請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/6838完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 劉長遠 | |
| dc.contributor.author | Hong-Yi Shih | en |
| dc.contributor.author | 施鴻逸 | zh_TW |
| dc.date.accessioned | 2021-05-17T09:19:13Z | - |
| dc.date.available | 2015-10-12 | |
| dc.date.available | 2021-05-17T09:19:13Z | - |
| dc.date.copyright | 2012-10-12 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-09-24 | |
| dc.identifier.citation | [1] C. Y. Liou and H. C. Yang. Handprinted Character Recognition Based On Spatial Topology Distance Measurement.IEEE Trans. Pattern Anal. Mach. Intell., 18(9):
941–945, 1996. [2] C. Y. Liou and W. J. Yu. Ambiguous Binary Representation in Multilayer Neural Networks. InNeural Networks, 1995. Proceedings., IEEE International Conference on, volume 1, pages 379–384. IEEE, 1995. [3] D. R. Liou, C. C. Lin, and C. Y. Liou. Setting Shape Rules for Handprinted Character Recognition. InACIIDS (2), pages 245–252, 2012. [4] J. Rocha and T. Pavlidis. A Shape Analysis Model with Applications to a Character Recognition System.IEEE Trans. Pattern Anal. Mach. Intell., 16(4):393–404, 1994. [5] J. Rocha and T. Pavlidis. Character Recognition Without Segmentation.IEEE Trans. Pattern Anal. Mach. Intell., 17(9):903–909, 1995. [6] S. W. Lu, Y. Ren, and C. Y. Suen. Hierarchical Attributed Graph Representation And Recognition of Handwritten Chinese Characters.Pattern Recognition, 24(7): 617–632, 1991. [7] C. Y. Liou and H. C. Yang. Selective Feature-to-Feature Adhesion for Recognition of Cursive Handprinted Characters.IEEE Trans. Pattern Anal. Mach. Intell., 21(2): 184–191, 1999. [8] J.J. Hopfield and D.W. Tank. Neural Computation of Decisions in Optimization Problems.Biological cybernetics, 52(3):141–152, 1985. [9] C. Y. Liou and H. C. Yang. Self-Organization of High-Order Receptive Fields in Recognition of Handprinted Characters. InNeural Information Processing, 1999. Proceedings. ICONIP’99. 6th International Conference on, volume 3, pages 1161–1166. IEEE, 1999. [10] A. Moscona and H. Moscona. The Dissociation and Aggregation of Cells from Organ Rudiments of The Early Chick Embryo. Journal of anatomy, 86(3):287, 1952. [11] P. L. Townes and J. Holtfreter. Directed Movements And Selective Adhesion of Embryonic Amphibian Cells. Journal of experimental zoology, 128(1):53–120, 1955. [12] N. M. Nasrabadi, W. Li, and C. Y. Choo. Object Recognition by a Hopfield Neural Network. InICCV, pages 325–328, 1990. [13] Ponnuthurai N. Suganthan, Eam Khwang Teoh, and Dinesh P. Mital. Pattern Recognition by Homomorphic Graph Matching Using Hopfield Neural Networks.Image Vision Comput., 13(1):45–60, 1995. [14] H. Szu. Fast TSP Algorithm Based on Binary Neuron Output and Analog Neuron Input Using The Zero-Diagonal Interconnect Matrix and Necessary and Sufficient Constraints of the Permutation Matrix.IEEE Trans. Int’l Conf Neural Networks, 2: 259–266, 1988. [15] S.V.B. Aiyer, M. Niranjan, and F. Fallside. A Theoretical Investigation Into the Performance of the Hopfield Model.Neural Networks, IEEE Transactions on, 1(2): 204–215, 1990. [16] D. E. Rummelhart, G.E. Hinton, and J. L. McClelland. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 1986. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/6838 | - |
| dc.description.abstract | 本論文為手寫字辨認設計兩項新的幾何規則，並將原有的特徵表示法做推廣，在應用霍氏模型的方法中得到較好的配對結果。除了手寫字辨認以外，我們也提出許多符合現今需求的新應用，本論文所提供的方法能夠繼續發展以解決這些更複雜的應用。
曲橢圓特徵模型適合用來表現複雜的幾何型態，這些特徵點在幾何上擁有許多規則，我們可以應用霍氏模型記憶這些規則以達成特徵點的配對。設計更多不同的幾何規則能提升識別率，也能解決許多不同類型的型態辨識問題。 | zh_TW |
| dc.description.abstract | There are two similarities constructed in earlier works, named inter-feature similarity and inter-link similarity. This work rewrites geomet-rical relations and constructs them into Hopfield model to improve the matching result.
Constructing a set of bended-ellipse features is an efficient way for sampling cursive patterns. It converts a pattern into structural features and pro-vides a natural way for handprinted characters recognition. The idea which called feature-to-feature adhesion constructs a topological configuration for a pattern and transforms it into an undirected graph. The compatibility asso-ciated with the graph is then formulated as an optimization problem and is solved by a devised Hopfield network. | en |
| dc.description.provenance | Made available in DSpace on 2021-05-17T09:19:13Z (GMT). No. of bitstreams: 1 ntu-101-R97922015-1.pdf: 1965726 bytes, checksum: 6f0271e9bf5013cf63a9fb88d2f8e2f2 (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | 致 謝 i
摘 要 ii Abstract iii Contents iv List of Figures v 1 Introduction 1 2 Feature-to-Feature Adhesion Method 4 2.1 Bended-Ellipse Features . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 Feature-to-Feature Order . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3 Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3 Our improve 17 3.1 Adding new similarity measurements . . . . . . . . . . . . . . . . . . . . 17 3.2 Weighted bended-ellipse feature . . . . . . . . . . . . . . . . . . . . . . 22 4 Applications and discussion 26 5 Summary 29 Bibliography 30 | |
| dc.language.iso | en | |
| dc.subject | Bended-ellipse feature | en |
| dc.subject | Handprinted character recognition | en |
| dc.subject | Pattern recognition | en |
| dc.subject | Hopfield model | en |
| dc.subject | Geometrical relation | en |
| dc.title | 應用霍氏模型記憶幾何規則 | zh_TW |
| dc.title | Finite Geometrical Relations Loading in Hopfield Model | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 101-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 呂育道,鄭為正,黃昭綺 | |
| dc.subject.keyword | 手寫字辨識,樣式辨識,霍氏模型,幾何規則,曲橢圓特徵, | zh_TW |
| dc.subject.keyword | Handprinted character recognition,Pattern recognition,Hopfield model,Geometrical relation,Bended-ellipse feature, | en |
| dc.relation.page | 32 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2012-09-25 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-101-1.pdf | 1.92 MB | Adobe PDF | 檢視/開啟 |
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。