Open AccessResearch on Feature Extraction of Local Binary Pattern of SLM Powder Bed Gray Image
Author(s) -
Yu Yin,
Liming,
Guan Dali
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 - 10.1088/1742-6596/1885/3/032007
Subject(s) - artificial intelligence , preprocessor , support vector machine , pattern recognition (psychology) , computer vision , local binary patterns , filter (signal processing) , binary image , binary number , median filter , image quality , feature extraction , computer science , image (mathematics) , gray level , noise (video) , materials science , image processing , mathematics , histogram , arithmetic
The quality of powder bed is one of the important factors that affect the quality of Selective Laser Melting(SLM) of parts. Image preprocessing method and defect identification method are proposed for recoater hopping during powder spreading by SLM. For the collected powder bed image, the Basic Mask method is designed to preprocess the image, uniform the light intensity distribution of the image and filter out the image noise. To extract the defect features accurately, different Local Binary Patterns (LBP) operators are used to classify and calculate the identification accuracy of each operator by Support Vector Machine (SVM). The recognition accuracy of this method is up to 98%.