图像拼接
人工智能
图像融合
计算机视觉
计算机科学
小波变换
稳健性(进化)
图像配准
特征(语言学)
特征检测(计算机视觉)
模式识别(心理学)
图像处理
小波
图像(数学)
基因
哲学
生物化学
化学
语言学
作者
Jinxin Ruan,Liying Xie,Yuyan Ruan,Lindong Liu,Qiang Chen,Qian Zhang
标识
DOI:10.1109/icdh.2018.00009
摘要
With the development of image stitching and its wide application, image stitching has become an important and heated topic in image processing. An effective image stitching algorithm based on SURF feature matching and wavelet transform image fusion is proposed in this paper. Firstly, SURF feature points in the two adjacent images are extracted and matched. Then rapid and accurate image registration can be achieved by adopting the improved RNASCA algorithm to removing the mismatched feature point pairs. The multi-resolution decomposition of the overlapping region is processed by Wavelet Transform. Then the multi-scale image fusion is processed by fade-in and fade-out in order to eliminate the stitching seam better. Experiments show that the fusion results of the overlapping region are natural and there also is a certain robustness for translation, rotation, scale and luminance variant.
科研通智能强力驱动
Strongly Powered by AbleSci AI