Research Of Rock Image Stitching Based On SURF Feature

With the development and utilization of petroleum resources continuously,rock micro-structure researching and developing has become the focus of world with the economic and technological.For underground operations,such as field mining,composition analysis,the key is to acquire accurate date of rock environment on a large range.Thin sections are important research subject for microstructures.The form,range,grain size and fabric of the rock can be studied in detail under a microscope.However,with the limitation of the scope of microscope horizon,the overall characteristics and the local details of the rock thin section cannot be showed clearly.This dissertation applies the image mosaic technology based on the SURF feature(Speeded Up Robust Features)to mosaic single-view rock images into large-view rock image.This dissertation explains the process of image stitching technology,analyses the procedure of SURF algorithm for extracting feature points.With an emphasis on the application of image stitching to rocks,the advantages and disadvantages of the SURF algorithm in analyzed and improved.On one hand,the overlapping regions of the images are calculated and the feature points of overlapping regions are extracted,so that matches can reduce the computation time and the error rate.On the other hand,bi-directional matching based on Bray-Curtis distance is applied to the overlapping regions which can effectively overcome the one-to-many matching problem that occurs when the similarity is large.Then,select the appropriate fusion algorithm to eliminate stitching when stitching is complete.After the stitch of two images,this method is expanded to huge amounts of high-resolution microscopy images for stitching and a comprehensive super ultra-high resolution panoramic view of the micrograph is got.Ultimately,researchers can observe the overview features under the large scale and study the local details under small scale.