出版社:Academy & Industry Research Collaboration Center (AIRCC)
摘要:An automatic mechanism for the selection of image subset of modern and historic images out ofa landmark large image set collected from the internet is designed in this paper. This selectiondepends on the extraction of dominant features using Gabor filtering. These features areselected carefully from a preliminary image set and fed into a neural network as a training set.The mechanism collects a raw large set of landmark images containing modern and historicimages and non-landmark images as well, process these images, and finally classify them aslandmark and non-landmark images. The classification performance highly depends on thenumber of candidate features of the landmark.