Relationship between Texture Features and Mineralogy Phases in Iron Ore Sinter Based on Gray-level Co-occurrence Matrix

Abstract

An intelligent recognition and quantification system for photomicrographs of iron ore sinter is useful and convenient; however, it is impossible to develop a successful intelligent system without adequate and accurate texture features of mineralogical phases. The gray-level co-occurrence matrix (GLCM) has been proved as an effective method for extracting the texture features in other fields, therefore, this work examines texture features for the main mineralogical phases, such as magnetite and calcium ferrite, based on GLCM. These features include contrast, energy, entropy, and inverse difference moment. Specifically, this study addresses the effect on these features of several parameters, including the gray levels, the size of the image window, and the distance between the co-occurrences, and the offset angle. When the gray levels equal 125, the size of image window equals 100, and the distance of the co-occurrence equals 15, the average values of the four offset angles indicated that the features of each phase were relatively constant. Space distance characterizes the differences between a known image and an image to be analyzed; it determines the texture pattern of the image and is calculated using the Canberra space distance equation. Further calculation validates the results, indicating that intelligent recognition and quantification systems can be developed based on this method.KEY WORDS: gray level co-occurrence matrix; image recognition; texture feature; mineralogical phase; iron ore sinter. 709© 2009 ISIJ system can also determine size distribution using the structural elements of various sizes and shapes. For automatic recognition, both determine the mineralogy phase based on the reflective powers, which can be determined from the brightness of the pixel in the image. The brightness of the image of the polished sinter section is determined by many factors, including the quality of the polished section, the technical parameters of the microscope, the working conditions of the CCD camera connected to the microscope, etc. If any one of these parameters changes, the brightness of the image also changes. For example, brightness increases as the intensity of the input light on the polished sinter section increases. The reliability of the reflective powers of the mineralogical phases in commercial sinter is, therefore, important. Industrial parameters such as sintering temperature or cooling speed affect the mineralogy phases, making them indistinguishable by brightness alone. The present authors have studied the relationship between the features of mineralogical phases and gray level histogram.5) Their previous work has shown that the mineralogy phases can be determined not only the brightness of the image, but also by their textures. The texture features are influenced less by operational parameters. Other researchers have successfully used the gray-level co-occurrence matrix (GLCM) technique 6) to determine the texture of rock 7) or of the earth's gravity field.8) This work uses the same technique to study...

Real-Time Texture Analysis for Identifying Optimum Microbubble Concentration in 2-D Ultrasonic Particle Image Velocimetry

“…Whereas, if it is too small, it may not sufficiently extract the texture feature. Lv et al 2009 suggested that contrast, energy and homogeneity change less when an image window was over 75 pixels. Therefore, a window size of 100 × 100 was used.…”

Comparison of Iron Ore Sinter Mineralogy Quantification

“…Nevertheless, the image processing techniques based on the evaluation of the shades of grey are also limited to dividing the minerals in examined sinter samples just into main groups, i.e. hematite, magnetite, Ca-ferrites, silicates and pores [15,[18][19][20]. This means that the distinction between calcium ferrite types is also not involved.…”

Silico-ferrite of Calcium and Aluminum Characterization by Crystal Morphology in Iron Ore Sinter Microstructure

“…Most of researches of phase composition realized today is still based on image analysis, where only shades of grey and shape of crystal can observed. 10,11) Many classify calcium ferrites according to that.…”