Research on Feasibility of Convolution Neural Networks for Rock Thin Sections Image Retrieval
Guojian Cheng, Qingqing Yue, Xinjian Qiang · 2018
In recent years, convolution neural networks have attracted extensive attention from researchers. It has outstanding performance in large-scale image processing, especially in the field of pattern recognition. Combining geological exploration with computer technology, it has achieved good achievements in rock image processing, and it is still being explored in order to better integrate it into practice. For geological exploration researchers, how to perform rapid and effective retrieval of a large number of rock thin sections image is worth investigating. Traditional text-based retrieval methods can no longer meet the requirements. For this reason, this paper attempts to introduce the convolution neural network into the retrieval of rock thin sections and analyze its feasibility in the retrieval of rock thin sections images.