A novel image classification method based on manifold learning and Gaussian mixture model

Abstract

Image classification is one of the important parts of digital image processing. We propose a novel feature space-based image classification method by combining manifold learning and mixture model. In this paper, the process of image classification can be viewed as two parts: a coarse-grained classification and a fine-grained classification. In the coarse-grained classification, we apply the ISOMAP (Isometric Mapping) algorithm to do a dimensional reduction based on manifold learning. Thus, solving the classification problem is transformed from a high-dimensional data space to a low-dimensional feature space. And then, during the fine-grained classification, we present an improved EM algorithm of finite Gaussian mixture model to do clustering. Experimental results have demonstrated that the proposed method performs well in both accuracy and time. Additionally, our algorithm is robust to some extent.