Abstract: Based on the high-resolution borehole image obtained by digital panoramic borehole camera system, a method for recognizing solution fissure based on color features was proposed. Considering the fact that typical rock mass structure, such as soil layer and solution fissure have obvious difference from common rock layer in color, a self-adaptive detection model based on HSV (hue- saturation-value) color space was established. The binarized image of solution fissure was obtained using this model. Secondly, the binary image was filtered to avoid the noise effects. Then, the binarized image of solution fissure was divided and the density of pixels in each segmentation was calculated to determine the depth, area and direction of the soil layer and the solution fissure, so that the identification of solution fissure in the digital borehole image can be achieved. Through verifying this method with many actual borehole images and comparing them with the corresponding borehole radar images, the results indicate that this method can identify all the solution fissure and the soil layer throughout the whole borehole digital optical image automatically and quickly. It provides a new reliable method for the automatic identification of borehole rock structures in practical engineering.

Key words: digital borehole image, self-adaptive HSV color model, image recognition, solution fissure recognition, soil layer recognition