Automated salt dome detection using an attribute ranking framework with a dictionary-based classifier

In this paper, we propose a dictionary-based classification approach for salt dome detection within migrated seismic volumes. The proposed workflow utilizes seismic attributes derived from the gray level co-occurrence matrix (GLCM), Gabor filter, and higher order singular value decomposition (HOSVD) to effectively learn and detect the salt bodies. We use an information theoretic framework to rank the seismic attributes as per their salt dome classification performance. Based on this ranking, we select the top K attributes for dictionary training, testing, and classification. To improve the accuracy of the detected salt bodies and make the proposed workflow robust to different datasets, we introduce a refining step, which utilizes edge strength and energy values to detect the shape of the salt dome boundary within the classified patches. The optimal set of attributes and the refining step ensure that the proposed workflow yields good results for detecting salt-dome boundaries even in the presence of weak seismic reflections. We use the seismic data from the Netherlands offshore F3 block (North Sea) to demonstrate the effectiveness of the proposed workflow in detecting salt bodies. Using both subjective and objective evaluation metrics, we compare the results of the proposed workflow with existing gradient-, texture-, and patch-based classification methods. The experimental results show that the proposed workflow outperforms existing salt dome delineation techniques in terms of both accuracy and precision.