首頁 > 網路資源 > 大同大學數位論文系統

Title page for etd-0902114-095721


URN etd-0902114-095721 Statistics This thesis had been viewed 1530 times. Download 219 times.
Author Jhe-Wei Gao
Author's Email Address No Public.
Department Computer Science and Enginerring
Year 2013 Semester 2
Degree Master Type of Document Master's Thesis
Language zh-TW.Big5 Chinese Page Count 42
Title Improving SIFT Matching Efficiency Using Hashing and Descriptor Binarization Techniques
Keyword
  • SIFT
  • descriptor binarization
  • hashing
  • hashing
  • descriptor binarization
  • SIFT
  • Abstract Scale-invariant feature transform (SIFT) is an algorithm in computer vision. Although it can achieve high accuracy in image matching, the speed of image matching is slow. The thesis presents a method that uses hashing and descriptor binarization to improve SIFT matching efficiency. Our method applies SIFT descriptor binarization to reduce the cost of image matching. It decreases the computational complexity with only a little loss of matching accuracy. Also, our method utilizes hashing to decrease the quantity of the matching pairs substantially and hence reduce the matching time. The experimental result demonstrates that, with only a small decrease in accuracy, the matching speed of our method is about 2500 times faster than that of SIFT linear matching. Moreover, our hashing method can be applied to other methods that adopt SIFT descriptor binarization.
    Advisor Committee
  • Shang-Lin Hsieh - advisor
  • Chen-Chiung Hsieh - co-chair
  • Liang-Teh Lee - co-chair
  • Files indicate accessible at a year
    Date of Defense 2014-07-30 Date of Submission 2014-09-02


    Browse | Search All Available ETDs