Open AccessA steel classification algorithm based on surface defects
Author(s) -
Wu Qinge,
An Ziming,
Lintao Zhou,
Chen Hu,
Yingbo Lu,
Zhiyuan Ma
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1939/1/012082
Subject(s) - artificial intelligence , pattern recognition (psychology) , co occurrence matrix , image texture , feature extraction , computer science , gray level , probabilistic neural network , image (mathematics) , artificial neural network , texture (cosmology) , probabilistic logic , feature (linguistics) , contextual image classification , computer vision , image processing , time delay neural network , linguistics , philosophy
In the research of image recognition and classification, image retrieval, image data mining, and so on, feature extraction is the basic work, among which the texture feature of an image is of great significance to describe the content of the image. In this paper, an extraction method of steel texture features based on a gray co-occurrence matrix is presented, and the influence of various structural parameters on the structure is analyzed. The feature extraction of specific texture images based on a gray level co-occurrence matrix is realized, and the data classification is carried out by using a probabilistic neural network.