1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 基於多元編碼機制之區域特徵描述子
Local Descriptors Based on Multi-level Encoding Scheme
作者 翁苡甄
貢獻者 廖文宏
翁苡甄
關鍵詞 多元化區域特徵描述子
二元化區域特徵描述子
影像辨識
local multi-level encoding descriptor
local binary descriptor
object recognition
日期 2014
上傳時間 1-Dec-2014 14:19:35 (UTC+8)
摘要 影像辨識一直是電腦視覺中很重要的技術，且伴隨著行動裝置與相機的普及，人們更加重視辨識的準確度與效能，以區域梯度分佈及直方圖表示方法為基礎的影像特徵描述子，如SIFT與SURF，是近十多年來的物件辨識技術中所採用的主流演算法，然而此類特徵表示法，常需要為多維度的資訊提供大量的儲存空間與複雜的距離計算流程，因此，近年來有學者提出了另一種形式的區域二元特徵描述子 ( Local Binary Descriptor, LBD)，以二元架構建立描述子，使得LBD能在較少空間之下提供可相抗衡的辨識率。
本論文提出以多元編碼機制之區域特徵描述子(LMLED)，乃基於LBD的基本架構，但改以多元編碼取代LBD的二元編碼方法，利用緩衝區的架構達到更強的抗噪性，並提出降維方法以承襲二元編碼在儲存空間的優勢，使得多元編碼機制之區域特徵描述子能在不影響匹配能力與儲存空間的情況下，得到更佳的影像辨識能力。
Efficient and robust object recognition is an important yet challenging task in computer vision. With the popularity of mobile equipment and digital camera, the demand for effectiveness and efficiency in image recognition has become increasingly pressing. In the past decade, local feature descriptors based on the distribution of local gradients and histogram representation such as SIFT and SURF have achieved a certain level of success. However, these descriptors require a large amount of storage and computing resources for high dimensional feature vectors. Hence, local binary descriptor (LBD) arises and becomes popular in recent years, providing comparable performance with binary structure that needs dramatically lower storage cost.
In this thesis, we propose to employ multi-level encoding scheme to replace binary encoding of LBD. The resultant descriptor is named local multi-level encoding descriptor (LMLED). LMLED takes advantage of multiple decision intervals and thus can achieve better noise resistivity. Methods to reduce the dimension have been devised to maintain low storage cost. Extensive experiments have been performed and the results validate that LMLED can achieve superior performance under noisy condition while maintaining comparable matching efficacy and storage requirement.
參考文獻 [1] Mikolajczyk, K.,Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 2004, 1615-1630.
[2] Hua, G., Brown, M., Winder, S.: Discriminant Embedding for Local Image Descriptors. In International Conference on Computer Vision, 2007.
[3] Calonder, M., Lepetit, V., Strecha, C., Fua, P.:“Brief: Binary robust independent elementary features.” In Proceeding of the European Conference on Computer Vision(ECCV), 2010. 778-792.‏
[4] Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: “ORB: an efficient alternative to SIFT or SURF.” In International Conference on Computer Vision ICCV, 2011, In IEEE International Conference, 2011.‏
[5] Leutenegger, S., Chli, M., Siegwart, R.Y.: “BRISK: Binary robust invariant scalable keypoints.”In International Conference on Computer Vision ICCV, 2011, IEEE International Conference, 2011.‏
[6] Alahi, A., Ortiz, R., Vandergheyns, P.: “Freak: Fast retina keypoint”, In Computer Vision and Pattern Recognition (CVPR), 2012, IEEE International Conference, 2012.‏
[7] Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. Computer Vision and Image Understanding 20, 91–110, 2004.
[8] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: Speeded Up Robust Features, Computer Vision and Image Understanding 10, 346–359, 2008.
[9] Canny, J.:A Computational Approach To Edge Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.
[10] Scharr, Hanno: Dissertation (in German), Optimal Operators in Digital Image Processing, 2000.
[11] C. Harris and M. Stephens: ”A combined corner and edge detector”, Proceedings of the 4th Alvey Vision Conference. 147–151, 1998.
[12] S. M. Smith and J. M. Brady:"SUSAN–a new approach to low level image processing", International Journal of Computer Vision 23,45–78,1997.
[13] Rosten, E., Drummond, T.: Machine learning for high-speed corner detection. In Proceeding of the European Conference on Computer Vision(ECCV), 2006.
[14] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: Speeded Up Robust Features, Computer Vision and Image Understanding 10, 346–359, 2008.
[15] P. L. Rosin. Measuring corner properties. Computer Vision and Image Understanding, 73(2):291 – 307, 1999.
[16] Everingham, M.: The PASCAL Visual Object Classes Challenge 2006 (VOC2006) Results.
[17] Hamming, Richard W.:"Error detecting and error correcting codes", Bell System Technical Journal29(2),147–160,1950.
[18] Cao, X. , Zhang, H., Liu, S., Guo, X., Lin, L.: “SYM-FISH: A Symmetry-Aware Flip Invariant Sketch Histogram Shape Descriptor”, In Computer Vision (ICCV), IEEE International Conference, 313 – 320, 2013.
[19] Heinly, J., Dunn, E., Frahm, JM.: Comparative Evaluation of Binary Features, In Computer Vision (ECCV), 2012.
[20] Miksik, O., Mikolajczyk, K.: Evaluation of local detectors and descriptors for fast feature matching, In Pattern Recognition (ICPR), 21st International Conference on pp. 2681~2684, 2012.
[21] H.R. Sheikh, Z.Wang, L. Cormack and A.C. Bovik, "LIVE Image Quality Assessment Database Release 2", http://live.ece.utexas.edu/research/quality.
[22] E. C. Larson and D. M. Chandler, "Most apparent distortion: full-reference image quality assessment and the role of strategy," Journal of Electronic Imaging, 19 (1), March 2010.
[23] N. Ponomarenko, O. Ieremeiev, V. Lukin, K. Egiazarian, L. Jin, J. Astola, B. Vozel, K. Chehdi, M. Carli, F. Battisti, C.-C. Jay Kuo, Color Image Database TID2013: Peculiarities and Preliminary Results, Proceedings of 4th Europian Workshop on Visual Information Processing EUVIP2013, June 10-12, 2013, pp. 106-111.
[24] R. Arandjelović and A. Zisserman, "Three things everyone should know to improve object retrieval", CVPR, 2012.
描述 碩士
國立政治大學
資訊科學學系
101753013
103
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0101753013
資料類型 thesis
dc.contributor.advisor 廖文宏zh_TW
dc.contributor.author (Authors) 翁苡甄zh_TW
dc.creator (作者) 翁苡甄zh_TW
dc.date (日期) 2014en_US
dc.date.accessioned 1-Dec-2014 14:19:35 (UTC+8)-
dc.date.available 1-Dec-2014 14:19:35 (UTC+8)-
dc.date.issued (上傳時間) 1-Dec-2014 14:19:35 (UTC+8)-
dc.identifier (Other Identifiers) G0101753013en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/71720-
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) 101753013zh_TW
dc.description (描述) 103zh_TW
dc.description.abstract (摘要) 影像辨識一直是電腦視覺中很重要的技術，且伴隨著行動裝置與相機的普及，人們更加重視辨識的準確度與效能，以區域梯度分佈及直方圖表示方法為基礎的影像特徵描述子，如SIFT與SURF，是近十多年來的物件辨識技術中所採用的主流演算法，然而此類特徵表示法，常需要為多維度的資訊提供大量的儲存空間與複雜的距離計算流程，因此，近年來有學者提出了另一種形式的區域二元特徵描述子 ( Local Binary Descriptor, LBD)，以二元架構建立描述子，使得LBD能在較少空間之下提供可相抗衡的辨識率。
本論文提出以多元編碼機制之區域特徵描述子(LMLED)，乃基於LBD的基本架構，但改以多元編碼取代LBD的二元編碼方法，利用緩衝區的架構達到更強的抗噪性，並提出降維方法以承襲二元編碼在儲存空間的優勢，使得多元編碼機制之區域特徵描述子能在不影響匹配能力與儲存空間的情況下，得到更佳的影像辨識能力。		zh_TW
dc.description.abstract (摘要) Efficient and robust object recognition is an important yet challenging task in computer vision. With the popularity of mobile equipment and digital camera, the demand for effectiveness and efficiency in image recognition has become increasingly pressing. In the past decade, local feature descriptors based on the distribution of local gradients and histogram representation such as SIFT and SURF have achieved a certain level of success. However, these descriptors require a large amount of storage and computing resources for high dimensional feature vectors. Hence, local binary descriptor (LBD) arises and becomes popular in recent years, providing comparable performance with binary structure that needs dramatically lower storage cost.
In this thesis, we propose to employ multi-level encoding scheme to replace binary encoding of LBD. The resultant descriptor is named local multi-level encoding descriptor (LMLED). LMLED takes advantage of multiple decision intervals and thus can achieve better noise resistivity. Methods to reduce the dimension have been devised to maintain low storage cost. Extensive experiments have been performed and the results validate that LMLED can achieve superior performance under noisy condition while maintaining comparable matching efficacy and storage requirement.		en_US
dc.description.tableofcontents 第一章 緒論----------------------------------------------------------------------------------- 1
1.1 研究背景與目的----------------------------------------------------------------- 1
1.2 流程架構與方法----------------------------------------------------------------- 2
第二章 相關研究----------------------------------------------------------------------------- 4
2.1 特徵擷取--------------------------------------------------------------------------- 4
2.1.1 FAST------------------------------------------------------------------------- 5
2.1.2 AGAST --------------------------------------------------------------------- 6
2.2 二元特徵描述子------------------------------------------------------------------ 6
2.2.1 BRIEF----------------------------------------------------------------------- 7
2.2.2 ORB------------------------------------------------------------------------- 9
2.2.3 BRISK---------------------------------------------------------------------- 11
2.2.4 FREAK--------------------------------------------------------------------- 13
2.2.5 SYM-FISH----------------------------------------------------------------- 15
2.2.6 小結------------------------------------------------------------------------- 16
第三章 基於多元編碼機制之區域特徵描述子---------------------------------------- 17
3.1 二元區域特徵描述子----------------------------------------------------------- 17
3.2 多元編碼機制之區域特徵描述子--------------------------------------------- 22
第四章 實驗結果與分析------------------------------------------------------------------- 28
4.1 多元編碼機制之定義------------------------------------------------------------ 28
4.2 降維方法---------------------------------------------------------------------------- 29
4.3 多元編碼機制之實驗--------------------------------------------------------------31
4.3.1 實驗資料樣本與評估方法---------------------------------------------- 31
4.3.2 實驗結果(一)--------------------------------------------------------------- 34
4.3.3 實驗結果(二)-----------------------------------------------------------------51
4.3.4 實驗結果(三)-----------------------------------------------------------------55
4.3.5 實驗結果(四)-----------------------------------------------------------------59
4.3.6 多元編碼機制之BRISK的實驗小結------------------------------------63
第五章 結論與未來目標------------------------------------------------------------------- 63
參考文獻---------------------------------------------------------------------------------------- 64
附錄一 增加白色雜訊，增加閃爍雜訊-------------------------------------------------- 67
附錄二 高斯模糊化，JPEG壓縮法------------------------------------------------------- 81
附錄三 亮度變化，對比度變化---------------------------------------------------------- 106
附錄四 旋轉不變性、延展不變性與視角轉換---------------------------------------- 110		zh_TW
dc.format.extent 17511681 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0101753013en_US
dc.subject (關鍵詞) 多元化區域特徵描述子zh_TW
dc.subject (關鍵詞) 二元化區域特徵描述子zh_TW
dc.subject (關鍵詞) 影像辨識zh_TW
dc.subject (關鍵詞) local multi-level encoding descriptoren_US
dc.subject (關鍵詞) local binary descriptoren_US
dc.subject (關鍵詞) object recognitionen_US
dc.title (題名) 基於多元編碼機制之區域特徵描述子zh_TW
dc.title (題名) Local Descriptors Based on Multi-level Encoding Schemeen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) [1] Mikolajczyk, K.,Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 2004, 1615-1630.
[2] Hua, G., Brown, M., Winder, S.: Discriminant Embedding for Local Image Descriptors. In International Conference on Computer Vision, 2007.
[3] Calonder, M., Lepetit, V., Strecha, C., Fua, P.:“Brief: Binary robust independent elementary features.” In Proceeding of the European Conference on Computer Vision(ECCV), 2010. 778-792.‏
[4] Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: “ORB: an efficient alternative to SIFT or SURF.” In International Conference on Computer Vision ICCV, 2011, In IEEE International Conference, 2011.‏
[5] Leutenegger, S., Chli, M., Siegwart, R.Y.: “BRISK: Binary robust invariant scalable keypoints.”In International Conference on Computer Vision ICCV, 2011, IEEE International Conference, 2011.‏
[6] Alahi, A., Ortiz, R., Vandergheyns, P.: “Freak: Fast retina keypoint”, In Computer Vision and Pattern Recognition (CVPR), 2012, IEEE International Conference, 2012.‏
[7] Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. Computer Vision and Image Understanding 20, 91–110, 2004.
[8] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: Speeded Up Robust Features, Computer Vision and Image Understanding 10, 346–359, 2008.
[9] Canny, J.:A Computational Approach To Edge Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.
[10] Scharr, Hanno: Dissertation (in German), Optimal Operators in Digital Image Processing, 2000.
[11] C. Harris and M. Stephens: ”A combined corner and edge detector”, Proceedings of the 4th Alvey Vision Conference. 147–151, 1998.
[12] S. M. Smith and J. M. Brady:"SUSAN–a new approach to low level image processing", International Journal of Computer Vision 23,45–78,1997.
[13] Rosten, E., Drummond, T.: Machine learning for high-speed corner detection. In Proceeding of the European Conference on Computer Vision(ECCV), 2006.
[14] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf: Speeded Up Robust Features, Computer Vision and Image Understanding 10, 346–359, 2008.
[15] P. L. Rosin. Measuring corner properties. Computer Vision and Image Understanding, 73(2):291 – 307, 1999.
[16] Everingham, M.: The PASCAL Visual Object Classes Challenge 2006 (VOC2006) Results.
[17] Hamming, Richard W.:"Error detecting and error correcting codes", Bell System Technical Journal29(2),147–160,1950.
[18] Cao, X. , Zhang, H., Liu, S., Guo, X., Lin, L.: “SYM-FISH: A Symmetry-Aware Flip Invariant Sketch Histogram Shape Descriptor”, In Computer Vision (ICCV), IEEE International Conference, 313 – 320, 2013.
[19] Heinly, J., Dunn, E., Frahm, JM.: Comparative Evaluation of Binary Features, In Computer Vision (ECCV), 2012.
[20] Miksik, O., Mikolajczyk, K.: Evaluation of local detectors and descriptors for fast feature matching, In Pattern Recognition (ICPR), 21st International Conference on pp. 2681~2684, 2012.
[21] H.R. Sheikh, Z.Wang, L. Cormack and A.C. Bovik, "LIVE Image Quality Assessment Database Release 2", http://live.ece.utexas.edu/research/quality.
[22] E. C. Larson and D. M. Chandler, "Most apparent distortion: full-reference image quality assessment and the role of strategy," Journal of Electronic Imaging, 19 (1), March 2010.
[23] N. Ponomarenko, O. Ieremeiev, V. Lukin, K. Egiazarian, L. Jin, J. Astola, B. Vozel, K. Chehdi, M. Carli, F. Battisti, C.-C. Jay Kuo, Color Image Database TID2013: Peculiarities and Preliminary Results, Proceedings of 4th Europian Workshop on Visual Information Processing EUVIP2013, June 10-12, 2013, pp. 106-111.
[24] R. Arandjelović and A. Zisserman, "Three things everyone should know to improve object retrieval", CVPR, 2012.		zh_TW