Analyzing Low-Level Visual Features Using Content-Based Image Retrieval

This paper describes how low-level statistical visual features can be analyzed in our content-based image retrieval system named PicSOM. The lowlevel visual features used in the system are all statistical by nature. They include average color, color moments, contrast-type textural feature, and edge histogram and Fourier transform based shape features. Other features can be added easily. A genuine characteristic of the PicSOM system is to use relevance feedback from the human user’s actions to direct the system in scoring the relevance of particular features in the present query. While the link from features to semantic concepts remains an open problem, it is possible to relate low-level features to subjective image similarity, as perceived instantaneously by human users. The efficient implementation of PicSOM allows tests using statistically sufficiently large and representative databases of natural images.