臺灣博碩士論文加值系統

近年來，機器人領域相關的應用迅速的蓬勃發展，像是 Sony 公司的QRIO Robot 與Honda 公司的ASIMO Robot。相信在不久的未來，機器人將會融入人類的生活，為了我們帶來更多便利的生活。而如何讓機器人能認識我們日常生活中的物品，是一個相當值得研究且有趣的議題。例如想請一位管家機器人拿餐桌上的蘋果給我吃，那麼機器人必須要在非常短的時間內，從餐桌上找到蘋果這件物品才有可能辦到。基於這樣的概念，本研究提出一套運用色彩及紋理兩種特徵，並結合支持向量機作為即時分類物品種類之辨識系統，實驗採用水果作為辨識的目標物。本研究將辨識流程分為四大部份，分別為前處理、影像分割、特徵擷取及類別辨識。本系統平均辨識一張640×480(pixels)大小的影像，運算時間約為0.401秒。首先將從網路攝影機取得之影像，利用對比增強的技術來增強水果與實驗環境背景之差異性，以便後續做分割的動作。接著逐一取得以形態學分割後的單一水果區塊，將其色彩空間由RGB 轉換至YCbCr，取CbCr 值作為顏色的特徵，為了區別同色系的水果，再加入以Y 值計算出的紋理特徵，形成一串描述單一水果之特徵向量。最後再將此特徵向量經由支持向量機訓練出該系統之決策函數。實驗結果證明本系統在辨識水果種類上辨識率達95.33%。

In recent years, the field of robot applications such as Sony’s Dancing Robot QRIO and Honda’s ASIMO Robot is rapid developed. In the near future, robots will be integrated into human’s life. In order to bring us more convenient. How to make the robot to recognize the objects is a very interesting issue. For example, the housekeeper robot is requested to take the apple which is on the table and then the robot must find the apple out from the table in a very short time. Based on this idea, this study proposed a method which were applying color and texture features and using Support Vector Machine(SVM) to classify the objects in real-time. Experiments are fruit as the target. The whole procedure was divided into four steps, which are preprocessing, image segmentation, feature extraction, and matching. The average recognition speed of the proposed system to recognize all fruit in an image size of 640×480(pixels) is about 0.401 seconds.First, the observed image is captured by webcam and using enhancement technology to enhance the difference between fruit and the background of experimental environment. Then to segment image via morphology becomes to a single block of each fruit one by one. Translate color space from RGB to YCbCr and analyze texture and color feature. Final step is to find out the decision function with feature vector by SVM. The overall accuracy rate of the proposed system is about 95.33%.

摘要................................................................................................................................ iv
英文摘要.......................................................................................................................... v
誌謝................................................................................................................................ vi
目次...............................................................................................................................vii
表目錄.............................................................................................................................. x
圖目錄............................................................................................................................. xi
第一章 緒論.............................................................................................................. 1
1.1 研究動機...................................................................................................... 1
1.2 研究背景...................................................................................................... 3
1.3 研究目標與條件限制.................................................................................. 4
1.4 章節架構...................................................................................................... 6
第二章 系統架構...................................................................................................... 7
2.1 系統環境...................................................................................................... 7
2.2 系統流程...................................................................................................... 7
第三章 影像前處理.................................................................................................. 9
3.1 前處理流程................................................................................................ 11
3.1.1 影像分割........................................................................................ 12
3.1.2 對比增強........................................................................................ 15
3.1.3 灰階影像與二值影像.................................................................... 17
3.1.4 形態學............................................................................................ 19
3.2 連通元件標記............................................................................................ 23
3.3 物品定位.................................................................................................... 25
第四章 特徵擷取.................................................................................................... 33
4.1 色彩空間.................................................................................................... 33
4.1.1 RGB色彩空間................................................................................ 33
4.1.2 HSI色彩空間.................................................................................. 34
4.1.3 YCbCr色彩空間............................................................................. 35
4.1.4 色彩特徵........................................................................................ 36
4.2 紋理分析.................................................................................................... 37
4.2.1 LBP................................................................................................. 37
4.2.2 Rotation Invariant LBP................................................................... 38
4.2.3 紋理特徵........................................................................................ 42
第五章 分類器........................................................................................................ 43
5.1 機率式分類器............................................................................................ 43
5.1.1 貝式分類器.................................................................................... 44
5.1.2 KNN分類器.................................................................................... 45
5.2 支持向量機................................................................................................ 46
5.2.1 超平面............................................................................................ 46
5.2.2 核心函數........................................................................................ 49
第六章 研究成果.................................................................................................... 52
6.1 實驗環境.................................................................................................... 52
6.2 實驗結果.................................................................................................... 53
6.2.1 實驗一(正常環境).......................................................................... 54
6.2.2 實驗二(色彩特徵比較).................................................................. 56
6.2.3 實驗三(外加光線干擾環境).......................................................... 57
6.2.4 實驗四(物品重疊擺放).................................................................. 58
6.2.5 實驗五(複雜背景環境).................................................................. 60
6.3 結論與未來展望........................................................................................ 61
6.3.1 結論................................................................................................ 61
6.3.2 未來展望........................................................................................ 61
參考文獻 ...................................................................................................................... 63
附錄 .............................................................................................................................. 66
A 水果影像資料庫(蘋果) ............................................................................. 66
B 水果影像資料庫(芭樂) ............................................................................. 67
C 水果影像資料庫(香蕉) ............................................................................. 68
D 水果影像資料庫(棗子)............................................................................. 69
E 水果影像資料庫(奇異果) ......................................................................... 70
F 水果影像資料庫(蓮霧).............................................................................. 71
G 水果影像資料庫(檸檬)............................................................................. 72
H 水果影像資料庫(柳丁)............................................................................. 73
I 水果影像資料庫(柿子) .............................................................................. 75
J 水果影像資料庫(橘子) .............................................................................. 76
作者簡介 ...................................................................................................................... 78

1.http://www.sony.net/SonyInfo/News/Press_Archive/200312/03-060E/
2.http://world.honda.com/ASIMO/
3.Bulanon, D.M. , Kataoka, T., Ukamoto, H. , Hata, S. “Development of a Real-time Machine Vision System for the Apple Harvesting Robot,” SICE Annual Conference in Sapporo, August 4-6,2004 Hokkaido Institute of Technology, Japan.
4.R. Bolle. “Veggie Vision: A Produce Recognition System,” IBM TJ Watson Research Center, 1996.
5.T. Ojala, M. Pietikäinen and T. Mäenpää, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, pp. 971-987, 2002.
6.Nello Cristianini and John Shawe-Taylor. ”An Introduction to Support Vector Machines and other kernel-based learning methods,” Cambridge University Press, 2000.
7.C.-C. Chang and C.-J. Lin. “LIBSVM: a library for support vector machines,” 2001.
8.Jean Serra “Image Analysis and Mathematical Morphology, Volume 2: Theoretical Advances, “ 1998.
9.L.G. Roberts, “Machine perception of 3-D solids. In: Optical and Electro-optical Information Processing,” MIT Press (1965), pp. 159–197.
10.Y. Deng and B. S. “Manjunath. Unsupervised segmentation of color-texture regions in images and video,” IEEE Trans. Pattern Anal. Mach. Intell., 23(8):800–810, 2001.
11.J. Shi, and J. Malik, “Normalized Cuts and Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, Issue 8, pp. 888-905, August 2000.
12.C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Color- and Texture-based Image Segmentation Using the Expectation-Maximization Algorithm and Its Application to Content-Based Image Retrieval,” Int. Conference Computer Vision, Bombay, India, Jan 1998.
13.C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying,” IEEE Transaction on Pattern Analysis and Machine Intelligence, 24(8), 1026-1038, August 2002.
14.洪智毅 “交疊錢幣辨識之研究,” 南台科技大學資訊工程系碩士論文，2007.
15.Georges Matheron and Jean Serra “History of Mathematical Morphology, “ 1968.
16.T. Uchiyama, M. A. Arbib, “Color Image Segmentation Using Competitive Learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 12, pp. 1197-1206, Dec. 1994.
17.R. C. Gonzalez and R. E. Woods, “Digital Image Processing, 2nd Ed.,” Prentice Hall, New Jersey, 2002.
18.Charles Poynton, “Digital Video and HDTV,” Chapter 24, pp. 291-292, Morgan Kaufman, 2003.
19.M. Varma and A. Zisserman. “A Statistical Approach to Texture Classification from Single Images,” International Journal of Computer Vision, 62(1):61–81, 2005.
20.Ojala, T., Pietikäinen, M., Harwood, D.: “A Comparative Study of Texture Measures with Classification Based on Feature Distributions,” Pattern Recognition 29 51-59. 1996.
21.Pietikäinen, M., Ojala, T., Xu Z.: “Rotation-Invariant Texture Classification Using Feature Distributions,” Pattern Recognition 33 43-52. 2000.
22.Ojala, T., Pietikäinen, M., Harwood, D.: “Performance evaluation of texture measures with classification based on Kullback discrimination of distributions,” Proc. 12th international Conference on Pattern Recognition (ICPR 1994), Jerusalem, Israel vol. I, 582-585, 1994.
23.Martin A. Hunt, et al., ”Paradigm for selecting the optimum classifier in semiconductor automatic defect classification applications,” Proceedings of SPIE vol. 3998, 2000.
24.Bayes, Thomas “An Essay towards solving a Problem in the Doctrine of Chances.” Philosophical Transactions of the Royal Society of London 53: 370–418. 1763.
25.Domingos, Pedro & Michael Pazzani “On the optimality of the simple Bayesian classifier under zero-one loss”. Machine Learning, 29:103–¬137. 1997.
26.陳耀俊,呂炎州 “自動瑕疵分類在LCD瑕疵檢測的應用,” 機械工業雜誌第277期 pp.90-98，2006.
27.Ma Jian-bin, Li Ying, Teng Gui-fa, Wang Fang, Zhao Yang, “The comparison studies on the algorithm of KNN and SVM for Chinese text classification,” Journal of Agricultural University of HeBei, vol.31(3), 2008
28.Vapnik, V. and Lerner, A., “Pattern Recognition using Generalized Portrait Method,” Automation and Remote Control , vol.24, 1963.
29.Vapnik, V., “The Nature of Statistical Learning Theory,” Springer, N.Y, 1995.
30.Vapnik, V., “Statistical Learning Theory,” Wiley , 1998.
31.Pontil, M. and Verri, A., “Object recognition with support vector machines,” IEEE Trans. On PAMI , 20 , pp.637-646, 1998.
32.Brown, M. , Grundy, W. , Lin, D. , Cristianini, N. , Sugnet, C. , Furey, T. , Ares, M. , and Haussler, D. “Knowledge-base analysis of microarray gene expression data using support vector machines,” Technical report, University of California in Santa Cruz , 1999.
33.Joachims, T. , “Text categorization with support vector machines,” In Proceedings of European Conference on Machine Learning (ECML) ,1998.
34.B.Scholkopt and A.J.Smola, “Learning with Kernels,” Cambridge, Mass. MIT Press, 2002.
35.U. KreBel. “Pairwise Classification and Support Vector Machines. Advances in Kernel Methods-Support Vector Learning,” pp.254-268, Cambridge, MA, 1999, MIT Press.
36.Z. Aghbari and A. Makinouchi, “Semantic Approach to Image Database Classification and Retrieval,” NII Journal, no. 7, September, 2003.
37.C.J.C.Burges, ”A Tutorial on Support Vector Machines for Pattern Recognition,” Knowledge Discovery and Data Mining, vol.2, no.2, pp,121-167, 1998.N.Cristianini and J.Shawe-Taylor, “An Introduction to Support Vector Machines,” Cambridge, U.K.Cambridge Univ.Press, 2000.
38.http://www.csie.ntu.edu.tw/~cjlin/libsvm/
39.Hsu, Chih-Wei, Chang, Chih-Chung, and Lin, Chih-Jen , “A Practical Guide to Support Vector Classification,” 2003.