The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
For the recognition of different similar airplane targets, a set of wavelet moment invariants are applied based on the invariant moment theory and wavelet analysis, and a feature selection algorithm based on the DB Index guidelines is presented in order to get a locally optimum feature set. The experimental results prove that this algorithm is superior to Hu's moment invariants and Zernike's moment...
In order to detect the intrusion in the system, the information fusion technology was applied into intrusion detection. First, the audit data based on host and network data based on net were trained all together by using SVM and classification were realized. Then the D-S evidence theory was adopted to complete decision fusion. The performance of intrusion detection system is improved greatly, false...
The traditional KNN algorithm for text classification has some insufficiencies, an improved KNN algorithm has been presented in this paper. By use of the clustering center vector, we put the distance of the be classified text and the text category into the similarity calculation formula, and take the ratio of the number of common features appear in two texts and the maximum number of respective features...
In this paper we study on a tracing system for infrared target and propose an optimized algorithm to track and recognize the objects such as flying target. So we need to detect the moving targets from the background in image sequences, and keep track of them by the Kaiman filter algorithm and image processing. In the first stage, we segment the moving regions from the background area with GMM(Gaussian...
This paper analyses the defections of traditional support vector machine (for short SVM). According to the characteristics of grain information on the web, a multi-class classification method based on Huffman binary tree SVM (for short HBT-SVM) is presented for grain information classification. Compared with existing SVM methods, this method has higher computation efficiency. The experimental results...
A new method which is based on the invariance of cross ratio with non-calibrated CCD cameras is presented in this paper in order to get the size of small workpieces by non-contact means. Edges as well as some other features of the workpieces will be detected and extracted after the images of workpieces been remotely acquired by camera and preprocessed. According to two orthogonal sets of parallel...
We deduce the expression of the laser range profile according to the laser radar equation, and get the one-dimensional range profile of a frustum of a cone, an ellipsoid and a rotating parabolic convex. And then, we put forward another method named Surface Elements Imaging Method, which can be used in arbitrary targets. Meanwhile, the one-dimensional and three-dimensional range profiles of a satellite...
Object localization is a critical factor in automatic system testing, which poses two main difficulties: 1) the scale variation of the icons, 2) the absence of the gradient information in some icons. This paper proposes a systematic method based on cascade template matching to localize the object. Firstly we use the multiple templates of different scales to detect the object. Secondly we distinguish...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.