完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | 王信硯 | en_US |
dc.contributor.author | Wang, Hsin-Yen | en_US |
dc.contributor.author | 彭文孝 | en_US |
dc.contributor.author | Peng, Wen-Hsiao | en_US |
dc.date.accessioned | 2014-12-12T02:43:22Z | - |
dc.date.available | 2014-12-12T02:43:22Z | - |
dc.date.issued | 2013 | en_US |
dc.identifier.uri | http://140.113.39.130/cdrfb3/record/nctu/#GT070056073 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/75465 | - |
dc.description.abstract | 基於MPEG壓縮描述子用於視覺化檢索(CDVS)之架構,本論文提出一個利用本文資訊,濾掉特徵點配對中錯誤配對的方法。在區域描述子量化以及配對缺乏幾何資訊下,特徵點配對很容易產生非常多的錯誤,影響幾何驗證的判斷。因此,本論文嘗試結合了半區域演算法和虛弱幾何一致性兩方法,有效的將錯誤的配對濾除,進而減少幾何驗證的誤判率。為了減輕本文確認自身複雜度,本論文提出了以本文資訊為基礎之適配度檢定(WGC Goodness-of-fit Test),有效將近一半的雜訊影像省略幾何驗證的步驟。最後,在觀察到特徵點配對才是檢索中最複雜之下,本論文亦提出兩種以雜湊為基礎的特徵點配對方法,有效地降低整體檢索架構時間,並維持檢索精確度。實驗結果發現在mAP上相對於CDVS有1.0-2.1%的進步,而就檢索時間的分析上,本文資訊適配度檢定可以節省約4-14%的時間,而雜湊特徵點配對可以節省將近40-50%的時間。 | zh_TW |
dc.description.abstract | A key problem in MPEG-7 Compact Descriptors for Visual Search (CDVS) framework is the ambiguity of feature matching. To alleviate it, a new contextual verification scheme is introduced in CDVS by combining semi-local constraints and weak geometric consistency check. To mitigate time complexity incurred by the contextual verification, we propose a goodness-of-fit test based on the features’ orientation, which is motivated by the CDVS goodness-of-fit test. Moreover, we propose two hash-based feature matching schemes to speed up the feature matching process, which is found to be the most time-consuming process in the current CDVS framework. Experimental results show that the contextual verification offers 1.0-2.1% mAP improvements over CDVS. For time reduction experiments, 4-14% and 40-50% time savings are achieved by our goodness-of-fit test and hash-based feature matching scheme. | en_US |
dc.language.iso | zh_TW | en_US |
dc.subject | 巨量影像檢索 | zh_TW |
dc.subject | 區域描述子配對 | zh_TW |
dc.subject | 本文確認 | zh_TW |
dc.subject | 適配度檢定 | zh_TW |
dc.subject | 雜湊區域描述子配對 | zh_TW |
dc.subject | Large | en_US |
dc.subject | Local descriptor matching | en_US |
dc.subject | Contextual verification | en_US |
dc.subject | Goodness-of-fit test | en_US |
dc.subject | Hash-based feature matching | en_US |
dc.title | 針對巨量影像檢索使用本文資訊之區域描述子配對法 | zh_TW |
dc.title | Local descriptor matching using contextual information for large-scale image retrieval | en_US |
dc.type | Thesis | en_US |
dc.contributor.department | 資訊科學與工程研究所 | zh_TW |
顯示於類別: | 畢業論文 |