Paper Info
Title
Robust reservoir rock fracture recognition based on a new sparse feature learning and data training method
Abstract
In this paper, the main goal is to identify the sine fractures of reservoir rock automatically. Therefore, a five-step algorithm is applied on the imaging logs. The first step consists of extracting the features of the imaging log by applying the Zernike moments. In the second step, the features are learned by using sparse coding. In the third step, the imaging log is segmented by using the self-organizing map neural network and the training dataset. In the fourth step, the fracture points are extracted by Steger method. In the last step, to determine the sine parameters of fractures, the Hough transform is applied to the image fracture points. The experimental results show that the proposed algorithm is highly able to detect the fractures of the imaging logs successfully. Also, the precision of the proposed method to extract the fracture pixels is so high and it has low sensitivity to noise in the imaging logs. In this paper, the proposed algorithm has been applied on the imaging datasets of FMI and the obtained results show that the classification has better precision compared with other proposed algorithm.
Year
DOI
Venue
2019
10.1007/s11045-019-00645-8
Multidimensional Systems and Signal Processing
Keywords
Field
DocType
Imaging log, Zernike moments, Sparse coding, Self-organizing neural network, Steger method, Hough transform
Mathematical optimization,Pattern recognition,Neural coding,Sine,Hough transform,Zernike polynomials,Artificial intelligence,Pixel,Artificial neural network,Mathematics,Feature learning,Petroleum reservoir
Journal
Volume
Issue
ISSN
30
4
0923-6082
Citations 
PageRank 
References 
1
0.35
0
Authors
3
Name
Order
Citations
PageRank
Fatemeh Taibi110.35
Gholamreza Akbarizadeh2516.19
Ebrahim Farshidi3186.26