On image classification: city vs. landscape

Abstract

Grouping images into semantically meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective indices can be built for an image database. The authors show how a specific high-level classification problem (city vs. landscape classification) can be solved from relatively simple low-level features suited for the particular classes. They have developed a procedure to qualitatively measure the saliency of a feature for classification problem based on the plot of the intra-class and inter-class distance distributions. They use this approach to determine the discriminative power of the following features: color histogram, color coherence vector DCT coefficient, edge direction histogram, and edge direction coherence vector. They determine that the edge direction-based features have the most discriminative power for the classification problem of interest. A weighted k-NN classifier is used for the classification. The classification system results in an accuracy of 93.9% when evaluated on an image database of 2,716 images using the leave-one-out method.