Rock joint detection from borehole imaging logs based on gray-level co-occurrence matrix and Canny edge detector

Rock joints play an important role in characterizing the rock mass quality for geo-mechanical design and stability analysis. An approach was developed to detect and characterize the rock joints from images collected by a borehole imaging system. A gray-level co-occurrence matrix was employed to locate the joint regions, allowing more focused and effective detection processing, followed by extractions of the upper and lower edges of rock using the Canny algorithm. Four basic geometrical parameters of rock joints－orientation, depth, aperture, and core length－were determined based on the fitting of sinusoids to joints’ edges. Furthermore, the joint density was determined based on the geometric parameters. To calibrate the proposed approach, a borehole in the Rumei hydropower station engineering at Lantsang River was selected as a case study. Orientation of rock joints with gentle dip angles, which was determined from borehole imaging logs, corresponded to the measurement in three horizontal tunnels. Additionally, both joint density and pressure-wave velocity revealed that jointed rock mass was observed in the depth from 100 m to 120 m, and intact rock mass was presented in the depth of 150 m to 170 m, indicating the good performance of the proposed method.

Download Full-text

Experimental Study on Hydromechanical Behavior of an Artificial Rock Joint with Controlled Roughness

Sustainability ◽

10.3390/su11041014 ◽

2019 ◽

Vol 11 (4) ◽

pp. 1014

Author(s):

Seungbeom Choi ◽

Byungkyu Jeon ◽

Sudeuk Lee ◽

Seokwon Jeon

Keyword(s):

Rock Mass ◽

Rock Joint ◽

Great Influence ◽

Rock Joints ◽

In Situ Tests ◽

Joint Roughness ◽

Artificial Rock ◽

Geometric Conditions ◽

Bedding Planes ◽

Hydraulic Aperture

Rock mass contains various discontinuities, such as faults, joints, and bedding planes. Among them, a joint is one of the most frequently encountered discontinuities in rock engineering applications. Generally, a joint exerts great influence on the mechanical and hydraulic behavior of rock mass, since it acts as a weak plane and as a fluid path in the rock mass. Therefore, an accurate understanding on joint characteristics is important in many projects. In-situ tests on joints are sometimes consumptive in terms of time and expenses so that the features are investigated by laboratory tests, providing fundamental properties for rock mass analyses. Although the behavior of a joint is affected by both mechanical and geometric conditions, the latter are often limited, since quantitative control on the conditions is quite complicated. In this study, artificial rock joints with various geometric conditions, i.e., joint roughness, were prepared in a quantitative manner and the hydromechanical characteristics were investigated by several laboratory experiments. Based on the results, a prediction model for hydraulic aperture was proposed in the form of ( e h / e m ) 3 = exp ( − 0.0462 c ) × ( 0.8864 ) J R C , which was a function of the mechanical aperture, joint roughness, and contact area. Relatively good agreement between the experimental results and predicted value indicated that the model is capable of estimating the hydraulic aperture properly.

Download Full-text

Effects of Gouge Fill on Elastic Wave Propagation in Equivalent Continuum Jointed Rock Mass

Materials ◽

10.3390/ma14123173 ◽

2021 ◽

Vol 14 (12) ◽

pp. 3173

Author(s):

Ji-Won Kim ◽

Song-Hun Chong ◽

Gye-Chun Cho

Keyword(s):

Wave Propagation ◽

Rock Mass ◽

Rock Joint ◽

Physical And Mechanical Properties ◽

Jointed Rock ◽

Rock Joints ◽

Shear Joint ◽

Equivalent Continuum Model ◽

Particulate Soil ◽

Equivalent Continuum

The presence of gouge in rock joints significantly affects the physical and mechanical properties of the host rock mass. Wave-based exploration techniques have been widely used to investigate the effects of gouge fill on rock mass properties. Previous research on wave propagation in gouge-filled joints focused on analytical and theoretical methods. The lack of experimental methods for multiple rock joint systems, however, has limited the verification potential of the proposed models. In this study, the effects of gouge material and thickness on wave propagation in equivalent continuum jointed rocks are investigated using a quasi-static resonant column test. Gouge-filled rock specimens are simulated using stacked granite rock discs. Sand and clay gouge fills of 2 and 5 mm thicknesses are tested to investigate the effects of gouge material and thickness. Comprehensive analyses of the effects of gouge thickness are conducted using homogeneous isotropic acetal gouge fills of known thickness. The results show that gouge fill leads to changes in wave velocity, which depend on the characteristics of the gouge fill. The results also show that particulate soil gouge is susceptible to preloading effects that cause permanent changes in the soil fabric and contact geometry and that increased gouge thickness causes a more significant stiffness contribution of the gouge material properties to the overall stiffness of the equivalent continuum specimen. The normal and shear joint stiffnesses for different gouge fill conditions are calculated from the experimental results using the equivalent continuum model and suggested as input parameters for numerical analysis.

Download Full-text

Neutrosophic Functions of the Joint Roughness Coefficient and the Shear Strength: A Case Study from the Pyroclastic Rock Mass in Shaoxing City, China

Mathematical Problems in Engineering ◽

10.1155/2016/4825709 ◽

2016 ◽

Vol 2016 ◽

pp. 1-9 ◽

Cited By ~ 15

Author(s):

Jun Ye ◽

Rui Yong ◽

Qi-Feng Liang ◽

Man Huang ◽

Shi-Gui Du

Keyword(s):

Shear Strength ◽

Rock Mass ◽

Rock Joint ◽

Sampling Bias ◽

Rock Joints ◽

Joint Surface ◽

Pyroclastic Rock ◽

Roughness Coefficient ◽

Joint Roughness Coefficient ◽

Joint Roughness

Many studies have been carried out to investigate the scale effect on the shear behavior of rock joints. However, existing methods are difficult to determinate the joint roughness coefficient (JRC) and the shear strength of rock joints with incomplete and indeterminate information; the nature of scale dependency of rock joints is still unknown and remains an ongoing debate. Thus, this paper establishes two neutrosophic functions of the JRC values and the shear strength based on neutrosophic theory to express and handle the incomplete and indeterminate problems in the analyses of the JRC and the shear strength. An example, including four rock joint samples derived from the pyroclastic rock mass in Shaoxing city, China, is provided to show the effectiveness and rationality of the developed method. The experimental results demonstrate that the proposed neutrosophic functions can express and deal with the incomplete and indeterminate problems of the test data caused by geometry complexity of the rock joint surface and sampling bias. They provide a new approach for estimating the JRC values of the different-sized test profiles and the peak shear strength of rock joints.

Download Full-text

Pemilihan Daging Kelapa Bermutu Berdasarkan Warna dan Tekstur untuk Produksi Wingko Berkualitas Menggunakan Metode Support Vector Machine (SVM) dan Fusi Informasi

Jurnal Teknologi Informasi dan Ilmu Komputer ◽

10.25126/jtiik.2021834391 ◽

2021 ◽

Vol 8 (3) ◽

pp. 587

Author(s):

Arwin Datumaya Wahyudi Sumari ◽

Ahmad Alfian Alfian ◽

Cahya Rahmad

Keyword(s):

Support Vector Machine ◽

Information Fusion ◽

Imaging System ◽

Support Vector ◽

Gray Level ◽

Single Feature ◽

Occurrence Matrix ◽

Selection Of ◽

Coconut Meat

Mutu daging kelapa adalah faktor utama yang menentukan kualitas produksi wingko baik yang berasal dari kelapa muda atau kelapa tua dari varietas genjah. Dalam upaya menjaga kualitas produksi wingko kelapa, diperlukan teknik dalam memilih daging kelapa yang bermutu tinggi secara konsisten dengan bantuan teknologi. Dalam penelitian ini telah dibangun sebuah sistem pencitraan digital berbasis Kecerdasan Artifisial untuk pemilihan daging kelapa bermutu. Pemilihan tersebut didasarkan pada warna dan tekstur dengan memanfaatkan Support Vector Machine (SVM) sebagai pengklasifikasi, dan fusi informasi. Pengolahan citra digital menggunakan kombinasi metode Hue, Saturation, Value (HSV) dan metode Gray-Level Co-Occurrence Matrix (GLCM) sebagai pengekstraksi fitur warna dan fitur energi. Kedua macam fiur tersebut difusikan menjadi fitur tunggal guna mempercepat klasifikasi oleh SVM sebagai landasan pemilihan daging kelapa. Dengan menggunakan sistem ini, pemilihan daging kelapa bermutu berhasil mencapai akurasi sebesar 50%. Dalam penelitian ini juga ditemukan bahwa ketidak tepatan pelabelan memberi dampak signifikan pada akurasi pemilihan daging kelapa. AbstractThe quality of coconut meat is a primary factor which determines the quality of wingko production whether that comes from young coconut or old one from Genjah variety. In the effort of maintaining the quality of coconut wingko production, a technique for selecting high quality of coconut meat in consistent way with the aid of technology is needed. In this research, an Artificial Intelligence-based digital imaging system for selecting quality coconut meat has been developed. The selection is based on color and texture by utilizing Support Vector Machine (SVM) as classifier and information fusion. The digital image processing uses the combination of Hue, Saturation, Value (HSV) and Gray-Level Co-Occurrence Matrix (GLCM) methods as color and energy feature extractors. Both features are fused to obtain single feature to accelerate SVM classification as the basis for selection the coconut meat. By using this system, the selection of quality coconut meat is successful to achieve the accuracy as much as 50%. In this research it was also found that incorrectly labeling gives significant impact to the accuracy of coconut meat selection.

Download Full-text

Detection of image region-duplication forgery based on gray level co-occurrence matrix

Journal of Computer Applications ◽

10.3724/sp.j.1087.2011.01628 ◽

2012 ◽

Vol 31 (6) ◽

pp. 1628-1630

Author(s):

Jia-jia OU ◽

Bi-ye CAI ◽

Bing XIONG ◽

Feng LI

Keyword(s):

Gray Level ◽

Image Region ◽

Region Duplication ◽

Occurrence Matrix

Download Full-text

Gray-Level Co-occurrence Matrix and Random Forest Based Off-line Odia Handwritten Character Recognition

Recent Patents on Engineering ◽

10.2174/1872212112666180601085544 ◽

2019 ◽

Vol 13 (2) ◽

pp. 136-141 ◽

Cited By ~ 2

Author(s):

Abhisek Sethy ◽

Prashanta Kumar Patra ◽

Deepak Ranjan Nayak

Keyword(s):

Feature Extraction ◽

Random Forest ◽

Character Recognition ◽

Recognition Rate ◽

Discrete Wavelet ◽

Gray Level ◽

Handwritten Character Recognition ◽

Handwritten Character ◽

Wide Range ◽

Occurrence Matrix

Background: In the past decades, handwritten character recognition has received considerable attention from researchers across the globe because of its wide range of applications in daily life. From the literature, it has been observed that there is limited study on various handwritten Indian scripts and Odia is one of them. We revised some of the patents relating to handwritten character recognition. Methods: This paper deals with the development of an automatic recognition system for offline handwritten Odia character recognition. In this case, prior to feature extraction from images, preprocessing has been done on the character images. For feature extraction, first the gray level co-occurrence matrix (GLCM) is computed from all the sub-bands of two-dimensional discrete wavelet transform (2D DWT) and thereafter, feature descriptors such as energy, entropy, correlation, homogeneity, and contrast are calculated from GLCMs which are termed as the primary feature vector. In order to further reduce the feature space and generate more relevant features, principal component analysis (PCA) has been employed. Because of the several salient features of random forest (RF) and K- nearest neighbor (K-NN), they have become a significant choice in pattern classification tasks and therefore, both RF and K-NN are separately applied in this study for segregation of character images. Results: All the experiments were performed on a system having specification as windows 8, 64-bit operating system, and Intel (R) i7 – 4770 CPU @ 3.40 GHz. Simulations were conducted through Matlab2014a on a standard database named as NIT Rourkela Odia Database. Conclusion: The proposed system has been validated on a standard database. The simulation results based on 10-fold cross-validation scenario demonstrate that the proposed system earns better accuracy than the existing methods while requiring least number of features. The recognition rate using RF and K-NN classifier is found to be 94.6% and 96.4% respectively.

Download Full-text