Yuzhu Wang

Image-Based Rock Typing Using Chan-Vese Model

Yuzhu Wang, Shuyu Sun, Abdulaziz Azzaben and Christoph H. Arns

Image-based rock typing is carried out to classify an image of the heterogeneous rock sample into different rock types where each rock type can be treated as a homogeneous porous medium. In this study, we propose an innovative method for rock typing of the heterogeneous rock sample via two steps. First, the target image, a segmented binary image with two phases of pore and solid, is consecutively inputted into two filters of a local homogeneity filter and an average filter. The function of the local homogeneity filtering is to increase the contrast between different rock types and the average filter is used to decrease the contrast within each single rock type. Second, Chan-Vese model is applied to classify the filtered image into different rock types. The local homogeneity filtering introduced in this study is a special high-pass filter which is undertaken by counting the number of pixels that possess the same phases as the center pixel within a 33 pixels neighborhood. If the most of pixels within a 33pixels neighborhood have the same phase with the center pixel, the value of the center pixel is assigned by 1, otherwise it is 0. This process is carried out iteratively, which means the previously estimated pixel will be used in the estimation of its neighbor unprocessed pixels. We demonstrate the application of the proposed method in several heterogeneous samples and present excellent performance.