Classifying images of classical architectures: Chinese vs. European

Image classification is an important problem in computer vision. All existing image classification approaches tend to classify images of distinctly different objects. In this paper, we attempt to classify two similar image classes, Chinese and European classical architecture. First, Gabor filter is utilized to catch texture features of images. Then color histogram distance is adopted as a coefficient of image dissimilarity in a modified k-NN classifier. Images are segmented to regions, and all region texture features are combined into vectors by corresponding area proportion. We also studied the impact of image segmentation on classification by comparing two different segmentation algorithms. The experiment shows the new approach is effective in distinguishing images of Chinese and European classical architectures.