Open AccessSummary of Metal Fracture Image Recognition Method
Author(s) -
Yufei Lu,
Lin Wang,
Danguang Pan,
Xiaoxia Chen
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 - 10.1088/1742-6596/1982/1/012070
Subject(s) - fracture (geology) , artificial intelligence , computer science , pattern recognition (psychology) , feature (linguistics) , matching (statistics) , image (mathematics) , computer vision , engineering , mathematics , linguistics , geotechnical engineering , philosophy , statistics
Fracture is the metal component in the test or use of the fracture surface after the formation of a matching section. In fracture analysis, the macroscopic and microscopic morphology of fracture provides the most direct information for failure analysis and the most direct evidence for fracture analysis. How to effectively process a series of feature information contained in fracture image and make reasonable use of these feature information is of great significance in engineering practice. At present, metal fatigue failure detection in industrial production mainly relies on human eyes, experience and simple auxiliary tools. However, it is difficult to guarantee the accuracy of detection because of individual differences. To solve this problem, this paper lists three metal fracture image recognition methods, which are Grouplet-RVM recognition method, the empirical Ridgelet-2DPCA method and the empirical Ridgelet-KPCA method. All the three methods aim to extract higher recognition effect so as to compare and optimize the recognition of metal fracture images. The advantages and disadvantages of these methods are discussed in detail in this article for ease of use.