Abstract
The recognition and classification of rock lithology is an extremely important task of geological surveys. This paper proposes a new method for quickly identifying multiple types of rocks suitable for geological survey work field. Based on the two lightweight convolutional neural networks (CNNs), SqueezeNet and MobileNets, and combined with the transfer learning method, a rock lithology recognition model was established. The model was embedded into a smart phone for testing. This method was used to identify and classify the images of 28 kinds of rocks. Through a comprehensive comparison of the two models, the accuracy of SqueezeNet and MobileNets in the test dataset is 94.55% and 93.27%, respectively. Via the two models, the average recognition time of a single rock image is 557 and 836 milliseconds, and rock images with a recognition accuracy of over 96% accounted for 95% and 93% of the entire test dataset. Compared with the classification method based on rock thin section images, this method does not need to make rock thin sections. This paper meets the requirements of workers to quickly and accurately identify rocks in the work field, which improves the work efficiency and limits identification costs.
Highlights
The recognition and classification of rock lithology is an important part of geological research, and is important work in the field of geological surveys
This paper presented a new method for identifying multiple types of rocks using lightweight convolutional neural networks (CNNs) model in the geological survey work field
The recognition accuracies based on the SqueezeNet and MobileNets convolution neural network models were 94.55% and 93.27% on the test dataset of the smart phones, and the single-rock image results with a confidence rate of more than 96% accounted for 95% and 93% of the test dataset
Summary
The recognition and classification of rock lithology is an important part of geological research, and is important work in the field of geological surveys. Fan et al.: Recognizing Multiple Types of Rocks Quickly and Accurately Based on Lightweight CNNs Model the characteristics of color image histograms [12] This kind of method solves the problems of strong subjectivity and low identification efficiency existing in traditional identification methods, identification still takes place after making a rock thin section in the laboratory [13]. 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 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. Compared with the rock classification method based on rock thin section images, the presented method improves work efficiency and reduces recognition cost
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
