本研究提出一個基於 SURF 和 RANSAC 的方法來取代傳統 OCR 方法進行書本
辨識，透過本研究根據書本特性提出的基於透視變換的N2Area 特徵點篩選法，
可將 RANSAC 的結果再進行更一步的篩選，藉此提升書本辨識的準確，同時利用
篩選所計算出的 RANSAC 殘留率當作閾值，也可以在計算重複率之前先行判定是
否要將該結果列入考量，藉此減少誤判的情況發生。但由於透視變換的對映矩
陣是基於 RANSAC 結果所計算而來，所以運算速度取決於 RANSAC 演算法的限制
而較為緩慢。而透過實驗的結果，N2Area 篩選法在進行特徵點區域落點判斷時，
應有一定的誤判，才會造成區域分割越多，反而準確率越低的情況。
從實驗結果來看，本研究方法仍有可以改良的地方；可使用 Overlapping
的方法來減少N2Area 篩選法所造成的誤判；因為計算 RANSAC 的時間為本研究
提出的方法中花費最多時間的步驟，若能改善 RANSAC 的計算時間就能夠更快的
提供比對結果，如何加快 RANSAC 的運算速度為本研究是否能實現即時檢索的關
鍵，降低 SURF 維度也是一種方法，但是 Bay 的研究[2]已經提出會因降低 SURF
維度而造成準確率降低，不過考慮到檢索可以用前 n 筆中有包含到正確圖片就
算對的情況下，或許是一個可以實作的選項之一。
42
參考文獻
[1]D.G. Lowe, "Distinctive image features from scale-invariant keypoints", In:
International journal of computer vision, 60.2(2002), 91-110.
[2]H. Bay, T.Tuytelaars, and L. Van Gool, "Surf: Speeded up robust features" , In:
Computer Vision-ECCV 2006.Springer,2006,404-417.
[3]E. Rosten andT. Drummond, "Machine learning for high-speed corner detection", In: Computer Vision-ECCV 2006.Springer,2006,430-443.
[4]E. Mair, G. D. hager, D. Burschka, M. Suppa, and G. Hirzinger, "Adaptive and generic corner detection based on the accelerated segment test", In: Computer
Vision-ECCV 2010.Springer,2010,183-196.
[5]E. Rosten, R. Porter, and T. Drummond, "Faster and better: A machine learning approach to corner detection", In: Pattern Analysis and Machine Intelligence,
IEEE Transactions on32.1(2010), 105-119.
[6]S. Leutenegger, M. Chli, and R. Y. Siegwart, "BRISK: Binary robust invariant scalable keypoints", In: Computer Vision(ICCV), 2011 IEEE International
Conference on.IEEE,2011, 2548-2555.
[7]M. Calonder, V. Lepetit, M. Ozuysal, T. Trzcinski, C. Strecha, and P. Fua, "BRIEF:
Computing a local binary descriptor very fast", In:Pattern Analysis and Machine
Intelligence, IEEE Transactions on34.7(2012), 1281-1298.
[8]E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: an efficient alternative to SIFT or SURF",In:In: Computer Vision(ICCV), 2011 IEEE International
Conference on.IEEE,2011, 2564-2571.
[9]C. Harris and M. Stephens, "A combined corner and edge detector",In: Alvey vision
conference.Vol. 15. Manchester, UK, 1988, p.50.
[10]E. Tola, V. Lepetit, and P. Fua, "Daisy: An efficient dense descriptor applied to wide-baseline stereo", In:Pattern Analysis and Machine Intelligence, IEEE
Transactions on32.5(2010), 815-830.
[11]M. A. Fischler and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography", In:
43
Communications of the ACM24.6(1981),381-395.
[12]P. Heckbert. Fundamentals of Texture Mapping and Image Warping. Master’s thesis, University of California at Berkeley, Department ofElectrical Engineering and Computer Science, June 17 1989.
[13]A. Criminisi, I. Reid, and A. Zisserman, "A plane measuring device", In: Image
and Vision Computing, vol17, Issue 8, June 1999, 625–634.
[14]"Parameter values for the HDTV standards for production and international programme exchange," ed: ITU-R Rec. BT. 709-5, 2002.
[15]P.A. Viola and M.J. Jones," Rapid object detection using a boosted cascade of simple features", In: CVPR, issue 1, 2001, pp. 511–518.
[16]D. Lowe, "Object recognition from local scale-invariant features", In: Computer
Vision(ICCV), 1999 IEEE International Conference on.IEEE,1999, 1150-1157.
[17]A. Neubeck and L. Van Gool, "Efficient non-maximum suppression", In: ICPR, 2006.
[18]M. Brown and D. Lowe, "Invariant features from interest point groups", In:
BMVC, 2002.
[19]O. Miksik and K. Mikolajczyk, "Evaluation of local detectors and descriptors for fast feature matching", In: Pattern Recognition(ICPR), 2012 21st International
Conference on. IEEE, 2012, 2681-2684.
[20] T. Lindeberg, "Scale-space for discrete signals",In: Pttern Analysis and Machine
Intelligence,IEEE Transactions on 234-254, 1990.
[21]Open Library. URL:https://openlibrary.org/lists [22]Cover Browser. URL:http://www.coverbrowser.com/
[23]Amazon. URL: http://www.amazon.com
[24]Q. Fan, V. Lepetit, and P. Fua, "Daisy: An efficient dense descriptor applied to wide-baseline stereo", In:Pattern Analysis and Machine Intelligence, IEEE Transactions on 32.5(2010), 815-830.
[25]K. Mikolajczyk and C. Schmid. "A performance evaluation of local descriptors".
In: Pttern Analysis and Machine Intelligence, IEEE Transactions on 27.10(2005), 1615-1630
44
[26]L. Juan and O. Gwun. "A comparison of sift, pca-sift and surf". In: International