跳到主要內容

臺灣博碩士論文加值系統

(44.192.22.242) 您好!臺灣時間:2021/08/01 12:36
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:陳淳哲
研究生(外文):Chun-Che Chen
論文名稱:使用二元化SIFT特徵及查找表的快速影像搜尋機制
論文名稱(外文):An Efficient Image Retrieval Scheme Using Binarized SIFT Features and Look-up Tables
指導教授:謝尚琳謝尚琳引用關係
指導教授(外文):Shang-Lin Hsieh
口試委員:謝尚琳
口試委員(外文):Shang-Lin Hsieh
口試日期:2015-05-12
學位類別:博士
校院名稱:大同大學
系所名稱:資訊工程學系(所)
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:英文
論文頁數:93
中文關鍵詞:特徵值二元化SIFT 特徵影像搜尋影像雜湊
外文關鍵詞:Feature binarizationSIFT featureImage retrievalHashing
相關次數:
  • 被引用被引用:1
  • 點閱點閱:202
  • 評分評分:
  • 下載下載:40
  • 收藏至我的研究室書目清單書目收藏:0
在影像搜尋的各種方法中,著名的 SIFT 是一種可以有效抽取影像特徵的方法,它已經被廣泛地應用在各個領域。然而,它在比對影像時會消耗太多的時間,導致整個搜尋的效率降低,因此比對是它最大的缺點。SIFT 方法在比對影像時,使用歐式距離(Euclidean distance)來計算二個向量之間的差距,而計算歐式距離相當花費時間,因為它使用到數值平方的運算。另一方面,影像資料庫的規模,通常會大到不合適使用線性方式來做搜尋,如此將導致搜尋速度過慢。為求改善 SIFT 的比對效率,本論文提出一種快速影像搜尋機制,將 SIFT 抽取的特徵值二元化,使得原本複雜的比對,簡化成快速的二進制運算。此外,本機制使用查找表(look-up tables)的技術來搜尋影像,查找表由四層的索引建立而成,索引值是由二元化的特徵值延伸而得,因此更加快了影像搜尋比對的速度。實驗用來測試二元化及查找表的有效性及效率,結果證明了本機制可以快速有效地搜尋影像,達到與 SIFT 相當的精確度,並且能優於其它方法。
In image retrieval, the well-known SIFT is capable of extracting distinctive features and has been widely used in many fields. However, it is time consuming in matching the features, which slows down the entire process and becomes its major drawback. In the SIFT matching, the Euclidean distance is used as the measurement between two vectors. The calculation of the distance is expensive because it involves the calculation of square of numbers. On the other hand, the scale of the image database usually is too large to adopt linear search for image retrieval. To improve the SIFT matching, this dissertation proposes a fast image retrieval scheme that transforms the SIFT features to binary representation. Accordingly, the complexity of the matching process can be reduced to a much simpler bit-wise operation, which greatly decreases the retrieval time. Furthermore, the proposed scheme utilizes look-up tables (LUT) with four layers of indexes to retrieve similar images. The indexes are derived from the binarized features and can further speed up the retrieval process. Experiments were conducted to examine the usefulness of the binary representation and the LUT, and to demonstrate the effectiveness and efficiency of the proposed scheme. SIFT method and two other methods were also tested for comparison. The experimental results show that the proposed scheme can retrieve images efficiently with comparable accuracy to SIFT and outperforms the other two methods.
CHAPTER 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Objective 6
1.3 Dissertation Organization 7
CHAPTER 2 RELATED BACKGROUND AND RESEARCH 8
2.1 Background 8
2.1.1 Log-polar transform 8
2.1.2 Scale-invariant feature transform 10
2.1.3 Hashing 16
2.1.4 Distance measurement 18
2.1.5 Look-up tables 19
2.2 SIFT-based Methods 20
2.2.1 Increasing the speed of SIFT matching calculation 21
2.2.2 Reducing the number of SIFT keypoints 24
2.2.3 Decreasing the dimension of SIFT descriptors 27
2.2.4 Binarizing the representation of SIFT keypoints 29
2.3 Non-SIFT Based Methods 37
2.3.1 A fast image retrieval method using inverted index 37
2.3.2 A duplicate images detecting scheme using multiple hash tables 39
2.4 Summary of The Improving Methods 42
CHAPTER 3 THE PROPOSED IMAGE RETRIEVAL SCHEME 43
3.1 Structure of the Proposed Scheme 43
3.2 The Feature Generation Phase 43
3.2.1 Preprocessing and SIFT feature extraction 44
3.2.2 SIFT feature extraction 44
3.2.3 Keypoint descriptor binarization 44
3.2.4 LUT indexing 47
3.3 The Similarity Measurement Phase 50
CHAPTER 4 EXPERIMENT RESULTS 55
4.1 The First Test of the Experiment 56
4.2 The Second Test of the Experiment 63
4.3 Matching Time Results 66
CHAPTER 5 COMPARISON AND DISCUSSION 67
5.1 Matching Accuracy 67
5.2 V1, V2 Determination and the Relationship Between Feature-α and Feature-β 69
5.3 Performance Analysis 70
5.3.1 Comparisons with other methods 70
5.3.2 Experimental average case 72
CHAPTER 6 CONCLUSIONS AND FUTURE WORK 75
REFERENCES 76
PUBLICATION 83
[1]Image retrieval, http://en.wikipedia.org/wiki/Image_retrieval, Accessed 15 April 2015.
[2]V. Karimi and A. Tashk, “Age and gender estimation by using hybrid facial features,” in Proceedings of 20th Telecommunications Frum, pp.1725-1728, November 2012.
[3]X. Jiang, “Feature extraction for image recognition and computer vision,” in Proceedings of Second IEEE International Conference on Computer Science and Information Technology, pp.1-15, August 2009.
[4]Y. Yang, “Geographic image retrieval using local invariant features,” IEEE Transactions on Geoscience and Remote Sensing, vol. 51, no. 2, pp.818-832, February 2013.
[5]Z. Liu, Houqiang Li, Wengang Zhou, Ruizhen Zhao, and Qi Tian, “Contextual hashing for large-scale image search,” IEEE Transactions on Image Processing, vol. 23, no. 4, pp.1606-1614, April 2014.
[6]U. Park, J. Park, and A. K. Jain, “Robust keypoint detection using higher-order scale space derivatives: application to image retrieval,” IEEE Signal Pocessing Letters, vol. 21, no. 8, pp.962-965, August 2014.
[7]J. Li, S. Zhou, J. Xing, C. Sun, and W. Hu, “An efficient approach to web near-duplicate image detection,” in Proceedings of 2013 Second IAPR Asian Conference on Pattern Recognition, pp.187-190, November 2013.
[8]S. M. Khamankar and M. S. Madankar, “Exposing digital image forgeries from near duplicate images,” in Proceedings of 2014 Fourth International Conference on Communication Systems and Network Technologies, pp.924-928, April 2014.
[9]C. Kim, and J. N. Hwang, “Object-based video abstraction for video surveillance systems,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 12, issue 12, pp.1128-1138, December 2002.
[10]B. Liu, J. Zhang, and X. Liao, “Projection kernel regression for image registration and fusion in video-based criminal investigation,” in Proceedings of the 2011 International Conference on Multimedia and Signal Processing, vol. 1, pp.348-352, May 2011.
[11]P. Ghosh, E. D. Gelasca, K. R. R. and B. S. Manjunath, “Duplicate image detection in large scale databases,” in Platinum Jubilee Volume, Indian Statistical Institute, Kolkata, 2007.
[12]J. Li, S. Zhou, J. Xing, C. Sun, and W. Hu, “An efficient approach to web near-duplicate image detection,” in Proceedings of 2013 Second IAPR Asian Conference on Pattern Recognition, pp.187-190, November 2013.
[13]J. Luo, Y. Ma, E. Takikawa, S. Lao, M. Kawade, and B. L. Lu, “Person-specific SIFT features for face recognition,” in Proceedings of 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 2, pp.593-596, April 2007.
[14]S. Z. Wang and X. P. Zhang, “Recent development of perceptual image hashing,” Journal of Shanghai University, vol. 11, no. 4, pp.323-331, 2007.
[15]H. B. Kekre1 and Dhirendra Mishra, “Image retrieval using image hashing,” Journal of Science, Engineering, and Technique Management, vol. 2, no. 1, January 2010.
[16]S. H. Yang and C. F. Chen, “Robust image hashing based on SPIHT,” in Proceedings of Third International Conference on Information Technology: Research and Education, pp.110-114, June 2005.
[17]N. Nikolaidis and I. Pitas, “Still image and video fingerprinting,” in Proceedings of 2009 Seventh International Conference on Advances in Pattern Recognition, pp.3-8, February 2009.
[18]L. Yua, M. Schmuckerb, C. Buschb, and S. Suna, “Cumulant-based image fingerprints,” in Proceedings of Seventh Conference on Security, Steganography, and Watermarking of Multimedia Contents, pp.68-75, January 2005.
[19]http://en.wikipedia.org/wiki/Content-based_image_retrieval#Applications, Accessed 15 April 2015.
[20]A. Auclair, N. Vincent, and L. D. Cohen, “Hash functions for near duplicate image retrieval,” in Proceedings of 2009 Workshop on Applications of Computer Vision, pp.1-6, December 2009.
[21]Y. H. Wan, Q. L. Yuan, S. M. Ji, L. M. He, and Y. L. Wang, “A survey of the image copy detection,” in Proceedings of IEEE Conference on Cybernetics and Intelligent Systems, pp.738-743, September 2008.
[22]Y. Zhao, S. Wang, G. Feng, and Z. Tang, “A robust image hashing method based on zernike moments,” Journal of Computational Information Systems, vol. 6, no. 3, pp.717-725, 2010.
[23]K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, issue 10, pp.1615-1630, 2005.
[24]V. Monga and B. L. Evans, “Perceptual image hashing via feature points: performance evaluation and tradeoffs,” IEEE Transactions on Image Processing, vol. 15, issue 11, pp.3453-3466, 2006.
[25]S. A. Berrani, L. Amsaleg, and P. Gros, “Robust content-based image searches for copyright protection,” in Proceedings of the first ACM International Workshop on Multimedia Databases, pp.70-77, 2003.
[26]H. Ling, L. Wang, F. Zou, and W. Yan, “Fine-search for image copy detection based on local affine-invariant descriptor and spatial dependent matching,” Multimedia Tools and Application, vol. 52, issue 2-3, pp.551-568, 2011.
[27]D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, issue 2, pp.91-110, 2004.
[28]J. Luo and G. Oubong, “A comparison of SIFT, PCA-SIFT, and SURF,” International Journal of Image Processing, vol. 3, issue 4, 2009.
[29]N. Y. Khan, B. McCane and G. Wyvill, “SIFT and SURF performance evaluation against various image deformations on benchmark dataset,” in Proceedings of 2011 International Conference on Digital Image Computing: Techniques and Applications, pp.510-506, December 2011.
[30]Image retrieval, http://pages.cs.wisc.edu/~beechung/dlm_image_processing/image_processing/retrieve.html, Accessed 15 April 2015.
[31]C. Harris and M. Stephens, “A combined corner and edge detector,” in Proceedings of the Fourth Alvey Vision Conference, pp.147-151, 1988.
[32]D. Zhu and X. Wang, “A method of improving SIFT algorithm matching efficiency,” in Proceedings of Second International Congress on Image and Signal Processing, pp.1-5, October 2009.
[33]J. Zhao, L. J. Xue, and G. Z. Mmen, “Optimization matching algorithm based on improved Harris and SIFT,” in Proceedings of the Ninth International Conference on Machine Learning and Cybernetics, vol. 1, pp.258-261, July 2010.
[34]R. J. Alitappeh, K. J. Saravi, and F. Mahmoudi, “Key point reduction In SIFT descriptor used by subtractive clustering,” in Proceedings of the 11th International Conference on Information Science, Signal Processing and their Applications, pp.906-911, July 2012.
[35]Y. Usui and K. Kondo, “The SIFT image feature reduction method using the histogram intersection kernel,” in Proceedings of International Symposium on Intelligent Signal Processing and Communication Systems, pp.517-520, January 2009.
[36]S. L. Hsieh, Y. W. Chen, C. C. Chen, and T. W. Chang, “A geometry-distortion resistant image detection system based on log-polar transform and scale invariant feature transform,” in Proceedings of the 13th International Conference on High Performance Computing and Communications, pp.893-897, September 2011.
[37]Y. Ke and R. Sukthankar, “PCA-SIFT: A more distinctive representation for local image descriptors,” in Proceedings of IEEE Computer Society Conference of Computer Vision and Pattern Recognition, pp.503-513, July 2004.
[38]W. Chen, K. Ding, and X. Wu, “Dimension reduction based SPM for image classification,” in Proceedings of the 25th Chinese Control and Decision Conference, pp.3755-3759, May 2013.
[39]Z. S. Ni, “B-SIFT: A binary SIFT based local image feature descriptor,” in Proceedings of the Fourth International Conference on Digital Home, pp.117-121, November 2012.
[40]K. A. Peker, “Binary SIFT: fast image retrieval using binary quantized sift features,” in Proceedings of ninth International Workshop on Content-Based Multimedia Indexing, pp.217-222, June 2011.
[41]C. C. Chen and S. L. Hsieh “Image retrieval using binarized sift features and hashing,” in Proceedings of 2014 International Conference on Business, Information, and Cultural Creative Industry, pp.47-56, August 2014.
[42]Hashing, http://searchsqlserver.techtarget.com/definition/hashing, Accessed 15 April 2015.
[43]Hash function, http://en.wikipedia.org/wiki/Hash_function, Accessed 15 April 2015.
[44]Inverted index, Wikipedia, http://en.wikipedia.org/wiki/Inverted_index, Accessed 15 April 2015.
[45]Y. Min, X. Li, Y. Zhang, Y. Zhao, and H. Lian, “A new sift keypoint descriptor for copy detection,” in Proceedings of fourth International Congress on Image and Signal Processing, pp.842-845, October 2011.
[46]Hamming distance, http://en.wikipedia.org/wiki/Hamming_distance, Accessed 15 April 2015.
[47]Look-up Table, http://en.wikipedia.org/wiki/Lookup_table, Accessed 15 April 2015.
[48]Using Table Look-up Techniques Efficiently, http://www2.sas.com/proceedings/forum2008/095-2008.pdf, Accessed 15 April 2015.
[49]J. A. Haitsma and T. Kalker, “A highly robust audio fingerprinting system,” in Proceedings of the International Conference on Music Information Retrieval, October 2002.
[50]J. S. Seo, J. Haitsma, T. Kalker, and C. D. Yoo, “A robust image fingerprinting system using the Radon transform,” Signal Processing: Image Communication, vol. 19, issue 4, pp.325-339, 2004.
[51]S. S. Thunuguntla, B. K. Gunturk, “feature-based image registration in Log-polar domain,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp.853-856, 2005.
[52]R. Matungka and Y. F. Zheng, “Studies on Log-Polar transform for image registration and improvements using adaptive sampling and logarithmic spiral,” Doctoral Dissertation, Ohio State University, OH, USA, 2009.
[53]J. Yao, X. Wang, and R. Wang, “Copy image detection based on local keypoints,” in Proceedings of 2011 International Conference of Soft Computing and Pattern Recognition, pp.258-262, October 2011.
[54]S. L. Hsieh, C. C. Chen, and C. R. Chen, “A novel approach to detecting duplicate images using multiple hash tables,” Multimedia Tools and Applications, February 2014.
[55]Zurich building image database for image-based recognition, http://www.vision.ee.ethz.ch/showroom/zubud/, Accessed 15 April 2015.
[56]K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 27, issue 10, pp.1615-1630, October 2005. http://lear.inrialpes.fr/people/mikolajczyk/Database/det_eval.html, Accessed 15 April 2015.
[57]Subtractive Clustering, http://radio.feld.cvut.cz/matlab/toolbox/fuzzy/fuzzyt42.html, Accessed 15 April 2015.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
1. 7. 江武讓(1993),「金融業務債權證券之研究」,彰銀資料,第42卷第6期。
2. 2. 王志誠(1997),「資產證券化與信託管理」,集保月刊,47期。
3. 6. 方燕玲(2001),「我國金融資產證券化之架構及應考量之問題」,會計研究月刊,191,34-36。
4. 13.吳家昌、游迺文(1999),「金融資產證券化及其對金融業影響之探討」,金融財務,第四期,頁35-44。
5. 18.林世淵(1995),「我國未來金融資產及不動產證券發展之方向」,證交資料,Vol.399,頁4-19。
6. 20.林倬仲(2000),「國內銀行發展資產證券化之探討」,今日合庫,第26卷第2期,27-46。
7. 23.郭恆慶(2002),「銀行金融資產證券化」,信用合作季刊,73期,頁42-54。
8. 24.陳建智(2004),「金融資產證券化財務報導探討(上)(中)(下1)(下2)」,證券櫃檯101期∼104期。
9. 32.黃建森、歐仁和、洪文興(2003),「台灣地區金融資產證券化之問題研究」,信用合作季刊,77期,頁08-29。
10. 33.黃建森、嚴宗銘、洪文興(2003),「金融發展與金融資產證券化問題研究」,信用合作季刊,78期,頁24-44。
11. 35.黃朝熙,「金融資產證券化對銀行體系之影響暨對中央銀行政策之意涵」,中央銀行季刊,第二十六卷第一期。
12. 38.張華平(2000),「資業證券化-日本經濟之啟示」,證券市場發展季刊,45期,117-139.
13. 39.張華平、黃莉芳、林魁德、陳佳慧、朱世宏(2004),台灣資產證券化市場之現況與未來發展,證券櫃檯月刊,第117期。
14. 41.廖咸興、李阿乙(2001),「資產證券化簡介與在台灣發展前景」,貨幣市場雙月刊,第5卷第4期,1-15.
15. 43.臧大年(1992),「資產證券-美國之經驗」,證券市場發展季刊,第16期。
 
無相關點閱論文