Geological Feature Extraction Using Independent Component Analysis
Abstract
Abstract This paper presents a resilient and adaptive method for edge detection in seismic images via independent component analysis (ICA). ICA is used on seismic image patches, where the fixed-point FastICA technique is used to learn the basis functions. The majority of these sparse basis functions are used as patterns or template to extract features. Like Gabor wavelet bases, these basis functions are band-limited and confined. The proposed algorithm first transforms a grayscale seismic image into different classes representing edges and background. The edges are extracted by thresholding using sparse components which in turn generates an image into a pattern or feature map. Further, this paper investigates the capabilities of ICA compared with classical methods of edge detection based on seismic images through simulation results.
Read the paper
Related studies
- Current state and future directions for deep learning based automatic seismic fault interpretation: A systematic review
- Physics of Partially Saturated Porous Media: Residual Saturation and Seismic-Wave Propagation
- Modern Imaging Using Seismic Reflection Data
- Effects of marine seismic surveys on free-ranging fauna: a systematic literature review
- A review of the recent seismic activity in the southern part of egypt (upper egypt)
- A review of research on mechanism of seismic attenuation and energy compensation
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.