the positions of feature points of Candide-3 model and the action units of FACS are studied. The application system for computing the facial expressions of students in the experiment teaching process is developed. The feasibility of the application system is demonstrated.

Abstract: Based on multi-source substation equipment inspection data, this article achieve fault diagnosis in the case of incomplete understanding of the mechanism of substation equipment, by establishing fault diagnosis model.This article selected a substation equipment failures and operational information in different conditions as simulation study. The simulation results show the feasibility of the algorithm. Compared with the traditional fault diagnosis model, this method is more flexible , have a stronger ability to handle noisy data and good prospects.

Abstract: Due to the problem that the many digital images can be modified more and more easily, watermarking algorithms are proposed. There are many types of digital watermarking algorithms, such as robust digital watermarking algorithms, watermarking schemes for authentication, and reversible digital watermarking algorithms. However, there are some special images, such as the digital medical images for remote treatment, the military images for tracking object, and the remote sensing images, and they are so sensitive to any modification that we should authenticate the copyright by special technique. And this technique is zero-bit watermarking algorithms. In this paper, about zero-bit watermarking algorithms are surveyed. The basic procedures of these classical algorithms are analyzed, and some suggestion about the zero-bit algorithms is given.

Abstract: Various basic image enhancement techniques of License Plate Recognition are discussed and simulated with MATLAB. Through a lot of experiments, an improved image enhancement method is proposed by combining gray-level transformation and median filtering. The method can efficiently avoid interfere and enhance the contrast of image and obtain satisfying effects.

Abstract: Based on image processing of SF₆ gas leakage on-line pattern recognition method, this paper achieves gas leakage feature extracting, on-line identification of gas leakage and leakage points, SF₆ gas leakage can be on-line automatic identification. The simulation results show the feasibility of the algorithm. Compared with the traditional method, paper provides a more intuitive discrimination basis for field staff , as well as for the depth of the late testing data mining provides a research way of thinking

Abstract: We tried to obtain numbers of the plant electrical signal with the help of experiments. We made comprehensive treatment and analysis by using the time domain analysis method and frequency domain analysis method to the large numbers of data of the plant electrical signal. The experiment finds that that the plant electrical signal is a kind of low frequency,tiny and fairly stable signal. The features of plant electrical signals remarkably responsive to external stimuli. The measuring precision is limited in the test, so the conclusion only can be mined and used for for future research.

Abstract: Global motion estimation between two successive frames is important to the process of video stabilization. In the proposed approach, the estimation of global motion was based on the background feature points (BFPS). First, feature points (FPS) were collected from the input video by FAST operator; second, feature point’s descriptor and matching were based on FREAK operator.The M-SAC is used to classify the BFPS. Last, the six parameters of the affine transform model to calculate the interframe motion estimation vector. The experiment results show that he proposed method can stabilize inter-frame jitter, in the meanwhile, it improve the video quality effectively.