| dc.contributor | 資訊科學系 | - |
| dc.creator (作者) | 廖文宏 | zh_TW |
| dc.date (日期) | 2013-10 | - |
| dc.date.accessioned | 15-Apr-2016 11:32:21 (UTC+8) | - |
| dc.date.available | 15-Apr-2016 11:32:21 (UTC+8) | - |
| dc.date.issued (上傳時間) | 15-Apr-2016 11:32:21 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/84747 | - |
| dc.description.abstract (摘要) | 區域樣式其各種變型被廣泛應用於物件辨識中的特徵描述，然而現有的區域特徵描述方式(無論是二元或三元樣式)，因採用門檻值決定編碼的對應，因此當參考點像素值與中心點差異接近該門檻時，易受雜訊干擾而產生編碼的差異，先前我們所定義的延展式區域三元化樣式，也呈現同樣的狀況。 為了克服上述問題，本研究擬導入模糊邏輯，建構更具抗噪力的樣式描述方法，而導入的時機點有二，一是將模糊理論應用於編碼的過程中，改用成員函式的方法進行樣式之編碼(稱為Fuzzy ELTP)；二是應用於降維的階段，即用模糊化的分群法(如 fuzzy c-means)取代原步驟中的分群法(稱為 FCM-ELTP)。 我們將研究以上兩類區域模糊特徵描述子的特性，並針對其抗噪性、描述力與通用性進行深度的分析與廣泛的實驗，以檢驗此類圖像描述方法之效能，並與現有的各種特徵描述法，含LBP、ELTP、CDR-ELTP等相互比較。我們也預計將模糊理論與三元化及的概念，套用至區域二元化樣式的各種變型，以定義更多樣化的區域圖像描述方法。 | - |
| dc.description.abstract (摘要) | Local binary/ternary patterns are widely employed to describe the local structure of an image. However, local patterns are very sensitive to noise due to the thresholding process. Extended local ternary patterns have been shown to exhibit better noise resistance. Yet the ternarization process introduces discontinuities near the threshold values and results in abrupt changes in the generated ternary patterns. In this research, we propose two different approaches to incorporate fuzziness in extended local ternary patterns (ELTP) to enhance the robustness of this class of operator to interferences. The first approach replaces the ternary mapping mechanism with fuzzy member functions to arrive at a fuzzy ELTP representation. The second approach modifies the clustering operation in formulating ELTP to a fuzzy c-means procedure to construct soft histograms in the final feature representation, denoted as FCM-ELTP. The newly defined local fuzzy descriptors will be extensively tested to analyze its universality, discriminability, and noise sensitivity. Specifically, experiments will be conducted to compare the performance of original LBP, ELTP and the newly proposed fuzzy ELTP and FCM-ELTP. We will also utilize fuzzy theory along with the concept of ternarization to various derivatives of local binary pattern to generate more versatile local fuzzy descriptors. | - |
| dc.format.extent | 2459284 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | 計畫編號 NSC101-2221-E004-009 | - |
| dc.title (題名) | 基於區域模糊樣式的特徵描述方式 | zh_TW |
| dc.title.alternative (其他題名) | Feature Description Using Local Fuzzy Patterns | - |
| dc.type (資料類型) | report | - |
