Marble microsection automatically identifying method

A thin-film, automatic technology used in character and pattern recognition, instruments, computer parts, etc. to solve problems such as inefficiency, identification process dependent on personal experience, and high cost

Inactive Publication Date: 2014-10-22
南京大学镇江高新技术研究院
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing rock thin section identification is mostly manual, which not only requires professional identification experts, ...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Marble microsection automatically identifying method
  • Marble microsection automatically identifying method
  • Marble microsection automatically identifying method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] figure 1 Shown is the technical framework of the automatic identification method for marble micro-thin sections. The input to the method is a microscopic image of the rock slice; the output of the method is whether the rock slice belongs to marble. In order to ensure the correct application of the method, it is necessary to prepare a rock thin section image data set in advance, and mark whether each image belongs to marble in the data set. The technical framework is divided into five steps: first, convert the color bitmap image into a grayscale image; then decompose the grayscale image into four coefficient matrices of low frequency, horizontal, vertical and diagonal by referring to wavelet transform; then convert the four coefficient matrices The element value is gradientized to 0-255, and the gradient distribution is counted; then the distribution characteristics of the four gradient distributions are counted respectively to form a texture eigenvalue vector; finally,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06K9/62
Inventor 郝慧珍汪丹茹顾庆胡修棉陈道蓄
Owner 南京大学镇江高新技术研究院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap