Characteristic scale detection in remote-sensing data

Texture models are widely in use for image content description. In remote-sensing images textures occur at very different scales, requiring the application of multiple texture models. We present an algorithm based on a multi-scale random field model to detect the characteristic scales at which textures are present, so that texture models can be applied to a few selected scales only. The algorithm is compared to two other models based on Haralick and wavelet features. Such a scale selection scheme reduces computation time and minimizes the index size. Both are critical parameters in the design of large remote-sensing databases with content-based retrieval services.