The naming of rock hand specimens is usually conducted by geological workers based on observed mineral composition,texture characteristics,etc.,combined with their own knowledge reserves.The accuracy of identification...The naming of rock hand specimens is usually conducted by geological workers based on observed mineral composition,texture characteristics,etc.,combined with their own knowledge reserves.The accuracy of identification results is limited by the experience,research interests,and identification level of the identifier,as well as the complexity of the rock composition.To improve the efficiency of rock hand specimen identification,this paper proposes a method for rock image recognition and classification based on deep learning and the Inception-v3 model.It encompasses the preprocessing of collected photographs of typical intrusive rock hand specimens,along with augmenting the sample size through data augmentation methods,culminating in a comprehensive dataset comprising 12501 samples.Experimental results show that the model has good learning ability when there is sufficient data.Through iterative training of the Inception-v3 model on the rock dataset,the accuracy of rock image recognition reaches 92.83%,with a loss of only 0.2156.Currently,several common types of intrusive rocks can be identified:gabbro,granite,diorite,peridotite,granodiorite,diabase,and granite porphyry.Software is developed for open use by geological workers to improve work efficiency.展开更多
基金Supported by the Qinghai Province Geological Exploration Fund Project(2023085029ky004)Natural Science Foundation of Jilin Provinc(20220101161JC)Open Project Plan of Shandong Province Deep Gold Exploration in Big Data Application and Development Engineering Laboratory(SDK202203).
文摘The naming of rock hand specimens is usually conducted by geological workers based on observed mineral composition,texture characteristics,etc.,combined with their own knowledge reserves.The accuracy of identification results is limited by the experience,research interests,and identification level of the identifier,as well as the complexity of the rock composition.To improve the efficiency of rock hand specimen identification,this paper proposes a method for rock image recognition and classification based on deep learning and the Inception-v3 model.It encompasses the preprocessing of collected photographs of typical intrusive rock hand specimens,along with augmenting the sample size through data augmentation methods,culminating in a comprehensive dataset comprising 12501 samples.Experimental results show that the model has good learning ability when there is sufficient data.Through iterative training of the Inception-v3 model on the rock dataset,the accuracy of rock image recognition reaches 92.83%,with a loss of only 0.2156.Currently,several common types of intrusive rocks can be identified:gabbro,granite,diorite,peridotite,granodiorite,diabase,and granite porphyry.Software is developed for open use by geological workers to improve work efficiency.
