自然場景影像中的字元通常包含多種不同字體，而且因為拍照或是環境因素的影響，可能導致字元的變形與破碎，造成辨識上的困難。根據形狀內容特徵之特性，可以用來針對自然場景影像中不同字型之字元進行辨識，並且容許字元有些微的變形，因此本研究選用形狀內容作為特徵來對自然場景中的字元影像進行辨識。
傳統上利用形狀內容特徵進行辨識時需要進行多次迭代來作對應，每次迭代都是使用匈牙利演算法對特徵點進行最佳對應。由於匈牙利演算法需要耗費大量計算時間，時間複雜度為O(n3)。因此本研究保留特徵點的二維空間資訊，對於形狀內容特徵點給予不同的空間標記，做特徵點對應時僅需要對同一標記之特徵點進行一次性對應，而不需要透過迭代方式，藉此提升辨識速度與效率。
本研究針對ICDAR 2003所提供的自然場景字元影像資料集(數字0~9與大寫英文字母A~Z，共5100張)進行辨識，得到最佳化形狀內容特徵參數，並且討論不同空間資訊參數對辨識結果的影響。相較於傳統形狀內容特徵對應方法，本研究所提出之方法，在辨識率與處理速度都有大幅的提升。

Natural scene images contain a variety of characters in different type of fonts. The camera and environmental factors could cause the characters to be deformed and be broken. The deformable and broken images make it hard to be recognized. Based on the property of shape context, this method can be used for natural scene images of the characters in different type of fonts, even allowing a few deformed in characters. Therefore, this study selected the shape contexts as feature for character recognition in natural scene images.
Traditionally, the shape contexts method requires multiple iterations to make feature point matching and each iteration used the Hungarian algorithm to optimize for feature point correspondence. Because the Hungarian algorithm requires a lot of computing time, the time complexity is O (n3). Therefore, this study added the two-dimensional spatial information of feature points, each feature points given the label from different spatial information. Only the corresponding feature point with the same label would be matched, without the need for iteration. The proposed method will improve character recognition speed and efficiency.
This study used the data set of ICDAR 2003 (digits 0 through 9 and the uppercase letters A ~ Z, a total of 5100 images) for character recognition. Based on the experimental results, this study got the best shape context parameters and the effect of different parameters of spatial information could be discussed. Compared to the traditional shape contexts of the corresponding method, the proposed method’s recognition rate and the processing speed improved dramatically.

摘要 I
ABSTRACT II
誌謝 IV
目錄 V
圖目錄 VII
表目錄 X
第一章 簡介 1
第二章 文獻回顧 3
2.1 形狀內容-(Shape context) 7
2.2 矩量特徵 12
2.2.1 Hu矩量 12
2.2.2 Zernike矩量 13
2.3 區域特徵-Zoning 14
2.4 紋理特徵-賈伯特徵 15
2.5 小結 19
第三章 研究方法 21
3.1 前處理 23
3.1.1 輪廓擷取 24
3.1.2 取樣 27
3.2 形狀內容特徵擷取 27
3.3 成本矩陣計算 28
3.3.1 樣板影像 29
3.3.2 形狀特徵成本矩陣 30
3.3.3 梯度方向成本矩陣 30
3.4 空間排序對應 32
3.5 K最鄰近演算法(k-nearest neighbor, KNN) 34
第四章 結果與討論 36
4.1前處理分析 37
4.2 形狀內容參數分析 39
4.2.1 取樣點數分析 40
4.2.2 半徑參數設定 41
4.2.3 角度參數設定 43
4.2.4 成本矩陣參數調整 44
4.3 空間資訊參數分析 46
4.4 綜合討論 49
第五章 結論與未來展望 58
5.1 結論 58
5.2 未來展望 59
參考文獻 61

[1] O.D. Trier, A.K. Jain, and T. Taxt, “Feature extraction methods for character recognition—a survey,” Pattern Recognition, vol. 29, pp. 641–662, 1996.
[2] A. González, L.M. Bergasa, J.J. Yebes, and S. Bronte, “A character recognition method in natural scene images,” in Proceedings of International Conference on Pattern Recognition, pp. 621-624, 2012.
[3] T.E. Campos, B.R. Babu, and M. Varma, “Character recognition in natural images,” in Proceedings of the International Conference on Computer Vision Theory and Applications, 2009.
[4] S. Belongie and J. Malik, “Matching with Shape context,” in Proceeding of IEEE Workshop Content-Based Access of Image and Video Libraries, pp. 20–26, 2000.
[5] G. Mori, S. Belongie, and J. Malik, “Efficient Shape Matching
Using Shape context,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 11, pp. 1832-1837, 2005.
[6] Y. Wan, X. Xu, and L. Yao,” An efficient license plate character recognition algorithm based on Shape context,” SPIE Image Processing and Photonics for Agricultural Engineering, 2013.
[7] M. K. Hu, “Visual Pattern Recognition by Moment Invariants,” IRE Transactions on Information Theory, vol. IT-8, pp. 179–187, 1962.
[8] H. C. Andrews, “Multidimensional rotations in feature selection,” IEEE Transactions on. Comput, vol. 20, pp. 1045-1051, 1971.
[9] A. Khotanzad and Y.H. Hong, “Invariant image recognition by Zernike moments,” IEEE Transactions on Pattern Analysis and Machine Intelligence. vol. 12, no. 5, pp. 489-497, 1990.
[10] A. Khotanzad and Y.H. Hong, “Rotation invariant image recognition using features selected via a systematic method,” Pattern Recognition, vol. 23, no. 10, pp. 1089-1101, 1990.
[11] X. Wang, X. Ding and C. Liu, “Gabor filters-based feature extraction for character recognition,” Pattern Recognition, vol. 38 , pp. 369–379, 2005.
[12] H. Xu and Z. Ma, “A practical design of Gabor filter applied to license plate character recognition,” Proceedings of International Conference on Computer Science and Information Technology, pp. 398-401, 2008.
[13] K.P. Soman, R. Ramanathan, A.S. Nair, L. Thaneshwaran, S. Ponmathavan, and N. Valliappan, “Robust Feature Extraction Technique for Optical Character Recognition,” in Proceedings of International Conference on Advances in Computing Control and Telecommunication Technologies, pp. 573-575, 2009.
[14] Y. Hamamoto, S. Uchimura, M. Watanabe, T. Yasuda, Y. Mitani, and S.Tomita, “A Gabor filter-based method for recognizing handwritten numerals,” Pattern Recognition, vol. 31, no. 4, pp. 395-400, 1998.
[15] J.G. Daugman, “Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two dimensional visual cortical filters,” Journal of the Optical Society of America A, vol. 2, no. 7, pp. 1160-1169, 1985.
[16] S. Belongie, J. Malik, and J. Puzicha. “Shape matching and object recognition using Shape context,” Pattern Analysis and Machine Intelligence, vol. 24, pp. 509–522, 2002.