以優勢點樹鄰近搜尋方法設計4808個 中文常用字分類器

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：32

、訪客IP：3.21.231.245

姓名

張捷(Chang-Jay) 查詢紙本館藏

畢業系所

通訊工程學系在職專班

論文名稱

以優勢點樹鄰近搜尋方法設計4808個中文常用字分類器
(Designed with Vantage Point Tree proximity search method 4808 common Chinese word)

相關論文

★ 掌紋紋理特徵擷取與身分識別

★ 一個4x4磁場感應器陣列設計與實作

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2026-10-1以後開放)

摘要(中)

本論文提出在中文字辨識領域中以鄰近搜尋的方式取代深度學習的模型訓練架構。採用以Two Stage方式，將教育部提供的4808個常用中文字作為文字辨識的依據，以影像形態學處理加上水平垂直投影的方法進行文字切割，使用灰度共生矩陣與空間矩擷取中文字的特徵，透過正規化將特徵值等比例的縮放到0~1區間輸出，並以不同字型樣式的4808中文字作為優勢點樹分類器資料庫，並以優勢點樹分類器透過歐幾里得距離範圍進行中文字的鄰近搜尋辨識，與開源的Tesseract-OCR光學字元辨識軟體進行4808個中文字常用的辨識結果比較。實驗中發現優勢點樹分類器的建立時間均低於1秒，比起深度學習模型的訓練減少許多，而且在以新細明體作為優勢點樹分類器資料庫對於不同字型中文字的鄰近搜尋中，平均辨識率達到79%，優於Tesseract-OCR中文字的辨識結果。

摘要(英)

This paper proposes a model training architecture that replaces deep learning with proximity search in the field of Chinese character recognition, use 4808 commonly used Chinese characters provided by the Ministry of Education as the basis for character recognition, by using image morphology processing plus horizontal and vertical projection for Chinese character cutting, Using the grayscale symbiotic matrix and spatial moment to capture the characteristics of Chinese words, the characteristic value is scaled to 0 to 1 interval output by formalization. With different font styles of 4808 Chinese words as the advantage point tree classifier database, and the advantage point tree classifier through the Euclidean distance range for Chinese word proximity search identification. Compared with the optical character recognition software of open source Tesseract-OCR, the identification results of 4808 Chinese words were compared. In the experiment, found that the establishment time of the advantage point tree classifier was less than 1 second, which was much less than the training of the deep learning model, and the average recognition rate of the database of the advantage point tree classifier with the new detail as the advantage point tree classifier reached 79% in the adjacent search for different type Chinese words, which was better than the recognition results of Tesseract-OCR Chinese words.

關鍵字(中)

★ 鄰近搜尋
★ 歐幾里得距離
★ 文字辨識
★ 文字切割
★ 水平垂直投影

關鍵字(英)

★ Tesseract-OCR
★ VP-Tree
★ GLCM
★ Euclidean Distance

論文目次

摘要 I
Abstract II
致謝 III
目錄 IV
圖目錄 VI
表目錄 IX
第一章、緒論 1
1.1 研究動機 1
1.2 研究目的 3
1.3 論文架構 3
第二章、方法回顧 4
2.1 文字辨識 4
2.2 文字切割 5
2.2.1 二值化(Binary) 6
2.2.2 膨脹(Dilation) 8
2.2.3 影像的水平垂直投影 10
2.3 灰度共生矩陣(GLCM) 12
2.4 空間矩(Spatial moment) 16
2.5 正規化(Normalization) 18
2.4 鄰近搜尋方法(Near Search) 19
2.5 優勢點樹(VP-Tree) 20
2.6 Tesseract-OCR 23
第三章、4808個中文常用字分類器系統設計 25
3.1 MIAT系統設計方法論 25
3.1.1 IDEF0階層式架構 26
3.1.2 Grafcet離散事件建模 27
3.2 4808個中文常用字分類器系統架構 28
3.2.1 文字切割架構 30
3.2.2 特徵值擷取架構 32
3.2.3 優勢點樹鄰近搜尋中文字辨識架構 34
3.2.4 Tesseract-OCR中文字辨識架構 36
第四章、實驗結果與分析 38
4.1開發環境 38
4.2 文字切割實驗 39
4.3 特徵值擷取實驗 45
4.4 優勢點樹鄰近搜尋中文字辨識實驗 46
4.5 Tesseract-OCR中文字辨識實驗 58
第五章、結論與未來展望 63
5.1 結論 63
5.2 未來展望 64
參考文獻 65

參考文獻

[1] E. S. Lubana and R. P. Dick, "Digital Foveation: An Energy-Aware Machine Vision Framework," in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 37, no. 11, pp. 2371-2380, Nov. 2018.
[2] T. Parakontan and W. Sawangsri, "Development of the Machine Vision System for Automated Inspection of Printed Circuit Board Assembl," 2019 3rd International Conference on Robotics and Automation Sciences (ICRAS), 2019, pp. 244-248.
[3] Yihong Xu and G. Nagy, "Prototype extraction and adaptive OCR," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 12, pp. 1280-1296, Dec. 1999.
[4] IBM, Endicott chronology,1961-1969:
https://www.ibm.com/ibm/history/exhibits/endicott/endicott_chronology1960.html
[5] T. Nasir, M. K. Malik and K. Shahzad, "MMU-OCR-21: Towards End-to-End Urdu Text Recognition Using Deep Learning," in IEEE Access.
[6] S. S. Lee, M. Shishibori and C. Y. Han, "Compression of Search Range of VP-Tree for Multimedia Data Retrieval Applications," 2012 Data Compression Conference, 2012, pp. 403-403.
[7] C. Gupta, G. Ozsoyoglu and Z. M. Ozsoyoglu, "Efficient k-word proximity search," 2009 24th International Symposium on Computer and Information Sciences, 2009, pp. 123-128.
[8] J. Tan et al., "3D-GLCM CNN: A 3-Dimensional Gray-Level Co-Occurrence Matrix-Based CNN Model for Polyp Classification via CT Colonography," in IEEE Transactions on Medical Imaging, vol. 39, no. 6, pp. 2013-2024, June 2020.
[9] Narayanan, Natarajan & Govindarajan, Suresh Kumar. (2014). Spatial moment analysis of solute transport with Langmuir sorption in a fracture-skin-matrix coupled system. Journal of King Saud University - Engineering Sciences. 23. 10.1016/j.jksues
.2014.04.003.
[10] L. Friedman and O. V. Komogortsev, "Assessment of the Effectiveness of Seven Biometric Feature Normalization Techniques," in IEEE Transactions on Information Forensics and Security, vol. 14, no. 10, pp. 2528-2536, Oct. 2019.
[11] Á. Z. Kaló and M. L. Sipos, "Key-Value Pair Searhing System via Tesseract OCR and Post Processing," 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI), 2021, pp. 000461-000464.
[12] S. S. Al-Amri, N. Kalyankar, and S. Khamitkar, "Image segmentation by using edge detection", International journal on computer science and engineering, vol. 2, no. 3, pp. 804-807, 2010.
[13] B. Su, S. Lu and C. L. Tan, "Combination of Document Image Binarization Techniques," 2011 International Conference on Document Analysis and Recognition, 2011, pp. 22-26.
[14] S. Allegretti, F. Bolelli and C. Grana, "Optimized Block-Based Algorithms to Label Connected Components on GPUs," in IEEE Transactions on Parallel and Distributed Systems, vol. 31, no. 2, pp. 423-438, 1 Feb. 2020.
[15] J. Meng, W. Zhang and C. Ma, "Classifying algorithm for watermarks based on mathematical morphology," 2018 Chinese Control And Decision Conference (CCDC), 2018, pp. 2985-2988.
[16] G. Bouleux, M. Dugast and E. Marcon, "Information Topological Characterization of Periodically Correlated Processes by Dilation Operators," in IEEE Transactions on Information Theory, vol. 65, no. 10, pp. 6484-6495, Oct. 2019.
[17] M. K. Mahto, K. Bhatia and R. K. Sharma, "Combined horizontal and vertical projection feature extraction technique for Gurmukhi handwritten character recognition," 2015 International Conference on Advances in Computer Engineering and Applications, 2015, pp. 59-65.
[18] F. Ma, X. -Y. Jing, X. Zhu, Z. Tang and Z. Peng, "True-Color and Grayscale Video Person Re-Identification," in IEEE Transactions on Information Forensics and Security, vol. 15, pp. 115-129, 2020.
[19] N. A. Golilarz, H. Gao, W. Ali and M. Shahid, "Hyper-Spectral Remote Sensing Image De-Noising with Three Dimensional Wavelet Transform Utilizing Smooth Nonlinear Soft Thresholding Function," 2018 15th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 2018, pp. 142-146.
[20] M. Rakhshanfar and M. A. Amer, "Low-Frequency Image Noise Removal Using White Noise Filter," 2018 25th IEEE International Conference on Image Processing (ICIP), 2018, pp. 3948-3952.
[21] A. Jiménez-Sánchez, G. Silva-Navarro and F. Beltrán-Carbajal, "Structural analysis of superficial cracks on structural elements," 2019 16th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), 2019, pp. 1-6.
[22] Y. Jung, J. Ko, S. Bae, Y. Kang, H. -S. Lee and D. Kim, "Effective Surface Texturing of Diamond-Wire-Sawn Multicrystalline Silicon Wafers Via Crystallization of the Native Surface Amorphous Layer," in IEEE Journal of Photovoltaics, vol. 11, no. 1, pp. 43-49, Jan. 2021, doi: 10.1109/JPHOTOV.2020.3035122.
[23] H. Esponda, E. Vázquez, M. A. Andrade and B. K. Johnson, "A Setting-Free Differential Protection for Power Transformers Based on Second Central Moment," in IEEE Transactions on Power Delivery, vol. 34, no. 2, pp. 750-759, April 2019.
[24] J. Flusser, T. Suk, J. Boldyš and B. Zitová, "Projection Operators and Moment Invariants to Image Blurring," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 4, pp. 786-802, 1 April 2015, doi: 10.1109/TPAMI.2014.2353644.
[25] B. Zheng, H. Gao, X. Ma and X. Zhang, "Graph Partition Based on Dimensionless Similarity and Its Application to Fault Diagnosis," in IEEE Access, vol. 9, pp. 35573-35583, 2021.
[26] C. A. Rabbath, N. Hori and N. Lechevin, "Convergence of sampled-data models in digital redesign," in IEEE Transactions on Automatic Control, vol. 49, no. 5, pp. 850-855, May 2004.
[27] S. Eghbali, H. Ashtiani and L. Tahvildari, "Online Nearest Neighbor Search Using Hamming Weight Trees," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 7, pp. 1729-1740, 1 July 2020.
[28] Y. A. Malkov and D. A. Yashunin, "Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 4, pp. 824-836, 1 April 2020.
[29] W. Zhang, X. Chen, Y. Liu and Q. Xi, "A Distributed Storage and Computation k-Nearest Neighbor Algorithm Based Cloud-Edge Computing for Cyber-Physical-Social Systems," in IEEE Access, vol. 8, pp. 50118-50130, 2020.
[30] X. Gao and G. Li, "A KNN Model Based on Manhattan Distance to Identify the SNARE Proteins," in IEEE Access, vol. 8, pp. 112922-112931, 2020.
[31] P. Tabaghi, I. Dokmanić and M. Vetterli, "Kinetic Euclidean Distance Matrices," in IEEE Transactions on Signal Processing, vol. 68, pp. 452-465, 2020
[32] H. Q. Dinh, X. Wang and P. Maneejuk, "On the Hamming Distance of Repeated-Root Cyclic Codes of Length 6ps," in IEEE Access, vol. 8, pp. 39946-39958, 2020.
[33] Z. Liu, F. Chen and S. Duan, "Distributed Fast Supervised Discrete Hashing," in IEEE Access, vol. 7, pp. 90003-90011, 2019.
[34] J. K. Uhlmann, "Satisfying general proximity / similarity queries with metric trees," Information Processing Letters, vol. 40, no. 4, pp. 175-179, 1991/11/25/ 1991.
[35] J. P. Coon, M. Badiu, Y. Liu, F. Yarkin and S. Dang, "Binary-Tree Encoding for Uniform Binary Sources in Index Modulation Systems," in IEEE Journal of Selected Topics in Signal Processing, vol. 13, no. 6, pp. 1270-1285, Oct. 2019.
[36] S. Dai, L. Li and Z. Li, "Modeling Vehicle Interactions via Modified LSTM Models for Trajectory Prediction," in IEEE Access, vol. 7, pp. 38287-38296, 2019.
[37] R. David, "Grafcet: a powerful tool for specification of logic controllers," IEEE Transactions on Control Systems Technology, vol. 3, no. 3, pp. 253-268, 1995.

指導教授

林銀議陳慶瀚

審核日期

2021-10-19

推文