Research on Intelligent Identification of Rock Types Based on Faster R-CNN Method

Liu, Xiaobo; Wang, Huaiyuan; Jing, Hongdi; Shao, Anlin; Wang, Liancheng

doi:10.1109/access.2020.2968515

Cited by 56 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The nonlinear function is used for the obtained result to obtain the convolution graph of the first layer network. In the middle layer of the convolutional layer, the output result of the previous layer is trained and learned according to the weight parameters and offsets in the layer, and the image is convolved with different receptive fields of the same convolution kernel to reduce parameter settings to reduce the complexity of the network [20]. In the middle layer of the convolutional network, the high-level features of the image can be obtained through multiple feature extraction.…”

Section: Image Processing Technology Based On Cnnmentioning

confidence: 99%

Image Analysis Technology in the Detection of Particle Size Distribution and the Activity Effect of Low‐Silicon Copper Tailings

Zhao

Liu

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

To speed up the comprehensive utilization and treatment of copper tailings, the digital image processing technology is proposed in this study to detect the low-silicon copper tailings (LSCT) using a scanning electron microscope (SEM), and the particle size distribution (PSD) and the activity of LSCT are analysed under the action of mechanical force. Firstly, the current status and application of copper tailings are introduced, and the influence of the particle size of LSCT on its practical application performance is explained. Secondly, the LSCT SEM image target recognition model is designed based on the convolutional neural network (CNN), and the model parameters and the reference CNN are selected. Finally, the experimental process is designed, a SEM image data set of LSCT is prepared, the model is trained through the training set, and the image recognition test is performed on the produced data set. The experimental results show that when the number of iterations of the CNN is 10, the accuracy of model recognition can be guaranteed. After the action of mechanical force, the PSD of LSCT is mainly concentrated at 1 μm~100 μm; that around 1.4 μm~10 μm is the largest, and the PSD of LSCT around 1.4 μm increases with the increase of action time of mechanical force, but the PSD of the LSCT begins to increase when the grinding time exceeds 150 minutes, and the activity of LSCT reaches the maximum (75.545%) at 150 minutes. The average accuracy of SEM image detection of the model is 86.97%, and the model based on DenseNet shows better recognition accuracy than other models. This study provides a reference for analysing the PSD of LSCT.

show abstract

Section: Image Processing Technology Based On Cnnmentioning

confidence: 99%

Image Analysis Technology in the Detection of Particle Size Distribution and the Activity Effect of Low‐Silicon Copper Tailings

Zhao

Liu

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Rock type identification is a critical first step in resource exploration and development [ 1 , 2 , 3 ]. This involves a visual examination of the specimens for specific properties that are typically based on color, composition, sedimentary structures, and granularity [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

“…This involves a visual examination of the specimens for specific properties that are typically based on color, composition, sedimentary structures, and granularity [ 1 ]. Manual techniques are tedious, time-consuming, and can be subjective due to the quality of the preserved specimens [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Segmentation for Multi-Rock Types on Digital Outcrop Photographs Using Deep Learning Techniques

Malik

Puasa²,

Lai

2022

Sensors

View full text Add to dashboard Cite

The basic identification and classification of sedimentary rocks into sandstone and mudstone are important in the study of sedimentology and they are executed by a sedimentologist. However, such manual activity involves countless hours of observation and data collection prior to any interpretation. When such activity is conducted in the field as part of an outcrop study, the sedimentologist is likely to be exposed to challenging conditions such as the weather and their accessibility to the outcrops. This study uses high-resolution photographs which are acquired from a sedimentological study to test an alternative basic multi-rock identification through machine learning. While existing studies have effectively applied deep learning techniques to classify the rock types in field rock images, their approaches only handle a single rock-type classification per image. One study applied deep learning techniques to classify multi-rock types in each image; however, the test was performed on artificially overlaid images of different rock types in a test sample and not of naturally occurring rock surfaces of multiple rock types. To the best of our knowledge, no study has applied semantic segmentation to solve the multi-rock classification problem using digital photographs of multiple rock types. This paper presents the application of two state-of-the-art segmentation models, namely U-Net and LinkNet, to identify multiple rock types in digital photographs by segmenting the sandstone, mudstone, and background classes in a self-collected dataset of 102 images from a field in Brunei Darussalam. Four pre-trained networks, including Resnet34, Inceptionv3, VGG16, and Efficientnetb7 were used as a backbone for both models, and the performances of the individual models and their ensembles were compared. We also investigated the impact of image enhancement and different color representations on the performances of these segmentation models. The experiment results of this study show that among the individual models, LinkNet with Efficientnetb7 as a backbone had the best performance with a mean over intersection (MIoU) value of 0.8135 for all of the classes. While the ensemble of U-Net models (with all four backbones) performed slightly better than the LinkNet with Efficientnetb7 did with an MIoU of 0.8201. When different color representations and image enhancements were explored, the best performance (MIoU = 0.8178) was noticed for the L*a*b* color representation with Efficientnetb7 using U-Net segmentation. For the individual classes of interest (sandstone and mudstone), U-Net with Efficientnetb7 was found to be the best model for the segmentation. Thus, this study presents the potential of semantic segmentation in automating the reservoir characterization process whereby we can extract the patches of interest from the rocks for much deeper study and modeling to be conducted.

show abstract

“…Chen et al [39] introduced ResNet50 and ResNet101 neural networks to construct a classifier to complete the identification of rock thin-section images, reaching 90.24% and 91.63% performance, respectively. In addition, some other researchers have studied rock type classification based on datasets obtained by digital cameras instead of microscopic images [40][41][42].…”

Section: Introductionmentioning

confidence: 99%

Experimental Studies on Rock Thin-Section Image Classification by Deep Learning-Based Approaches

Zhang

2022

Mathematics

View full text Add to dashboard Cite

Experimental studies were carried out to analyze the impact of optimizers and learning rate on the performance of deep learning-based algorithms for rock thin-section image classification. A total of 2634 rock thin-section images including three rock types—metamorphic, sedimentary, and volcanic rocks—were acquired from an online open-source science data bank. Four CNNs using three different optimizer algorithms (Adam, SGD, RMSprop) under two learning-rate decay schedules (lambda and cosine decay modes) were trained and validated. Then, a systematic comparison was conducted based on the performance of the trained model. Precision, f1-scores, and confusion matrix were adopted as the evaluation indicators. Trials revealed that deep learning-based approaches for rock thin-section image classification were highly effective and stable. Meanwhile, the experimental results showed that the cosine learning-rate decay mode was the better option for learning-rate adjustment during the training process. In addition, the performance of the four neural networks was confirmed and ranked as VGG16, GoogLeNet, MobileNetV2, and ShuffleNetV2. In the last step, the influence of optimization algorithms was evaluated based on VGG16 and GoogLeNet, and the results demonstrated that the capabilities of the model using Adam and RMSprop optimizers were more robust than that of SGD. The experimental study in this paper provides important practical value for training a high-precision rock thin-section image classification model, which can also be transferred to other similar image classification tasks.

show abstract

Research on Intelligent Identification of Rock Types Based on Faster R-CNN Method

Cited by 56 publications

References 16 publications

Image Analysis Technology in the Detection of Particle Size Distribution and the Activity Effect of Low‐Silicon Copper Tailings

Image Analysis Technology in the Detection of Particle Size Distribution and the Activity Effect of Low‐Silicon Copper Tailings

Segmentation for Multi-Rock Types on Digital Outcrop Photographs Using Deep Learning Techniques

Experimental Studies on Rock Thin-Section Image Classification by Deep Learning-Based Approaches

Contact Info

Product

Resources

About