Image Mosaic Method Based on Gaussian Secondorder Difference Feature Operator  

Oleh:

Chen, Yong ; Hao, Yu-bin ; Zhan, Di

Jenis: Article from Journal - ilmiah nasional - terakreditasi DIKTI
Dalam koleksi: Telkomnika Indonesian Journal of Electrical Engineering vol. 15 no. 02 (Aug. 2015), page 336-345.
Topik: Sequence image; image matching; SIFT algorithm; first-order difference pyramid; secondorder difference pyramid.
Fulltext: 8124-18574-1-PB.pdf (436.21KB)

Isi artikel

To compose the wide visual angle and high resolution image from the sequence of images which have overlapping region in the same scene quickly and correctly, an improved SIFT algorithm which is based on D2oG interest point detector was proposed. It extracted the image feature points and generated corresponding feature descriptors by improved SIFT algorithm. Then, using the random consistency (RANSAC) algorithm purified feature point matching pairs and calculating the transformation matrix H. Last, complete the seamless mosaic of images by using the image fusion algorithm of slipping into and out. It respectively process the images which had the four typical transformations with the traditional SIFT and the proposed method. The result indicated that the number of feature pairs is fewer than SIFT algorithm and the mosaic time is shorter, and then the matching efficiency is higher than the later. This proposed method reduces the complexity of operation and improves real-time of image mosaic simultaneously.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali