Classification of
Classification
of Copper Alloys Microstructure using Image Processingand Neural Network
Ossama B. Abouelatta
Production Engineering
and Mechanical Design Department, Faculty of Engineering, Mansoura University,
35516 Mansoura, Egypt
Abstract: The
most important aspect of any engineering material is its structure. The methods
used to accurately determine the material microstructures is a very
time-consuming process, causes operator fatigue, and it is prone to human
errors and inconsistency. There are two computational approaches, a feature
features and a neural network algorithm, are used separately for classifying
and detection of surface textures in the field of remote sensing, science,
medicine, journalism, advertising, design, education and entertainment. In this
paper, a combination of the two approaches has been utilized to classify and to
detect copper and copper alloys microstructure using image process, texture
features and neural network. The overall average discrimination rate results
from the combined approaches are about 97.6%. This paper offers a reliable
basis for the classification and characterization of microscopic images by
image processing and neural network.
[Ossama B. Abouelatta. Classification of
Copper Alloys Microstructure using Image Processing and Neural Network. J
Am Sci 2013;9(6):213-223]. (ISSN: 1545-1003). http://www.jofamericanscience.org.
25
Key words: Classification, Copper alloys, Microstructure, Image
processing, Texture feature, Neural network