Benchmarking of image features for content-based retrieval

A very fundamental issue in designing a content-based image retrieval system is to select the image features that best represent the image contents in a database. Such a selection requires a comprehensive evaluation of retrieval performance of image features. In this paper, we provide a detailed comparison of a number of commonly used color and texture features based on a large and diverse collection of image data. The investigated color features include color histogram, color moments, color coherence vectors and color correlogram with respect to different color spaces and quantizations. As for texture features, we compare Tamura features, edge histogram, MRSAR, Gabor texture feature, and wavelet transform features. The result of this experiment can be used as a benchmark for selecting features in a content-based image retrieval system.