Assessing Texture Descriptors for Seismic Image Retrieval

Much work has been done on the assessment of texture descriptors for image retrieval in many domains. In this work, we evaluate the accuracy and performance of three wellknown texture descriptors - Gabor Filters, GLCM, and LBP - for seismic image retrieval. These subsurface images pose challenges ye...

Full description

Saved in:
Bibliographic Details
Main Authors: Britto Mattos, Andrea, Ferreira, Rodrigo S., Da Gama e Silva, Reinaldo M., Riva, Mateus, Brazil, Emilio Vital
Format: Conference Proceeding
Language:English
Subjects:
Entropy
Feature extraction
Gabor filters
Image retrieval
Three-dimensional displays
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Much work has been done on the assessment of texture descriptors for image retrieval in many domains. In this work, we evaluate the accuracy and performance of three wellknown texture descriptors - Gabor Filters, GLCM, and LBP - for seismic image retrieval. These subsurface images pose challenges yet not thoroughly investigated in previous works, which are addressed and evaluated in our experiments. We asked for domain experts to annotate two seismic cubes, Penobscot 3D and Netherlands F3, and used them to evaluate texture descriptors, corresponding parameters, and similarity metrics with the potential to retrieve visually similar regions of the considered datasets. While GLCM is used in the vast majority of works in this area, our findings indicate that LBP has the potential to produce satisfying results with lower computational cost.
ISSN:2377-5416
DOI:10.1109/SIBGRAPI.2017.45