**Eugene Donskoi \* and Andrei Poliakov**

CSIRO Mineral Resources, PO Box 883, Kenmore, QLD 4069, Australia; andrei.poliakov@csiro.au **\*** Correspondence: Eugene.Donskoi@csiro.au; Tel.: +61-422-464-438

Received: 27 July 2020; Accepted: 6 September 2020; Published: 8 September 2020

**Featured Application: The algorithms described in the article can be used in any applications of image processing for recognition**/**segmentation of phases**/**morphologies, particularly in mineralogical image analysis. Their specific application field is ironmaking and corresponding optical image analysis of iron ore, sinter, and coke.**

**Abstract:** Optical image analysis is commonly used to characterize different feedstock material for ironmaking, such as iron ore, iron ore sinter, coal and coke. Information is often needed for phases which have the same reflectivity and chemical composition, but different morphology. Such information is usually obtained by manual point counting, which is quite expensive and may not provide consistent results between different petrologists. To perform accurate segmentation of such phases using automated optical image analysis, the software must be able to identify specific textures. CSIRO's Carbon Steel Futures group has developed an optical image analysis software package called Mineral4/Recognition4, which incorporates a dedicated textural identification module allowing segmentation of such phases. The article discusses the problems associated with segmentation of similar phases in different ironmaking feedstock material using automated optical image analysis and demonstrates successful algorithms for textural identification. The examples cover segmentation of three different coke phases: two types of Inert Maceral Derived Components (IMDC), non-reacted and partially reacted, and Reacted Maceral Derived Components (RMDC); primary and secondary hematite in iron ore sinter; and minerals difficult to distinguish with traditional thresholding in iron ore.

**Keywords:** image analysis; texture; structure; optical; coke; iron ore; sinter; image processing; segmentation; identification
