Title :
Image features extraction of gas/liquid two-phase flow in horizontal pipeline by GLCM and GLGCM
Author :
Wang, Hongyi ; Dong, Feng
Author_Institution :
Sch. of Electr. Eng. & Autom., Tianjin Univ., Tianjin, China
Abstract :
Gray level co-occurrence matrix (GLCM) and the gray level-gradient co-occurrence matrix (GLGCM) were used to analyze gas/liquid flow images. Gas/liquid two-phase flow experiments were practiced and high-speed images were captured. A set of textural features were extracted from the GLCM and GLGCM. Examples of experimental results confirm the effectiveness of several features among them. All of the effective textural features have a relation with the gas/liquid density ratio, but not relate to the superficial velocity of gas or liquid.
Keywords :
feature extraction; flow visualisation; high-speed techniques; pipe flow; two-phase flow; GLCM; GLGCM; gas-liquid two phase flow; gray level cooccurrence matrix; gray level gradient cooccurrence matrix; high speed images; horizontal pipeline flow; image feature extraction; Digital images; Electric variables measurement; Feature extraction; Fluid flow; Fluid flow measurement; Image analysis; Image texture analysis; Instruments; Pipelines; Statistics; GLCM; GLGCM; gas/liquid density ratio; gas/liquid two-phase flow; textural feature;
Conference_Titel :
Electronic Measurement & Instruments, 2009. ICEMI '09. 9th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-3863-1
Electronic_ISBN :
978-1-4244-3864-8
DOI :
10.1109/ICEMI.2009.5274632
