Ellipse Support Vector Data Description
نویسندگان
چکیده
This paper presents a novel Boundary-based approach in one-class classification that is inspired by support vector data description (SVDD). The SVDD is a popular kernel method which tries to fit a hypersphere around the target objects and of course more precise boundary is relied on selecting proper parameters for the kernel functions. Even with a flexible Gaussian kernel function, the SVDD could sometimes generate a loose decision boundary. Here we modify the structure of the SVDD by using a hyperellipse to specify the boundary of the target objects with more precision, in the input space. Due to the usage of a hyperellipse instead of a hypersphere as the decision boundary, we named it "Ellipse Support Vector Data Description" (ESVDD). We show that the ESVDD can generate a tighter data description in the kernel space as well as the input space. Furthermore the proposed algorithm boundaries on the contrary of SVDD boundaries are less influenced by change of the user defined parameters.
منابع مشابه
Convex set reconstruction using prior shape information
In this paper we present several algorithms for reconstructing 2D convex sets given support line measurements for which the angles are known precisely but the lateral displacements are noisy. We extend the algorithms given in a previous paper by explicitly incorporating prior information about the shape of the objects to be reconstructed. We develop the Scale-Invariant algorithms, which incorpo...
متن کاملA Vision based Application for Virtual Mouse Interface Using Finger-Tip
This paper presents a vision based virtual mouse interface using a single camera. A virtual panel which is a rectangular board with its borders shaded by red color and its four corners shaded by blue color are extracted using HSV color quantization. In consecutive frames of a video, four corners are tracked using color based histogram tracker. The four corners of rectangular panel are mapped to...
متن کاملGeometric Interpretation and Precision Analysis of Algebraic Ellipse Fitting Using Least Squares Method
This paper presents a new approach for precision estimation for algebraic ellipse fitting based on combined least squares method. Our approach is based on coordinate description of the ellipse geometry to determine the error distances of the fitting method. Since it is an effective fitting algorithm the well-known Direct Ellipse Fitting method was selected as an algebraic method for precision e...
متن کاملSupport vector regression with random output variable and probabilistic constraints
Support Vector Regression (SVR) solves regression problems based on the concept of Support Vector Machine (SVM). In this paper, a new model of SVR with probabilistic constraints is proposed that any of output data and bias are considered the random variables with uniform probability functions. Using the new proposed method, the optimal hyperplane regression can be obtained by solving a quadrati...
متن کاملA modified concept of PCA to reduce the classification error using kernel SVM classifier
This paper focuses on the mathematical technique PCA with the drawback of its mixing of data pixel. We have extracted principal directions of the covariance ellipse as done in PCA, but we will not blindly take the Eigen vectors corresponding to k largest values. Instead, we transform the data vectors into the new n– dimensional (n is dimension of old input space) vector space spanned by the Eig...
متن کامل