Bilateral FS-UNet: a logging image feature segmentation model based on depth learning

Huafeng Wang; Yawen Yang

doi:10.1117/12.2692155

23 August 2023 Bilateral FS-UNet: a logging image feature segmentation model based on depth learning

Huafeng Wang, Yawen Yang

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 1278420 (2023) https://doi.org/10.1117/12.2692155
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

Intelligent recognition of geological images in the field of logging is the key to oil and gas exploration by engineers, and it is of great research value to improve the accuracy of geological image feature recognition. An effective way to achieve this goal is to use image segmentation techniques. However, due to the poor utilisation of features in logging image datasets, most of which are characterized by "weak" boundaries, there are few mature techniques that can accurately extract logging image features. In this study, an algorithm, Bilateral FS-UNet, is designed for the extraction and intelligent recognition of geological features in electro-imaging logging images, taking into account the complexity of logging data and the ability of U-Net to achieve better segmentation results for small samples. This algorithm combines the edge-preserving features of Bilateral Filtering with the advantages of U-Net, a semantic segmentation algorithm based on an encoder-decoder framework, to enhance the utilisation of features in the network and thus improve the segmentation accuracy. The proposed algorithm achieves an average pixel accuracy of 98.3%, which is 2.5% better than that of U-Net. The experimental results show that the proposed algorithm can significantly improve the segmentation effect of the model with good regional pixel coherence and category rationality. In practical applications, it can assist loggers in logging interpretation, reduce the difficulty of oil and gas exploration, and improve the efficiency of geological feature identification.

Citation Download Citation

Huafeng Wang and Yawen Yang "Bilateral FS-UNet: a logging image feature segmentation model based on depth learning", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 1278420 (23 August 2023); https://doi.org/10.1117/12.2692155

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image segmentation

Image processing

Feature extraction

Image filtering

Image processing algorithms and systems

Tunable filters

Deep learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years