Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry
The aim of the research is development and testing of new methods to classify the quality of metallographic samples of steels with high added value (for example grades X70 according API). In this paper, we address the development of methods to classify the quality of slab samples images with the mai...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
VSB-Technical University of Ostrava
2012-01-01
|
| Series: | Advances in Electrical and Electronic Engineering |
| Subjects: | |
| Online Access: | http://advances.utc.sk/index.php/AEEE/article/view/564 |
| _version_ | 1797827038167433216 |
|---|---|
| author | Petr Kotas Pavel Praks Ladislav Valek Vesna Zejkovic Vit Vondrak |
| author_facet | Petr Kotas Pavel Praks Ladislav Valek Vesna Zejkovic Vit Vondrak |
| author_sort | Petr Kotas |
| collection | DOAJ |
| description | The aim of the research is development and testing of new methods to classify the quality of metallographic samples of steels with high added value (for example grades X70 according API). In this paper, we address the development of methods to classify the quality of slab samples images with the main emphasis on the quality of the image center called as segregation area. For this reason, we introduce an alternative method for automated retrieval of region of interest. 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. Practical experience with retrieval of non-homogeneous noised digital images in industrial environment is discussed as well. |
| first_indexed | 2024-04-09T12:41:53Z |
| format | Article |
| id | doaj.art-715af5ec63d9443cb5730518bd854e3c |
| institution | Directory Open Access Journal |
| issn | 1336-1376 1804-3119 |
| language | English |
| last_indexed | 2024-04-09T12:41:53Z |
| publishDate | 2012-01-01 |
| publisher | VSB-Technical University of Ostrava |
| record_format | Article |
| series | Advances in Electrical and Electronic Engineering |
| spelling | doaj.art-715af5ec63d9443cb5730518bd854e3c2023-05-14T20:50:08ZengVSB-Technical University of OstravaAdvances in Electrical and Electronic Engineering1336-13761804-31192012-01-01101505610.15598/aeee.v10i1.564518Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in IndustryPetr Kotas0Pavel Praks1Ladislav Valek2Vesna Zejkovic3Vit Vondrak4Department of Applied Mathematics (K 470) Faculty of Electrical Engineering and Computer Science (FEI) VSB-Technical University of Ostrava Tr. 17. listopadu 15 CZ 708 33 Ostrava-Poruba Czech RepublicDepartment of Applied Mathematics (K 470) Faculty of Electrical Engineering and Computer Science (FEI) VSB-Technical University of Ostrava Tr. 17. listopadu 15 CZ 708 33 Ostrava-Poruba Czech RepublicResearch – Production Technology, ArcelorMittal Ostrava plc, Ostrava, Czech RepublicNew York Institute of Technology, School of Engineering & Computing Sciences, Nanjing campus, ChinaDepartment of Applied Mathematics (K 470) Faculty of Electrical Engineering and Computer Science (FEI) VSB-Technical University of Ostrava Tr. 17. listopadu 15 CZ 708 33 Ostrava-Poruba Czech RepublicThe aim of the research is development and testing of new methods to classify the quality of metallographic samples of steels with high added value (for example grades X70 according API). In this paper, we address the development of methods to classify the quality of slab samples images with the main emphasis on the quality of the image center called as segregation area. For this reason, we introduce an alternative method for automated retrieval of region of interest. 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. Practical experience with retrieval of non-homogeneous noised digital images in industrial environment is discussed as well.http://advances.utc.sk/index.php/AEEE/article/view/564steel makingmaterials science and technologyquality controlexpert systemscontrol system human factorsinformation retrievalimage segmentationimage classificationmonitoringslab qualitysegregation area. |
| spellingShingle | Petr Kotas Pavel Praks Ladislav Valek Vesna Zejkovic Vit Vondrak Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry Advances in Electrical and Electronic Engineering steel making materials science and technology quality control expert systems control system human factors information retrieval image segmentation image classification monitoring slab quality segregation area. |
| title | Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry |
| title_full | Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry |
| title_fullStr | Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry |
| title_full_unstemmed | Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry |
| title_short | Automated Region of Interest Retrieval of Metallographic Images for Quality Classification in Industry |
| title_sort | automated region of interest retrieval of metallographic images for quality classification in industry |
| topic | steel making materials science and technology quality control expert systems control system human factors information retrieval image segmentation image classification monitoring slab quality segregation area. |
| url | http://advances.utc.sk/index.php/AEEE/article/view/564 |
| work_keys_str_mv | AT petrkotas automatedregionofinterestretrievalofmetallographicimagesforqualityclassificationinindustry AT pavelpraks automatedregionofinterestretrievalofmetallographicimagesforqualityclassificationinindustry AT ladislavvalek automatedregionofinterestretrievalofmetallographicimagesforqualityclassificationinindustry AT vesnazejkovic automatedregionofinterestretrievalofmetallographicimagesforqualityclassificationinindustry AT vitvondrak automatedregionofinterestretrievalofmetallographicimagesforqualityclassificationinindustry |