Rock images classification by using deep convolution neural network

Abstract

Abstract. Granularity analysis is one of the most essential issues in authenticate under microscope. To improve the efficiency and accuracy of traditional manual work, an convolutional neural network based method is proposed for granularity analysis from thin section image, which chooses and extracts features from image samples while build classifier to recognize granularity of input image samples. 4800 samples from Ordos basin are used for experiments under colour spaces of HSV, YCbCr and RGB respectively. On the test dataset, the correct rate in RGB colour space is 98.5%, and it is believable in HSV and YCbCr colour space. The results show that the convolution neural network can classify the rock images with high reliability. IntroductionFor the effective development of reservoirs, it is necessary to provide a comprehensive reservoir description and characterization to determine the underground gas content. Granularity analysis is an important work of it [1]. The traditional method for rock classification is a manual work with many problems such as time-consuming and low accuracy. With the development of science and technology, Artificial intelligence is successfully applied in all walks of life. Many domestic and foreign scholars have done researches in the automatic classification of rock images, such as, Cheng Guojian and Liu Ye [2-3] used shallow neural network and SVM to classify rock images. Mariusz Młynarczuk et al. [4] performed the Classification of thin rock images respectively in RGB, CIELab, YIQ and HSV colour spaces using the nearest neighbour algorithm, K-nearest neighbour, the nearest pattern algorithm, and the optimized spherical neighbourhood; Hossein Izadi et al.[5] established a neural network to identify the rock mineral, whose accuracy was 93.81%. The above methods show that the application of machine learning in rock classification can improve its efficiency and accuracy.However, using machine learning to classify rock images still has the following shortcomings. Firstly, to classify rock images by machine learning is based on the premise of artificial extraction of image features. Secondly, if the images are large, training a shallow neural network is almost impossible.Convolution neural network (CNN) is an important deep learning architecture. It can extract the image features automatically and has a high classify accuracy. CNN has achieved a wide range of applications such as plant classification, face recognition, handwritten Chinese character recognition and so on [6][7][8]. In this paper, we construct a new convolution neural network for rock classification, rock images respectively in RGB, HSV, YCbCr colour spaces are used to train it, then contrasted the results and choose the best one. The Rock ImagesIt is usually determined by professional geological researchers for types and structural parameters of rocks after identifying rock thin section under polarized light microscopy. The rock images used in

Recognizing Multiple Types of Rocks Quickly and Accurately Based on Lightweight CNNs Model

“…The model extracts features by searching image pixels, without manual operation, reducing the influence of subjective factors. Compared with the use of rock thin section image processing technology to identify rocks [8], [11], [40], [41], [16], the presented method has lower requirements on the size of rock image, imaging range and light intensity. In this paper, the models based on MobileNets and SqueezeNet training were compared with the standard convolutional neural network ResNet in terms of running time and space.…”

“…Cheng et al used image processing technology to input features extracted from the gray digital image of rock thin sections into a neural network with an accuracy of 93.3% [10]. Guo et al calculated the standard arithmetic values of the different color channels of the original rock image, and established the mapping relationship between the feature space and the rock image category through the neural network [11]. The recognition accuracy of rock images in different color spaces is over 95%.…”

“…The accuracy of the algorithm was as high as 95% on the validation set of the Googlenet architecture, but the model requires more resources in the calculation, and is not the best solution for the geological survey field. Although these studies have reduced labor cost problem and strong subjectivity that occurs in the microscopic observation method based on rock thin section images [12], [19], [11], [20], and even provide a solution for rock identification in the geological survey field, they still lack comparison with other CNN models. Therefore, how to provide a more complete solution for geological survey personnel to quickly and accurately obtain rock lithology information is still an urgent problem to be solved.…”

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

“…Cheng and Guo [18] proposed a method for granularity analysis of rock flake images based on convolutional neural networks. 4800 samples were tested in HSV, YcbCr and RGB color spaces.…”

A New Belt Ore Image Segmentation Method Based on the Convolutional Neural Network and the Image-Processing Technology

“…At present, the top-5 accuracy of many convolutional neural networks in image recognition tasks can reach more than 90% for the ImageNet dataset [24][25][26]. Many research studies on rock image recognition and classification based on deep learning have achieved high accuracy [8,27,28].…”