Title :
Image processing and classification of metal fracture surface
Author_Institution :
Sch. of Mech. & Electr. Eng., Soochow Univ., Suzhou
Abstract :
In this paper, a method of the image processing of the metal fracture for eliminating the noise, detecting the edges of the image and classification of the typical morphology of the metal fracture surface by obtaining the imagespsila character based on the mathematical morphology will be described. The methods of the normalized pattern spectrum have unchangeable characteristic for rotating, zooming or moving the images. Then the images can be classified by using artificial neural network. In this paper, 60 images of corrosion fatigue fracture, stream design fracture and intergranular cracking fracture are used as a study samples and 48 images are used as a test samples. The data of the experiment explain the feasibility of the method and analyze the cause of the error.
Keywords :
corrosion fatigue; edge detection; fatigue cracks; image classification; mechanical engineering computing; neural nets; artificial neural network; corrosion fatigue fracture; edges detection; image character; image classification; image processing; intergranular cracking fracture; mathematical morphology; metal fracture surface; normalized pattern spectrum; stream design fracture; Filters; Image analysis; Image processing; Pattern analysis; Pattern recognition; Shape measurement; Surface cracks; Surface morphology; Surface waves; Working environment noise; Metal Fracture Surface; Normalized Pattern Spectrum; Top-Hat Transformation; Typical Morphology;
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-2238-8
Electronic_ISBN :
978-1-4244-2239-5
DOI :
10.1109/ICWAPR.2008.4635769
