Title :
An improved SIFT algorithm for image feature-matching
Author :
Chen, Wenyu ; Zhao, Yanli ; Xie, Wenzhi ; Sang, Nan
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China
Abstract :
SIFT algorithm has strong robustness and stability, which can be applied in many bad conditions to achieve high recognition rate. The 128-dimensional feature descriptor has good independence. However, it also contains redundant information, which makes the calculation amount of following matching increase. An improved SIFT algorithm is proposed to solve the disadvantages of large computation and not meet "real time" of the original one, which reduces the dimension of the feature vector and reduces the mismatching of SIFT algorithm. It has been proved from the experiment that the improved algorithm can significantly increase running speed and guarantee the robustness. Besides, it can meet "real-time" requirements.
Keywords :
feature extraction; image matching; image recognition; 128-dimensional feature descriptor; feature vector; image feature matching; image recognition; improved SIFT algorithm; stability; Accuracy; Algorithm design and analysis; Feature extraction; Histograms; Real time systems; Robustness; Signal processing algorithms; SIFT algorithm; dimension; real-time; robustness;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6003022
