[논문]슈퍼픽셀 DBSCAN 군집 알고리즘을 이용한 용융아연도금 강판의 부식이미지 분석

김범수; 김연원; 이경황; 양정현

doi:10.5695/jsse.2022.55.3.164

슈퍼픽셀 DBSCAN 군집 알고리즘을 이용한 용융아연도금 강판의 부식이미지 분석
Corrosion image analysis on galvanized steel by using superpixel DBSCAN clustering algorithm 원문보기

한국표면공학회지 = Journal of the Korean institute of surface engineering, v.55 no.3, 2022년, pp.164 - 172

김범수 (경상국립대학교 기계시스템공학과) , 김연원 (목포해양대학교 메카트로닉스공학부) , 이경황 (포스코 철강솔루션연구소) , 양정현 (경상국립대학교 기계시스템공학과)

Abstract ▼ AI-Helper

Hot-dip galvanized steel(GI) is widely used throughout the industry as a corrosion resistance material. Corrosion of steel is a common phenomenon that results in the gradual degradation under various environmental conditions. Corrosion monitoring is to track the degradation progress for a long time. Corrosion on steel plate appears as discoloration and any irregularities on the surface. This study developed a quantitative evaluation method of the rust formed on GI steel plate using a superpixel-based DBSCAN clustering method and k-means clustering from the corroded area in a given image. The superpixel-based DBSCAN clustering method decrease computational costs, reaching automatic segmentation. The image color of the rusty surface was analyzed quantitatively based on HSV(Hue, Saturation, Value) color space. In addition, two segmentation methods are compared for the particular spatial region using their histograms.

주제어

표/그림 (9)

그림 Fig. 1. Illustration of the DBSCAN cluster model[16].
그림 Fig. 2. Flowchart for rust analysis using the k-means and the superpixel DBSCAN methods.
그림 Fig. 3. GI 1 year exposure. (a) ROI is marked by a green rectangle, where offset is 5 pixels, (b) Segmented image using the grab-cut.
그림 Fig. 4. (a) The largest inscribed rectangle, (b) Cropped image.
그림 Fig. 5. GI 1 year exposure, k-means method. The left column shows the clustering and the right column displays their corresponding histograms.
그림 Fig. 6. GI, 1 year exposure. (a) superpixel with k = 1000, (b) superpixel based DBSCAN with =5, MinPts = 1
그림 Fig. 7. The figures in the first column correspond to (a) 2, (b) 3, (c) 5 and (d) 6 years exposure. The figures in the second column are the result of superpixel based DBSCAN with k = 1000, ϵ=5, MinPts. = 1.
표 Table 1. The numbers of regions for each exposure material and top and the upper and lower areas(%, percentage).
그림 Fig. 8. (a) The nonblack part is the largest region of the Fig. 6. and (b) histogram.

참고문헌 (16)

M. H. Hong, D. G. Kang, D. J. Paik, H. S. Hwang, S. H. Park, Effect of added magneisum on the coating properties of galvanized steel sheets, Korean J. Met. Mater., 54 (2016) 723-731.

상세보기
S. J. Kwon, S. M. Lee, M. H. Lee, S. S. Park, Study on corrosion and structural performancein hot-dip galvanizing steel, J. Korea Concr. Inst., 24 (2012) 613-621.
B. S. Kim, Y. W. Kim, J. H. Yang, Detection of corrosion on steel plate by using image segmentation method, J. Korean Inst. Surf. Eng., 54 (2021) 84-89.
V. Bondada, D. K. Pratihar, C. S. Kumar, Detection and quantitative assessment of corrosion on pipelines through image analysis, Procedia Comput. Sci., 133 (2018) 804-811.
K. W. Liao, Y. T. Lee, Detection of rust defects on steel bridge coatings via digital image recognition, Autom. Constr., 71 (2016) 294-306.

상세보기
B. S. Kim, J. S. Kwon, S. W. Choi, J. P. Noh, K. H. Lee, J. H. Yang, Corrosion image monitoring of steel plate by using k-means clustering, J. Korean Inst. Surf. Eng., 54 (2021) 278-284.
C. Rother, V. Kolmogorov, A. Blake, "GrabCut":interactive foreground extraction using iterated graph cuts, ACM Trans. Graph., 23 (2004) 309-314.

상세보기
K. P. Sinaga, M. S. Yang, Unsupervised k-means clustering algorithm, IEEE Access, 8 (2020) 80716-80727.

상세보기
D. M. Saputra, D. Saputra, L.D. Oswari, Effect of distance metrics in determining k-value in k-means clustering using elbow and silhouette method, Adv. Intell. Syst. Res., 172 (2019) 341-346.
R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Susstrunk, SLIC superpixels compared to state-of-the-art superpixel methods, IEEE Trans. Pattern Anal. Mach. Intell., 34, (2012) 2274-2282.

상세보기
M. Marzeh, M. Tahmasbi, N. Mirehi, Algorithm for finding the largest inscribed rectangle in polygon, J. Algorithm. Comput. Technol., 51 (2019) 29-41.
M. Ahmed, R. Seraj, S. M. S. Islam, The k-means algorithm: a comprehensive survey and performance evaluation, Electronics, 9 (2020) 1295.
R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, S. Susstrunk, SLIC superpixels compared to state-of-the-art superpixel methods, IEEE Trans. Pattern Anal. Mach. Intell., 34 (2012) 2274-2282.

상세보기
Y. Zhang, Q. Guo, Y. Zhang, C. Zhang, Fast and robust superpixel generation method, IET Image Process., 14 (2020) 4543-4553.
M. Ester, H. P. Kriegel, J. Sander, X. Xu, A density-based algorithm for discovering clusters in large spatial databases with noise, Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD 96). AAAI Press. (1996) 226-231.
E. Schubert, J. Sander, M. Ester, H. P. Kriegel, X. Xu, DBSCAN revisited, revisited: why and how you should (still) use DBSCAN, ACM Trans. Database Syst. (TODS), 42 (2017) 1-21.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증