Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 吳欣澔 | en_US |
dc.contributor.author | Wu, Shin-Hao | en_US |
dc.contributor.author | 陳稔 | en_US |
dc.contributor.author | Chen, Zen | en_US |
dc.date.accessioned | 2015-11-26T00:55:17Z | - |
dc.date.available | 2015-11-26T00:55:17Z | - |
dc.date.issued | 2015 | en_US |
dc.identifier.uri | http://140.113.39.130/cdrfb3/record/nctu/#GT070156602 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/125671 | - |
dc.description.abstract | 本論文的目標為低混淆性的手寫英數字辨識,為了解決手寫字筆劃多變化的問題,我們以電腦分析圖片文字骨架的方式得到固定的筆劃順序,使形狀相似的文字產生相似的筆劃順序。整個文字辨識系統分成三個步驟,第一步驟運用型態學方法找出文字圖片之主幹骨架,並得到細線化的文字圖;第二步驟對細線化後的文字圖做筆劃追蹤,得到文字的筆劃順序;第三步驟則使用Universal Hashing建立筆劃順序的1對1索引結構。 | zh_TW |
dc.description.abstract | The goal of this thesis is to recognize handwritten character with low ambiguity. In order to solve the problem that handwritten characters has too much stroke order, we use computer to analysis the skeleton of character image and get unify stroke order. So, character similar in shape will have same stroke order. This system is composed of into three steps. In the first steps, we find the major skeleton of the character image based on Morphology, and get thinned character image. In the second step, we trace the thinned character image to get stroke order of the character. In the third step, the Universal hashing is used to establish the index of stroke orders. | en_US |
dc.language.iso | zh_TW | en_US |
dc.subject | 文字辨識 | zh_TW |
dc.subject | Character Recognition | en_US |
dc.title | 低混淆性的手寫英數字印刷體辨識技術 | zh_TW |
dc.title | Handwritten Alphanumeric Character Recognition with Low Ambiguity | en_US |
dc.type | Thesis | en_US |
dc.contributor.department | 多媒體工程研究所 | zh_TW |
Appears in Collections: | Thesis |