TY - A2的Rana Zeeshan A . AU -风扇Guangpeng AU - Chen Feixiang AU - Chen Danyu AU - Li Yan盟——咚,焉耆PY - 2020 DA - 2020/05/19 TI -深学习模型的快速、准确识别智能手机SP - 7462524六世岩石- 2020 AB -在地质调查中,岩石岩性的识别和分类是一个重要的内容。基于岩石薄片的识别方法识别周期长，识别成本高，不能保证识别的准确性。而且，上述方法在实际应用中并不能提供有效的解决方案。智能手机作为一种具有多个传感器的通讯设备，被大多数地质调查人员随身携带。本文开发了一个基于卷积神经网络的智能手机应用。在这个应用中，手机的摄像头可以用来拍摄岩石的照片。可以在很短的时间内快速、准确地识别岩石类型和岩性。提出了一种快速、准确地识别现场岩性的方法。基于用于深度学习的轻量级卷积神经网络ShuffleNet，结合transfer learning方法，建立了岩石图像的识别模型。然后，经过训练的模型被部署到智能手机上。 A smartphone application for identifying rock lithology was designed and developed to verify its usability and accuracy. The research results showed that the accuracy of the recognition model in this paper was 97.65% on the verification data set of the PC. The accuracy of recognition on the test data set of the smartphone was 95.30%, among which the average recognition time of the single sheet was 786 milliseconds, the maximum value was 1,045 milliseconds, and the minimum value was 452 milliseconds. And the single-image accuracy above 96% accounted for 95% of the test data set. This paper presented a new solution for the rapid and accurate recognition of rock lithology in field geological surveys, which met the needs of geological survey personnel to quickly and accurately identify rock lithology in field operations. SN - 1574-017X UR - https://doi.org/10.1155/2020/7462524 DO - 10.1155/2020/7462524 JF - Mobile Information Systems PB - Hindawi KW - ER -