學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 基於點群排序關係的動態設定特徵描述子建構及優化
Construction and optimization of feature descriptor based on dynamic local intensity order relations of pixel group作者 游佳霖
Yu, Carolyn貢獻者 廖文宏
Liao, Wen-Hung
游佳霖
Yu, Carolyn關鍵詞 特徵描述子
點群排序關係
影像比對
Local feature descriptors
Dynamic intensity order relations
Image matching日期 2017 上傳時間 31-八月-2017 12:15:29 (UTC+8) 摘要 隨著智慧型手機的普及,在移動裝置上直接處理圖像的需求也大幅增加,故對於影像特徵描述子的要求,除了要表現出區域特徵的穩健性,同時也要維持良好的特徵比對效率與合理的儲存空間。過去所提出的區域影像特徵描述子建構方法之中,LIOP方法具有相當不錯的表現力,但其特徵描述子維度會隨著點群取樣數量的提高而以倍數增加,因此本研究提出Dynamic Local Intensity Order Relations (DLIOR)特徵描述子建構方法,利用LIOR方法探討點群中點與點之間的關係,減緩其維度增長幅度;透過動態設定像素差距門檻值,處理影像間像素差距分佈不均的問題,並使用線性轉換、點對歐幾里德距離等方式,重新定義描述子欄位的權重設定。經過實驗證實,DLIOR方法能夠使用比LIOP方法更少的維度空間,描述更多點群數的特徵資訊,並且具有更高的特徵比對能力。
With the popularity of smart phones, the amounts of images being captured and processed on mobile devices have grown significantly in recent years. Image feature descriptors, which play crucial roles in recognition tasks, are expected to exhibit robust matching performance while at the same time maintain reasonable storage requirement. Among the local feature descriptors that have been proposed previously, local intensity order patterns (LIOP) demonstrated superior performance in many benchmark studies. As LIOP encodes the ranking relation in a point set (with N elements), however, its feature dimension increases drastically (N!) with the number of the neighboring sampling points around a pixel. To alleviate the dimensionality issue, this thesis presents a local feature descriptor by considering pairwise intensity relation in a pixel group, thereby reducing feature dimension to the order of C^N_2. In the proposed method, the threshold for assigning order relation is set dynamically according to local intensity distribution. Different weighting schemes, including linear transformation and Euclidean distance, have also been investigated to adjust the contribution of each pairing relation. Ultimately, the dynamic local intensity order relations (DLIOR) is devised to effectively encode intensity order relation of each pixel group. Experimental results indicate that DLIOR consumes less storage space than LIOP but achieves better feature matching performance using benchmark dataset.參考文獻 [1] Zhenhua Wang, Bin Fan, and Fuchao Wu. Local intensity order pattern for feature description. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 603–610. IEEE, 2011.[2] Wen-Hung Liao, Chia-Chen Wu, and Ming-Ching Lin. Feature descriptor based on local intensity order relations of pixel group. In Pattern Recognition (ICPR), 2016 23rd International Conference on, pages 1977–1981. IEEE, 2016.[3] Krystian Mikolajczyk and Cordelia Schmid. Scale & affine invariant interest point detectors. International journal of computer vision, 60(1):63–86, 2004.[4] Maurice George Kendall. Rank correlation methods. 1948.[5] David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110, 2004.[6] David G Lowe. Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, volume 2, pages 1150–1157. Ieee, 1999.[7] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. Surf: Speeded up robust features. In European conference on computer vision, pages 404–417. Springer, 2006.[8] Engin Tola, Vincent Lepetit, and Pascal Fua. Daisy: An efficient dense descriptor applied to wide-baseline stereo. IEEE transactions on pattern analysis and machine intelligence, 32(5):815–830, 2010.[9] Timo Ojala, Matti Pietikäinen, and David Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1):51–59, 1996.[10] Timo Ojala, Matti Pietikainen, and Topi Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis and machine intelligence, 24(7):971–987, 2002.[11] Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. Brief: Binary robust independent elementary features. In European conference on computer vision, pages 778–792. Springer, 2010.[12] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: An efficient alternative to sift or surf. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 2564–2571. IEEE, 2011.[13] Stefan Leutenegger, Margarita Chli, and Roland Y Siegwart. Brisk: Binary robust invariant scalable keypoints. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 2548–2555. IEEE, 2011.[14] Alexandre Alahi, Raphael Ortiz, and Pierre Vandergheynst. Freak: Fast retina keypoint. In Computer vision and pattern recognition (CVPR), 2012 IEEE conference on, pages 510–517. Ieee, 2012.[15] Zhenhua Wang, Bin Fan, Gang Wang, and Fuchao Wu. Exploring local and overall ordinal information for robust feature description. IEEE transactions on pattern analysis and machine intelligence, 38(11):2198–2211, 2016.[16] Ondrej Miksik and Krystian Mikolajczyk. Evaluation of local detectors and descriptors for fast feature matching. In Pattern Recognition (ICPR), 2012 21st International Conference on, pages 2681–2684. IEEE, 2012.[17] Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, Andrew Zisserman, Jiri Matas, Frederik Schaffalitzky, Timor Kadir, and Luc Van Gool. A comparison of affine region detectors. International journal of computer vision, 65(1-2):43–72, 2005.[18] Krystian Mikolajczyk and Cordelia Schmid. A performance evaluation of local descriptors. IEEE transactions on pattern analysis and machine intelligence, 27(10):1615–1630, 2005. 描述 碩士
國立政治大學
資訊科學學系
104753007資料來源 http://thesis.lib.nccu.edu.tw/record/#G0104753007 資料類型 thesis dc.contributor.advisor 廖文宏 zh_TW dc.contributor.advisor Liao, Wen-Hung en_US dc.contributor.author (作者) 游佳霖 zh_TW dc.contributor.author (作者) Yu, Carolyn en_US dc.creator (作者) 游佳霖 zh_TW dc.creator (作者) Yu, Carolyn en_US dc.date (日期) 2017 en_US dc.date.accessioned 31-八月-2017 12:15:29 (UTC+8) - dc.date.available 31-八月-2017 12:15:29 (UTC+8) - dc.date.issued (上傳時間) 31-八月-2017 12:15:29 (UTC+8) - dc.identifier (其他 識別碼) G0104753007 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/112385 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學學系 zh_TW dc.description (描述) 104753007 zh_TW dc.description.abstract (摘要) 隨著智慧型手機的普及,在移動裝置上直接處理圖像的需求也大幅增加,故對於影像特徵描述子的要求,除了要表現出區域特徵的穩健性,同時也要維持良好的特徵比對效率與合理的儲存空間。過去所提出的區域影像特徵描述子建構方法之中,LIOP方法具有相當不錯的表現力,但其特徵描述子維度會隨著點群取樣數量的提高而以倍數增加,因此本研究提出Dynamic Local Intensity Order Relations (DLIOR)特徵描述子建構方法,利用LIOR方法探討點群中點與點之間的關係,減緩其維度增長幅度;透過動態設定像素差距門檻值,處理影像間像素差距分佈不均的問題,並使用線性轉換、點對歐幾里德距離等方式,重新定義描述子欄位的權重設定。經過實驗證實,DLIOR方法能夠使用比LIOP方法更少的維度空間,描述更多點群數的特徵資訊,並且具有更高的特徵比對能力。 zh_TW dc.description.abstract (摘要) With the popularity of smart phones, the amounts of images being captured and processed on mobile devices have grown significantly in recent years. Image feature descriptors, which play crucial roles in recognition tasks, are expected to exhibit robust matching performance while at the same time maintain reasonable storage requirement. Among the local feature descriptors that have been proposed previously, local intensity order patterns (LIOP) demonstrated superior performance in many benchmark studies. As LIOP encodes the ranking relation in a point set (with N elements), however, its feature dimension increases drastically (N!) with the number of the neighboring sampling points around a pixel. To alleviate the dimensionality issue, this thesis presents a local feature descriptor by considering pairwise intensity relation in a pixel group, thereby reducing feature dimension to the order of C^N_2. In the proposed method, the threshold for assigning order relation is set dynamically according to local intensity distribution. Different weighting schemes, including linear transformation and Euclidean distance, have also been investigated to adjust the contribution of each pairing relation. Ultimately, the dynamic local intensity order relations (DLIOR) is devised to effectively encode intensity order relation of each pixel group. Experimental results indicate that DLIOR consumes less storage space than LIOP but achieves better feature matching performance using benchmark dataset. en_US dc.description.tableofcontents 第一章 緒論 1 1.1 研究背景與目的 1 1.2 流程與架構 2第二章 相關研究 4 2.1 區域影像特徵 4 2.1.1、基於梯度方向統計 4 2.1.2、基於點對關係 6 2.1.3、基於點群關係 8 2.2 Kendall tau 相關係數 11第三章 研究方法 14 3.1 Local Intensity Order Relations (LIOR) 14 3.2 像素值差距閾值 17 3.3 權重設定 19 3.3.1、權重差距調整 19 3.3.2、動態配置 20 3.3.3、基於歐幾里德距離的欄位權重設定 21 3.4 基於Kendall 相關係數的欄位權重設定 22第四章 實驗結果與分析 23 4.1 測試樣本 23 4.2 評估方法 23 4.3 LIOP 實驗 25 4.4 LIOR 實驗 27 4.5 DLIOR 實驗 29 4.5.1、DLIOR:動態閾值設定 29 4.5.2、DLIOR:權重設定 33 4.6 實驗結果小結 39 4.7 前處理改善 41 4.8 基於Kendall 相關係數的欄位權重設定 45第五章 結論 47參考文獻 48附錄一 LIOP 實驗數據51附錄二 LIOR 像素值差距分佈 53 zh_TW dc.format.extent 30721752 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0104753007 en_US dc.subject (關鍵詞) 特徵描述子 zh_TW dc.subject (關鍵詞) 點群排序關係 zh_TW dc.subject (關鍵詞) 影像比對 zh_TW dc.subject (關鍵詞) Local feature descriptors en_US dc.subject (關鍵詞) Dynamic intensity order relations en_US dc.subject (關鍵詞) Image matching en_US dc.title (題名) 基於點群排序關係的動態設定特徵描述子建構及優化 zh_TW dc.title (題名) Construction and optimization of feature descriptor based on dynamic local intensity order relations of pixel group en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] Zhenhua Wang, Bin Fan, and Fuchao Wu. Local intensity order pattern for feature description. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 603–610. IEEE, 2011.[2] Wen-Hung Liao, Chia-Chen Wu, and Ming-Ching Lin. Feature descriptor based on local intensity order relations of pixel group. In Pattern Recognition (ICPR), 2016 23rd International Conference on, pages 1977–1981. IEEE, 2016.[3] Krystian Mikolajczyk and Cordelia Schmid. Scale & affine invariant interest point detectors. International journal of computer vision, 60(1):63–86, 2004.[4] Maurice George Kendall. Rank correlation methods. 1948.[5] David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110, 2004.[6] David G Lowe. Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, volume 2, pages 1150–1157. Ieee, 1999.[7] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. Surf: Speeded up robust features. In European conference on computer vision, pages 404–417. Springer, 2006.[8] Engin Tola, Vincent Lepetit, and Pascal Fua. Daisy: An efficient dense descriptor applied to wide-baseline stereo. IEEE transactions on pattern analysis and machine intelligence, 32(5):815–830, 2010.[9] Timo Ojala, Matti Pietikäinen, and David Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1):51–59, 1996.[10] Timo Ojala, Matti Pietikainen, and Topi Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis and machine intelligence, 24(7):971–987, 2002.[11] Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. Brief: Binary robust independent elementary features. In European conference on computer vision, pages 778–792. Springer, 2010.[12] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: An efficient alternative to sift or surf. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 2564–2571. IEEE, 2011.[13] Stefan Leutenegger, Margarita Chli, and Roland Y Siegwart. Brisk: Binary robust invariant scalable keypoints. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 2548–2555. IEEE, 2011.[14] Alexandre Alahi, Raphael Ortiz, and Pierre Vandergheynst. Freak: Fast retina keypoint. In Computer vision and pattern recognition (CVPR), 2012 IEEE conference on, pages 510–517. Ieee, 2012.[15] Zhenhua Wang, Bin Fan, Gang Wang, and Fuchao Wu. Exploring local and overall ordinal information for robust feature description. IEEE transactions on pattern analysis and machine intelligence, 38(11):2198–2211, 2016.[16] Ondrej Miksik and Krystian Mikolajczyk. Evaluation of local detectors and descriptors for fast feature matching. In Pattern Recognition (ICPR), 2012 21st International Conference on, pages 2681–2684. IEEE, 2012.[17] Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, Andrew Zisserman, Jiri Matas, Frederik Schaffalitzky, Timor Kadir, and Luc Van Gool. A comparison of affine region detectors. International journal of computer vision, 65(1-2):43–72, 2005.[18] Krystian Mikolajczyk and Cordelia Schmid. A performance evaluation of local descriptors. IEEE transactions on pattern analysis and machine intelligence, 27(10):1615–1630, 2005. zh_TW