Techniques for large zone segmentation of seismic images

Seismic techniques play an important role in the exploration for hydrocarbon deposits. The authors describe three knowledge-based segmentation techniques and compare their performance on a real seismic image. The first technique is based on a run length statistics algorithm extended by a decision process which incorporates heuristic rules to influence the segmentation. The second and third techniques are based on texture energy measures algorithms augmented by two knowledge-based classification processes. The knowledge-based process of the second technique is controlled by a parallel region growing scheme and that of the third technique is controlled by an iterative quadtree spitting scheme. Their results show that the third technique, which is based on texture measures augmented with a knowledge-based quadtree splitting scheme, provides a better segmentation of the test image than the other two.