Adult Image Detection Using Wavelet Trans form and Support Vector Machine

摘要

An efficient method of adult image based on wavelet transform incorporating with Support Vector Machine (SVM) is proposed. Firstly, a obect image template matching is used to coarse filter for locating and speeding up, then a Haar wavelet transform of template matching constrained subspace is performed to decrease the dimension and extract feature for SVM classify according to the eigenvector trained and built by given samples. The test results show that the system not only achieves high detection rate, but also reduces the computational complexity, has practice ability to be applied in embedded platform.