Automatic Grain Size Determination in Microstructures Using Computer Vision Algorithm Based on Support Vector Machine (SVM)

The properties of materials are identified as the results of its microstructures characteristics. Consequently the task of analysis of microstructure is very important in engineering. There are several methods such as the visual inspection and the semi-automatic inspection by image analysis. Visual inspection by an operator is subject to human error and can take important time. The semiautomatic method using specific algorithm and technique improves performance of the work, however still needs specific knowledge concerning image filters and image analysis technique. This research’s objectives are to present automatic image analysis algorithm to measure grains in microstructure images.