Vehicle Recognition Based on Support Vector Machine

Abstract

In some developed countries, the automatic vehicle recognition is a quite mature technology. This paper applies the multi-classification method based on Support Vector Machine (SVM) to vehicle recognition. Support vector machine, appeared recently, is a new theory and technology in the filed of pattern recognition and has shown excellent performance in practice. This method was proposed basing on Structural Risk Minimization (SRM) in place of Experiential Risk Minimization (ERM), thus it has good generalization capability. By mapping input data into a high dimensional characteristic space in which an optimal separating hyperplane is built, SVM presents a lot of advantages for resolving the small samples, nonlinear and high dimensional pattern recognition, as well as other machine-learning problems such as function fitting. The simulation results show that the proposed method is effective and feasible.

Prediction and Analysis of CO2 Emission in Chongqing for the Protection of Environment and Public Health

“…SVM is one of machine learning methods based on statistic theory based on statistic theory, which is proposed by Cortes and Vapnik in 1995 [38]. It provides excellent results on solving problem related to small samples, nonlinear and high-dimensional pattern recognition [39]. SVM for regression is also called SVR.…”

“…By using the thought of support vector and the method of Lagrange multiplier, the data can be analyzed by support vector regression. The basic function for SVR is given by [38,39,40,41,42]: $ffalse(xfalse)=\omega \cdot true\oint (x)+b$ where $ffalse(xfalse)$ is a nonlinear mapping function, $\omega$ and $b$ are the vector parameters need to be determined. With data set $\{false(x_1,y_{1}false),false(x_2,y_{2}false),\dots ,false(x_n,y_{n}false)false\}$ ($y_i\in R^n$, $x_i\in R^n$), $x_i$ is an input, $y_i$ is a output target and $R^n$ represents n-dimensional Euclidean space.…”

Improving a Leaves Automatic Recognition Process Using PCA

“…In this present work, we have improved that previous study using the transformation and reduction of border parameterization using Principal Component Analysis (PCA) [5], and classifying its result with Support Vector Machines (SVM) [6] [7]. The rest of this paper presents our proposal.…”

“…Particularly, we have used an implementation of Vapnik`s Support Vector Machine known as SVM light [6], [7] which is a fast optimization algorithm for pattern recognition, regression problem, and learning retrieval functions from unobtrusive feedback to propose a ranking function. The algorithm has scalable memory requirements and can handle problems with many thousands of support vectors efficiently.…”

“…For the classification system based on the SVM [6], [7], in order to establishing efficiency, we have calculated error, success and rejected rates on recognition.…”