Automated Region of Interest Retrieval of Metallographic Images for Quality Scoring Estimation

The aim of the research is development and testing of new methods to assess the quality of digital metallographic images introduced in the quality of steel with high added value. In this paper, we will address the development of methods to assess the quality of metallographic samples, including slabs with the main emphasis on the quality of the image center. For this reason, we introduce an alternative method for automated region of interest retrieval. In the first step, the metallographic image is segmented using both spectral method and thresholding. Then, the extracted macrostructure of the metallographic image is automatically analyzed by statistical methods. Finally, automatically extracted region of interests are compared with results of human experts.