A transfer learning method for automatic identification of sandstone microscopic images

Classification of sandstone microscopic images is an essential task in geology, and the classical method is either subjective or time-consuming. Computer aided automatic classification has been proved useful, but it seldom considers the situation where sandstone images are collected from separated regions. In this paper, we provide a method called Festra, which uses transfer learning to handle the problem of interregional sandstone microscopic image classification. The method contains two parts: one is feature selection, which aims to screen out features having great difference between the regions, the other is instance transfer using an enhanced TrAdaBoost, whose object is to mitigate the difference among thin section images collected from the regions. Experiments are conducted based on the sandstone images taken from four regions in Tibet to study the performance of Festra. The experimental results have proved both effectiveness and validity of Festra, which provides competitive prediction performance on all the four regions, with few target instances labeled suitable for the field use.