Marble microsection automatically identifying method

Abstract

The invention discloses a marble microsection automatically identifying method. The marble microsection automatically identifying method comprises the steps of 1) converting a color image into a grey level image; 2) referring to two-dimensional discrete wavelets to decompose the gray level image to a low-frequency coefficient matrix, a horizontal coefficient matrix, a vertical coefficient matrix and a diagonal coefficient matrix; 3) grading the element values of the four coefficient matrixes between 0-255, and calculating gradient distributions; 4) based on every gradient distribution, calculating distribution characteristics including mean value, median, variance, skewness and peak index to compose textural feature value vectors; 5) taking a section image as the textural feature value vectors, storing a sample set and through a random forest classification technology, automatically determining whether a rock section is a marble section. The marble microsection automatically identifying method automatically identifies marble microsections through the information processing technology, makes full use of the textural features and the lithological composition of marble, is simple and efficient in calculation and expansible and can improve the identifying accuracy along with increase of the data storage of rock sections and have application values in geological exploration and mineral study.

Description

technical field [0001] The invention relates to a method for identifying objects by using images, in particular to an automatic identification method for marble microscopic slices. The method aims at the high cost of manual identification of rock microscopic slices, and uses information processing technology to realize automatic identification of marble thin slices. identification. Extract the texture features of the image, convert the thin slice image into a texture feature value vector, and then use artificial intelligence to automatically identify rock thin slices. Background technique [0002] Marble is an igneous rock formed by carbonate rock through regional metamorphism or contact metamorphism, and is an excellent building material and raw material for arts and crafts. Rock thin section identification is to determine the type of rock based on the texture characteristics of the rock, and then determine its structure, source and genesis. Existing identification of roc...

AI Technical Summary

Problems solved by technology

Existing rock thin section identification is mostly manual, which not only requires professional identification experts, but also is expensive and inefficient; the identification process relies too much on personal experience and cannot be repeated

Images