Jiyuan Wang
ABSTRACT
In the exploration of oil, gas, mineral resources and geological analysis, the recognition of rock samples and the calculation of oil content are very important. The identification methods of rock samples mainly include logging, remote sensing, thin section analysis, etc. It is a new way to use deep learning method to establish automatic classification and calculation models. In this paper, we build the Resnet50 residual neural network model, use image enhancement algorithms to improve the recognition accuracy, train and visualize the network model. Under the condition of white light, we extract the features of each image and identify various types of rock samples. The result shows the accuracy of recognition is up to 90.5%. Under the condition of fluorescent lights, we use unsupervised learning algorithm to analyze different colors of images. Then we obtain the function between the different grayscales of the RGB three-channel color images and the colors of images. Finally, we calculate the oil content results of rock samples. The evaluation time for each image is 17s.
- Nikola Banić, Karlo Koščević, and Sven Lončarić. 2017. Unsupervised learning for color constancy. arXiv preprint arXiv:1712.00436(2017).Google Scholar
- Purbaditya Bhattacharya and U. Zölzer. 2020. Attentive Inception Module based Convolutional Neural Network for Image Enhancement. 2020 Digital Image Computing: Techniques and Applications (DICTA) (2020), 1–8.Google Scholar
- Sing T. Bow. 2002. Pattern Recognition and Image Preprocessing (2nd ed.). CRC press.Google Scholar
- Hieu Minh Bui, Margaret Lech, Eva Cheng, Katrina Neville, and Ian S. Burnett. 2016. Using grayscale images for object recognition with convolutional-recursive neural network. In Proceedings of the IEEE 6th International Conference on Communications and Electronics (ICCE 2016). IEEE, 321–325. https://doi.org/10.1109/CCE.2016.7562656Google ScholarCross Ref
- Xu Chen, Jianjun Li, Yanchao Zhang, Yu Lu, and Shaoyu Liu. 2020. Automatic feature extraction in X-ray image based on deep learning approach for determination of bone age. Future Generation Computer Systems 110 (September 2020), 795–801. https://doi.org/10.1016/j.future.2019.10.032Google Scholar
- Zoubin Ghahramani. 2003. Unsupervised Learning. In Advanced Lectures on Machine Learning. ML 2003, Olivier Bousquet, Ulrike von Luxburg, and Gunnar Rätsch (Eds.). Lecture Notes in Computer Science, Vol. 3176. Springer, Berlin, Heidelberg, 72–112. https://doi.org/10.1007/978-3-540-28650-9_5Google Scholar
- Chen Guojian and Li Peisong. 2021. Rock Thin-Section Image Classification based on Residual Neural Network. 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP) (2021), 521–524.Google ScholarCross Ref
- Soufiane Hayou, Eugenio Clerico, Bo He, George Deligiannidis, A. Doucet, and J. Rousseau. 2021. Stable ResNet. In AISTATS.Google Scholar
- Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 770–778.Google Scholar
- Ming He, Xudong Zhao, Yu Lu, and Yi Hu. 2021. An improved AlexNet model for automated skeletal maturity assessment using hand X-ray images. Future Generation Computer Systems 121 (August 2021), 106–113. https://doi.org/10.1016/j.future.2021.03.018Google Scholar
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (May 2015), 436–444. https://doi.org/10.1038/nature14539Google ScholarCross Ref
- Eimantas Ledinauskas, J. Ruseckas, Alfonsas Jursenas, and Giedrius Burachas. 2020. Training Deep Spiking Neural Networks. ArXiv abs/2006.04436(2020).Google Scholar
- Yu Lu, Xianghua Fu, Fangxiong Chen, and Kelvin K.L. Wong. 2020. Prediction of fetal weight at varying gestational age in the absence of ultrasound examination using ensemble learning. Artificial Intelligence in Medicine 102 (January 2020), 101748. https://doi.org/10.1016/j.artmed.2019.101748Google ScholarDigital Library
- Yu Lu, Xianghua Fu, Xiaoqing Li, and Yingjian Qi. 2020. Cardiac Chamber Segmentation Using Deep Learning on Magnetic Resonance Images from Patients Before and After Atrial Septal Occlusion Surgery. In Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2020). IEEE, 1211–1216. https://doi.org/10.1109/EMBC44109.2020.9175618Google ScholarCross Ref
- Yu Lu, Xi Zhang, Xianghua Fu, Fangxiong Chen, and Kelvin K.L. Wong. 2019. Ensemble Machine Learning for Estimating Fetal Weight at Varying Gestational Age. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), Vol. 33. 9522–9527. https://doi.org/10.1609/aaai.v33i01.33019522Google ScholarDigital Library
- Raman Maini and Himanshu Aggarwal. 2010. A Comprehensive Review of Image Enhancement Techniques. Journal of Computing 2, 3 (March 2010), 8–13.Google Scholar
- Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng. 2011. Multimodal Deep Learning. In Proceedings of the 28th International Conference on Machine Learning (ICML 2011). 689–696.Google Scholar
- Akio Ogura, Aoi Kamakura, Youhei Kaneko, Tomoya Kitaoka, Norio Hayashi, and Anna Taniguchi. 2017. Comparison of grayscale and color-scale renderings of digital medical images for diagnostic interpretation. Radiological Physics and Technology 10, 3 (September 2017), 359–363. https://doi.org/10.1007/s12194-017-0393-6Google ScholarCross Ref
- V. Panferov, D. Tailakov, and A. Donets. 2020. Recognition of Rocks Lithology on the Images of Core Samples. 2020 Science and Artificial Intelligence conference (S.A.I.ence) (2020), 54–57.Google Scholar
- Hu Qicheng, Ye Weimin, Wang Qiong, and Chen Yonggui. 2020. Recognition of Lithology with Big Data of Geological Images. Journal of Engineering Geology 28, 6 (December 2020), 1466–1473. https://doi.org/10.13544/j.cnki.jeg.2019-496Google Scholar
- Lei Shu, Kenneth McIsaac, Gordon R Osinski, and Raymond Francis. 2017. Unsupervised feature learning for autonomous rock image classification. Computers & Geosciences 106 (September 2017), 10–17. https://doi.org/10.1016/j.cageo.2017.05.010Google Scholar
- Mikhail Sidorenko, Denis Orlov, Mohammad Ebadi, and Dmitry Koroteev. 2021. Deep learning in denoising of micro-computed tomography images of rock samples. Computers & Geosciences 151 (June 2021), 104716. https://doi.org/10.1016/j.cageo.2021.104716Google Scholar
- Sasha Targ, Diogo Almeida, and Kevin Lyman. 2016. Resnet in Resnet: Generalizing Residual Architectures. In Proceedings of the International Conference on Learning Representations (ICLR 2016) Workshop Track. 1–4.Google Scholar
- Alan Wilkins. 2008. Ultraviolet light and its use with fluorescent minerals. Technical Report. Fluorescent Mineral Society (FMS). 1–9 pages.Google Scholar
- Yang You, Z. Zhang, Cho-Jui Hsieh, J. Demmel, and K. Keutzer. 2018. ImageNet Training in Minutes. Proceedings of the 47th International Conference on Parallel Processing (2018).Google ScholarDigital Library
- Ming Zhao, Wei Yang, Yu Lu, and Kelvin K.L Wong. 2020. A novel U-Net approach to segment the cardiac chamber in magnetic resonance images with ghost artifacts. Computer Methods and Programs in Biomedicine 196 (November 2020), 105623. https://doi.org/10.1016/j.cmpb.2020.105623Google Scholar
- Xiliang Zhu, Wei Yang, Yu Lu, Ming Zhao, Ke Yang, Shiqian Wu, Hui Zhang, and Kelvin K.L. Wong. 2021. Comparative analysis of active contour and convolutional neural network in rapid left-ventricle volume quantification using echocardiographic imaging. Computer Methods and Programs in Biomedicine 199 (February 2021), 105914. https://doi.org/10.1016/j.cmpb.2020.105914Google Scholar
Index Terms
- Recognition of rock images and quantification of oil content using deep residual neural networks
Recommendations
Facial expression recognition with Convolutional Neural Networks
Facial expression recognition has been an active research area in the past 10 years, with growing application areas including avatar animation, neuromarketing and sociable robots. The recognition of facial expressions is not an easy problem for machine ...
Treatment of Alkaline Wastewater from Oil Refinery Using Circulating Biological Aerated Filter
CDCIEM '11: Proceedings of the 2011 International Conference on Computer Distributed Control and Intelligent Environmental MonitoringThe alkaline wastewater from oil refinery is a high concentration alkaline wastewater, which contains a great deal of sulfide phenol and oil pollutants. A novel two stage circulating biological aerated filter (CBAF) was used to treat the alkaline ...
Prediction and classification of minerals using deep residual neural network
AbstractMinerals are in great demand because of their pervasive application in atomic energy and their use as raw materials for other industries. Despite this, it is challenging to identify and classify the minerals due to the deposit's broadness, mineral ...
Comments