請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/64148完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳柏翰(Po-Han Chen) | |
| dc.contributor.author | Chia-Yu Chien | en |
| dc.contributor.author | 簡嘉佑 | zh_TW |
| dc.date.accessioned | 2021-06-16T17:32:09Z | - |
| dc.date.available | 2017-08-27 | |
| dc.date.copyright | 2012-08-27 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-08-15 | |
| dc.identifier.citation | 中文部分：
1. 交通公路總局 (DGH, MOTC) (2011)。《交通部公路總局鋼橋選色作業說明及程序》。http://www.thb.gov.tw/TM/Default.aspx (2012/07/27 瀏覽)。 English: 1. AbdelRazig, Y. A. (1999). Construction quality assessment: A hybrid decision support model using image processing and neural learning for intelligent defects recognition, Ph.D. Dissertation, Purdue University. 2. Chang, Y.-C. (2000). Statistical models for MRF image restoration and segmentation, Ph.D. Dissertation, Purdue University. 3. Chen, P.-H. (2001). Digital image recognition methods for infrastructure surface coating assessment, Ph.D. Dissertation, Purdue University. 4. Chen, P.–H., and Chang, L.–M. (2003). “Artificial intelligence application to bridge painting assessment,” Automation in Construction, 12(4), 431-445. 5. Chen, P.-H., Chang, Y.-C., Chang, L.-M., Doerschuk, P. C. (2002). “Application of multi resolution pattern classification to steel bridge coating assessment,” Journal of Computing in Civil Engineering, 16(4), 244-251. 6. Chen, P.-H., Yang, Y.-C., and Chang, L.-M. (2009). “Automated bridge coating defect recognition using adaptive ellipse approach,” Automation in Construction, 18(5), 632-643. 7. Chen, P.-H., Yang, Y.-C., and Chang, L.-M. (2010a). “Box-and-Ellipse-Based ANFIS for bridge coating assessment,” Journal of Computing in Civil Engineering, 24(5), 389-398. 8. Chen, P.-H., Yang, Y.-C., and Chang, L.-M. (2010b). “Illumination adjustment for bridge coating images using BEMD-Morphology Approach (BMA),” Automation in Construction, 19(4), 475-484. 9. Chen, P.-H., and Chang, L.-M. (2002). “Intelligent steel bridge coating assessment using neuro-fuzzy recognition approach,” Computer-Aided Civil and Infrastructure Engineering, 17(5), 307-319. 10. Chen, P.-H., Shen, H.-K., Lei, C.-Y., Chang, L.-M. (2012). “Support-vector-machine-based method for automated steel bridge rust assessment,” Automation in Construction, 23, 9-19. 11. Cristianini, N., and Shawe-Talor, J. (2000). An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge: Cambridge University Press. 12. Fan, C.-N., and Zhang, F.-Y. (2011). “Homomorphic filtering based illumination normalization method for face recognition,” Pattern Recognition Letters, 32(10), 1468-1479. 13. Gonzalez, R. C., and Woods, R. E. (2008). Digital Image Processing (3rd ed.). New Jersey: Prentice Hall. 14. Gonzalez, R. C., Woods, R. E., and Eddins, S. L. (2009). Digital Image Processing Using MATLAB (2nd ed.). Knoxville: Gatesmark Publishing. 15. Hunt, R.W.G. (1991). Measuring Colour (2nd ed.). Ellis Horwood. 16. Lee, S. (2005). Digital color image processing system for civil infrastructure health assessment and monitoring: Steel bridge coating case, Ph.D. Dissertation, Purdue University. 17. Lee, S., Chang, L.-M., and Chen, P.-H. (2005). “Performance comparison of bridge coating defect recognition methods,” Corrosion, 61(1), 12-20. 18. Lee, S., Chang, L.-M., and Skibniewski, M. (2006). “Automated recognition of surface defects using digital color image processing,” Automation in Construction, 15(4), 540-549. 19. Sao, A. K., and Yegnanarayana, B. (2010). “On the use of phase of the Fourier transform for face recognition under variations in illumination,” Signal, Image Video Process, 4(3), 353-358. 20. Su, C.-K., Lin, C.-Y., and Wang, M.-T. (2003). “Taiwanese construction sector in a growing ‘maturity’ economy, 1964-1999,” Construction Management and Economic, 21(7), 719-728. 21. Tseng, C.-H., Chen, M.-N., Wu, P.-H., Fung, C.-P., Doong, J.-L., Lin, J.-Y., Hsu, C.-C. (2011, April). “Advanced Research & Development on Detecting Component of Mechanical Arm for Bridge Inspection,” Taiwan: Institute of Transportation, Ministry of Transportation and Communications (IOT, MOTC). 22. Tserng, H. P., Lin, G.–F., Tsai, L. K., Chen, P.–C (2011). “An enforced support vector machine model for construction contractor default prediction,” Automation in Construction, 20(8), 1242-1249. 23. van Rijsbergen, C. J. (1979). Information Retrieval. London: Butterworth-Heinemann. 24. Yang, Y.-C. (2009). Smart Color Image Recognition for Steel Bridge Rust Inspection, Master Thesis, National Taiwan University, Taiwan. 25. Zhang, T., Fang, B., Yuan, Y., Tang, Y. Y., Shang, Z., Li, D., Lang, F. (2009). “Multiscale facial structure representation for face recognition under varying illumination,” Pattern Recognition, 42(2), 251-258. 26. Zhang, T. P., Tang, Y.Y., Fang, B., Shang, Z. W., Liu, X. Y., (2009). “Face recognition under varying illumination using gradientfaces.” IEEE Trans. Image Process. 18(11), 2599-2606. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/64148 | - |
| dc.description.abstract | 鋼橋維護管理之良窳，關係日後使用年限與安全。評估鋼橋表面塗漆品質，一般是以表面塗漆缺陷面積所占的比例表示；儘管在塗漆缺陷分級上有明確的規範，但依靠人工目視判斷塗漆缺陷面積，無法擺脫不客觀、難維持一致性以及曠日費時的缺點。因此，運用數位影像處理技術執行自動化評估塗漆缺陷，有其存在的價值和必要。
過去的相關研究大多著重於灰階影像處理，其辨識效果會大幅受非均勻照度問題的影響。雖然 Adaptive Ellipse Approach (AEA) 和 box-ellipse-based ANFIS (BE-ANFIS) 的辨識機制能處理受非均勻照度影響的彩色影像，卻無法用於以紅色或棕色為背景顏色的鏽蝕影像。 本研究以支持向量機 (Support Vector Machine) 做為學習的機器，將彩色影像轉換至18種不同的色彩空間後，分別輸入54種色彩元素的組合加以測試，尋找即使受非均勻照度影響仍能表現出鋼橋鏽蝕影像特徵的模式。 測試結果顯示，xyY色彩空間中的x元素與y元素的組合，在非均勻照度和隨機混入雜訊的兩種條件下，能使得支持向量機在鏽蝕辨識上有顯著的效果；此一組合對於正常影像亦有優秀表現。 最後，本研究將彩色影像以xyY色彩空間中的x與y元素的組合搭配支持向量機，作為鋼橋進行自動化評估鏽蝕面積的工具，並利用傅立葉轉換與同態濾波器去調整非均勻照度影像的亮度和對比度，進一步提高鏽蝕辨識的精確率。 | zh_TW |
| dc.description.abstract | In many industries and fields of applications, image pattern recognition has been widely adopted over the last two decades. However, there are few robust methods for infrastructure maintenance to overcome non-uniform illumination problems in steel bridge rust assessment. Although the Adaptive Ellipse Approach (AEA) and the box-and-ellipse-based ANFIS (BE-ANFIS) methods have been proposed to deal with non-uniform illumination problems, they cannot work well on the images in red or brown background colors. The purpose of this research is to resolve non-uniform illumination problems for rust images in red or brown background colors.
In order to find out the best color configurations for uniformly illuminated, non-uniformly illuminated, and random pepper-like noise rust image segmentation, an investigation of 18 color spaces is done. Among the 18 color spaces, the x and the y color configurations of the xyY color space have substantial performance over the simulation test. Therefore, the x and the y color configurations are used with Fourier transform, homomorphic filter and support vector machine (SVM) to improve the recognition accuracy. In an advanced SVM, Fourier transform with a homomorphic filter is used to adjust the lightness and contrast of non-illumination images for building up the training set, which is used to train SVM. The results show that the homomorphic filter can quickly adjust non-uniformly illuminated images of the training set for making steel bridge rust recognition more reliable than processing without illumination adjustment. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T17:32:09Z (GMT). No. of bitstreams: 1 ntu-101-R99521711-1.pdf: 1323799 bytes, checksum: beb94005c3283a4d81e1d74ad72f2a04 (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | TABLE OF CONTENTS
ACKNOWLEDGMENTS ii 摘要 iii ABSTRACT iv TABLE OF CONTENTS vi LIST OF FIGURES ix LIST OF TABLES x CHAPTER 1 INTRODUCTION 11 1.1 Background 11 1.2 Problem Statement 12 1.3 Research Objectives 12 1.4 Research Methodology 14 1.5 Thesis Organization 15 CHAPTER 2 LITERATURE REVIEW 16 2.1 Steel Bridge Surface Inspection 16 2.1.1 AbdelRazig (1999) 16 2.1.2 Chen and Chang (2002) 16 2.1.3 Lee (2005) 17 2.1.4 Yang (2009) 17 2.1.5 Chen et al. (2012) 18 2.2 Color Spaces 18 2.2.1 The sRGB Color Space 20 2.2.2 The CMY Color Space 20 2.2.3 The XYZ and CIE RGB Color Spaces 21 2.2.4 The xyY Color Space 22 2.2.5 The NTSC RGB, YIQ, YUV, and YCbCr Color Spaces 23 2.2.6 The I1I2I3 and LSLM Color Spaces 24 2.2.7 The L*a*b*, L*u*v*, and W*U*V* Color Spaces 24 2.2.8 The HIS and HSV Color Spaces 26 2.2.9 The LCH and LSH Color Spaces 28 2.3 Support Vector Machine (SVM) 29 2.3.1 The Primal Problem of SVM 29 2.3.2 Non-Linear Classification 32 2.4 Fourier Transform 33 CHAPTER 3 COMPARISON OF COLOR CONFIGURATIONS USING SUPPORT VECTOR MACHINE (SVM) 35 3.1 Artificial Rust Image 35 3.1.1 Non-uniformly Illuminated Images 37 3.1.2 Random Pepper-like Noise Images 37 3.2 Transformation of 18 Color Spaces 38 3.3 Startup of SVM 40 3.4 Evaluation of Performance 42 3.5 Cross Validation 53 3.6 Summary 53 CHAPTER 4 FOURIER TRANSFORM WITH HOMOMORPHIC FILTER 54 4.1 The Features of the x Color Configuration’s and the y Color Configuration’s Response to Light 54 4.2 Homomorphic Filter 58 4.3 Illumination Adjustment 60 4.4 Model Validation 68 4.5 Summary 69 CHAPTER 5 CONCLUSIONS AND RECOMMENDATIONS 70 REREFENCES 72 中文部分： 72 English: 72 | |
| dc.language.iso | en | |
| dc.subject | 塗漆缺陷辨識 | zh_TW |
| dc.subject | 非均勻照度影像 | zh_TW |
| dc.subject | 同態濾波器 | zh_TW |
| dc.subject | 傅立葉轉換 | zh_TW |
| dc.subject | 支持向量機 | zh_TW |
| dc.subject | non-uniform illumination | en |
| dc.subject | Fourier transform | en |
| dc.subject | Homomorphic filter | en |
| dc.subject | Coating defect recognition | en |
| dc.subject | support vector machine | en |
| dc.title | 鋼橋鏽蝕評估─以傅立葉轉換結合支持向量機增進照度不均勻影像辨識效果之研究 | zh_TW |
| dc.title | Combining Fourier Transform and Support Vector Machine (SVM) to Enhance the Recognition Accuracy of Non-uniform Illuminated Steel Bridge Rust Images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 張陸滿(Luh-Maan Chang),楊亦東(I-Tung Yang),陳介豪(Jieh-Haur Chen) | |
| dc.subject.keyword | 塗漆缺陷辨識,支持向量機,傅立葉轉換,同態濾波器,非均勻照度影像, | zh_TW |
| dc.subject.keyword | Coating defect recognition,support vector machine,Fourier transform,Homomorphic filter,non-uniform illumination, | en |
| dc.relation.page | 75 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2012-08-15 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-101-1.pdf 未授權公開取用 | 1.29 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。