Seismic Image Identification and Detection Based on Tchebichef Moment Invariant

Abstract

The research focuses on the analysis of seismic data, specifically targeting the detection, edge segmentation, and classification of seismic images. These processes are fundamental in image processing and are crucial in understanding the stratigraphic structure and identifying oil and natural gas resources. However, there is a lack of sufficient resources in the field of seismic image detection, and interpreting 2D seismic image slices based on 3D seismic data sets can be challenging. In this research, image segmentation involves image preprocessing and the use of a U-net network. Preprocessing techniques, such as Gaussian filter and anisotropic diffusion, are employed to reduce blur and noise in seismic images. The U-net network, based on the Canny descriptor is used for segmentation. For image classification, the ResNet-50 and Inception-v3 models are applied to classify different types of seismic images. In image detection, Tchebichef invariants are computed using the Tchebichef polynomials’ recurrence relation. These invariants are then used in an optimized multi-class SVM network for detecting and classifying various types of seismic images. The promising results of the SVM model based on Tchebichef invariants suggest its potential to replace Hu moment invariants (HMIs) and Zernike moment invariants (ZMIs) for seismic image detection. This approach offers a more efficient and dependable solution for seismic image analysis in the future.

Transfer Learning Model Application for Rastrelliger brachysoma and R. kanagurta Image Classification Using Smartphone-Captured Images

“…This requires further development moving forward. Contrasting the outcomes of this inquiry with the research carried out by Lu et al [17], our study focuses on the classification of species within aquatic environments using transfer learning. In comparison, Liu et al's study tackles the broader challenge of fine-grained visual categorization (FGVC), highlighting the significance of integrating detailed information from diverse layers of CNNs.…”

“…Asli et al [15] introduced a method involving two-dimensional Zernike polynomials for image classification. Mathur and Goel [16] applied the ResNet-50 network for underwater fish classification, achieving improved accuracy despite limited datasets, while Lu and Honarvar Shakibaei Asli [17] utilized Gaussian filter preprocessing, U-net segmentation, and ResNet-50/Inception-v3 classification for the analysis of specific data.…”

An Application of 3D Cross-Well Elastic Reverse Time Migration Imaging Based on the Multi-Wave and Multi-Component Technique in Coastal Engineering Exploration

“…Surface seismic methods are highly susceptible to variations in near-surface conditions and encountering difficulties in transmitting a significant amount of energy through the weathered zone to reach the targeted depths [5][6][7]. Compared to surface seismic reflection or refraction surveys, cross-well seismic acquisition methods emerge as an optimal choice for effectively targeting specific coastal areas [8,9].…”