臺灣博碩士論文加值系統

本論文在Android平台上實現手寫文字辨識的功能，實作出一個完整的手寫文字之輸入與辨識的圖形介面。在文字辨識方面，使用特徵比對的方法進行文字辨識，在辨識的過程中，首先是對要辨識的區域使用二值化與Hilditch細化演算法，緊接著對細化後的區域使用Bandara GEMDC與Pathirana SD所提出的分割演算法進行分割。分割完成後，在依照每個文字之分割進行特徵擷取。同時，在特徵擷取階段，本論文提出改善判別弧的類型條件，據以提高手寫文字的辨識率。

The purpose of this thesis develops a graphic user interface for supporting handwritten character recognition in Android mobile platform. It is implemented for recognizing character through the word which is written on the screen. In character recognition perspective, the characteristics of character carry out character recognition. At first, the character skeletons have been processed by binarization and Hilditch thinning algorithm. Then, the handwritten character skeletons are segmented into meaningful segments through the segmentation algorithms which are proposed by Bandara GEMDC and Pathirana SD. Finally, the features can be extracted from the character segments. In the meantime, the new method can properly distinguish the arc type for feature extraction, so as the recognition rate of handwritten character can be improved.

摘要 i
Abstract ii
目錄 iii
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 論文架構 2
第二章 相關研究 3
2.1 影像辨識技術回顧 3
2.1.1 影像辨識的應用 3
2.2 Android系統平台相關研究 6
2.2.1 Android系統介紹 6
2.2.2 Android系統相關研究 7
第三章 手寫辨識之研究 8
3.1 影像前置處理 8
3.1.1 二值化 8
3.1.2 細化演算法 9
3.2 分割演算法 10
3.2.1 輸入與輸出 10
3.2.2 定義主要起始點與次要起始點 11
3.2.3 主要演算法 13
3.3 分割演算法－追蹤文字骨架 13
3.3.1 追蹤文字骨架 13
3.3.2 搜尋欲比較之暫存點 16
3.3.3 拜訪的方向 17
3.3.4 分割與角度計算 19
3.4 辨識 22
3.4.1 幾何特徵檢測(Geometrical feature detection) 23
3.4.2 計算特徵 24
3.4.3 定義特徵資料庫 29
第四章 文字辨識於Android系統 30
4.1 Android平台介紹 30
4.2 文字辨識於Android系統 31
4.2.1 手機的介面 32
4.2.2 影像前置處理 33
4.2.3 實現分割演算法 37
4.2.4 辨識 47
第五章 實驗結果 48
5.1 實現於Android平台之辨識結果 48
5.1.1 影像前置處理 48
5.1.2 分割演算法&辨識之結果 50
5.1.3 特徵資料庫之結果 51
5.2 文字辨識實驗 54
5.2.1 文字辨識的執行時間 54
5.2.2 文字辨識之辨識率實驗 61
第六章 結論與未來工作 62
6.1 結論 62
6.2 未來工作 62
參考文獻 63

[1]張宏林，「Visual C++數位影像模式識別技術及工程實踐」，臺北市：文魁資訊，2008。
[2]李寧原著、林城譯，「Android案例完全開發講義」，臺北市：碁峰資訊，2011。
[3]Android developer, http://developer.android.com/reference/packages.html. [Accessed: June 17, 2012].
[4]G. E. M. D. C. Bandara, S. D. Pathirana, and R. M. Ranawana, "Use of fuzzy feature descriptions to recognize handwritten alphanumeric characters," Proc. of 1st Conference on Fuzzy Systems and Knowledge Discovery, pp. 269-274, Singapore, 2002.
[5]C. J. Hilditch, B. Meltzer, and D. Michie, "Linear skeletons from square cupboards," in Machine Intelligence, vol. IV, Elsevier, New York, pp. 403-420, 1969.
[6]K. B. M. R. Batuwita and G. E. M. D. C. Bandara, " New segmentation algorithm for individual offline handwritten character segmentation," Proc. of 2nd Int. Conf. on Fuzzy Systems and Knowledge Discovery, Changsha, China, pp. 215–229 , 2005.
[7]Kim Gyeonghwan and Kim Sekwang, "Feature selection using genetic algorithms for handwritten character recognition," Proc. of the Sixth ACM SIGKDD, 2002.
[8]R. Ranawana, V. Palade, and G. E. M. D. C. Bandara, " Automatic fuzzy rule base generation for on-line handwritten alphanumeric character recognition," Int. Journal of Knowledge-Based and Intelligent Engineering Systems, vol. 9, no. 4, pp. 327–339, 2005.
[9]A. Goltsev and D. Rachkovskij, "Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings," Pattern Recognition, no. 3, pp. 315–322, 2005.
[10]A. Malaviya and L. Peters, "Handwriting recognition with fuzzy linguistic rules," Proc. of Third European Congress on Intelligent Techniques and Soft Computing ,Aachen, Germany, pp. 1430–1434, 1995.
[11]J. H. Chiang and P. D. Gader, "Hybrid fuzzy-neural systems in handwritten word recognition, " Proc. IEEE Trans. Fuzzy Systems, vol. 5, no. 4 , pp. 497–510, 1997.
[12]A. Malaviya and L. Peters, "Extracting meaningful handwriting features with fuzzy aggregation method," Proc. of ICDAR’95, Montreal, Canada, pp.841–844, 1995.