Fast Image Classification with Reduced Multiclass Support Vector Machines
نویسندگان
چکیده
Image classification is intrinsically a multiclass, nonlinear classification task. Support Vector Machines (SVMs) have been successfully exploited to tackle this problem, using one-vs-one or one-vs-all learning schemes to enable multiclass classification, and kernels designed for image classification to handle nonlinearities. To classify an image at test time, an SVM requires matching it against a small subset of the training data, namely, its support vectors (SVs). In the multiclass case, though, the union of the sets of SVs of each binary SVM may almost correspond to the full training set, potentially yielding an unacceptable computational complexity at test time. To overcome this limitation, in this work we propose a well-principled reduction method that approximates the discriminant function of a multiclass SVM by jointly optimizing the full set of SVs along with their coefficients. We show that our approach is capable of reducing computational complexity up to two orders of magnitude without significantly affecting recognition accuracy, by creating a super-sparse, budgeted set of virtual vectors.
منابع مشابه
Multi-class support vector machines: a new approach
In this paper, we propose a new approach for solving multiclass problems with Support Vector Machines. We modify the existing technique to properly reduce the empirical error, therefore we will be ideally able to outperform the previously proposed scheme for multi-class SVMs. The proposed approach also provides solutions with a significant reduction in the number of support vectors, which is an...
متن کاملFuzzy Support Vector Machines Based on Density Estimation with Gaussian Mixture for Multiclass Problems
In this paper, we introduce new Fuzzy Support Vector Machines (FSVMs) for a multiclass classification. The suggested Fuzzy Support Vector Machines include the data distribution with the density estimated in a set of functions defined as Gaussian mixture. The proposed method gives more appropriate boundaries than the classical FSVM method. We demonstrate some examples which confirm our approach.
متن کاملA comparative study of performance of K-nearest neighbors and support vector machines for classification of groundwater
The aim of this work is to examine the feasibilities of the support vector machines (SVMs) and K-nearest neighbor (K-NN) classifier methods for the classification of an aquifer in the Khuzestan Province, Iran. For this purpose, 17 groundwater quality variables including EC, TDS, turbidity, pH, total hardness, Ca, Mg, total alkalinity, sulfate, nitrate, nitrite, fluoride, phosphate, Fe, Mn, Cu, ...
متن کاملInteractive multiclass segmentation using superpixel classification
This paper adresses the problem of interactive multiclass segmentation. We propose a fast and efficient new interactive segmentation method called Superpixel Classification-based Interactive Segmentation (SCIS). From a few strokes drawn by a human user over an image, this method extracts relevant semantic objects. To get a fast calculation and an accurate segmentation, SCIS uses superpixel over...
متن کاملA Probabilistic Neural Network for Gene Selection and Classification of Microarray Data
In this paper, we present the mathematical foundations of a probabilistic neural network for gene selection and classification of high-dimensional microarray data. We present a catalogue of features that a classification system for microarray data should incorporate. We then use this catalogue and compare the theoretical properties of probabilistic neural networks with support vector machines w...
متن کامل