Quantitative determination of sinter structure by image analysis.

Shibuya, Teiji; Yanaka, Hideomi; Takemoto, Katsuhiro; Yamaoka, Yojiro; Yamada, Takeo; Uesugi, Mitsuaki

doi:10.2355/isijinternational1966.25.257

Cited by 9 publications

(23 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4. In the same manner, images (1,3), (1,4), (2,3), and (2, 4) are plotted in subfigure B, images (3, 1), (3,2), (4,1), and (4, 2) in subfigure C, and images (3,3), (3,4), (4,3), and (4, 4) in subfigure D. These subfigures demonstrate that the contrast increases with an increase gray level. The rate at which contrast increases is different…”

Section: Features Dependent On Gray Levelsmentioning

confidence: 96%

“…The average value of contrast for the four images in subfigure C is also the greatest among the four subfigures. Image (1,4) has the lowest contrast, and subfigure B also has the lowest average contrast. Subfigures A and C have greater contrast than subfigures B and D. High contrast in texture means that the texture is clear and the texture rills are deep.…”

Section: Features Dependent On Gray Levelsmentioning

confidence: 99%

“…Images showing pores or slag phases, however, do not always show the greatest contrast. For example, image (1,4) has the lowest contrast because the contrast is determined by both the area and the distribution of each phase. Generally, with more phases of varying gray levels, the texture shows greater contrast.…”

Section: Features Dependent On Gray Levelsmentioning

confidence: 99%

“…These morphological operations also permit signal enhancement and pattern recognition. Later, Shibuya and Yanaka 4) developed a system to quantify sinter structure using image analysis. According to this method, a TV camera and computer are used simultaneously to observe the sinter structure both macroscopically and microscopically.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Bai

Qiu

et al. 2009

ISIJ Int.

View full text Add to dashboard Cite

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...

show abstract

Section: Features Dependent On Gray Levelsmentioning

confidence: 96%

Section: Features Dependent On Gray Levelsmentioning

confidence: 99%

Section: Features Dependent On Gray Levelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Bai

Qiu

et al. 2009

ISIJ Int.

View full text Add to dashboard Cite

show abstract

“…The first, developed by IRSID and the School of Mines of Paris 1,2) is based on operational morphology. The second, developed by University of Tokyo and Nippon Corporation, 3) is based on pixel statistics. Jeulin determined the composition of the mineralogical phase by calculating the phase area after one pixel erosion.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Quantifying the Composition of Mineralogical Phase in Iron Ore Sinter

Bai

Qiu

et al. 2009

ISIJ Int.

View full text Add to dashboard Cite

This paper presents a new method to calculate accurately the composition of the mineralogical phase in iron ore sinter, especially the minor phases. This model is based on the combined model of gray-level distribution for a multi-phase system. The composition of the mineralogical phase is calculated by minimizing the difference between the theoretical gray-level histogram and the actual gray-level histogram of a micrograph of the iron ore sinter. A genetic algorithm and an improved genetic algorithm are introduced to solve this extreme value problem. Suitable parameters for the algorithm were determined by comparing the solutions for each of several cases. The example provided demonstrates that this model is valid, especially for the minor phases, and the solution is credible.

show abstract

Novel Recognition Method of Blast Furnace Dust Composition by Multifeature Analysis Based on Comprehensive Image-Processing Techniques

Guo

Bai

et al. 2014

JOM

View full text Add to dashboard Cite

Quantitative determination of sinter structure by image analysis.

Cited by 9 publications

References 0 publications

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

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

A Novel Method for Quantifying the Composition of Mineralogical Phase in Iron Ore Sinter

Novel Recognition Method of Blast Furnace Dust Composition by Multifeature Analysis Based on Comprehensive Image-Processing Techniques

Contact Info

Product

Resources

About