Image Stitching Based on Discrete Wavelet Transform and Slope Fusion
The fusion algorithm of traditional image stitching does not fully consider the differences of the clarity of the two images, and the conventional Discrete Wavelet Transform algorithm would blur the image when applied to image stitching. Owing to these, an improved method based on Discrete Wavelet Transform and Slope Fusion is proposed. The proposed algorithm firstly performs Haar wavelet transform on the image to be fused to obtain a low-frequency component and multiple high-frequency components. Subsequently, the Slope Fusion method is used for the obtained low-frequency component and the sub-regional Slope Fusion method is used for the high-frequency components. Finally, the fused image is obtained by using the Inverse Discrete Wavelet Transform for the new low-frequency component and high-frequency components. The proposed algorithm can retain the information of direction and detail while taking full account of differences in image sharpness, all of those benefits help improve the quality of the fused image effectively. The experimental results show that the proposed algorithm can make the fused image clearer and objectively enhance multiple fusion indicators of the fused image.
KeywordsImage stitching Discrete Wavelet Transform Slope Fusion Inverse Discrete Wavelet Transform Fusion indicators
The authors would like to acknowledge the supports by the National Natural Science Foundation of China (Grant No. 61471124), Key Industrial Guidance Projects of Fujian Science and Technology Department (Grant No. 2016H0016 and 2015H0021).
- 2.Ha, Y.J., Kang, H.D.: Evaluation of feature based image stitching algorithm using OpenCV. In: 10th International Conference on Human System Interactions (HSI) (2017)Google Scholar
- 3.Chen, X., Liu, H., Zhou, M., et al.: Medical image mosaic based on low-overlapping regions. In: International Congress on Image and Signal Processing (2018)Google Scholar
- 6.Chen, K., Wang, M.: Image stitching algorithm research based on OpenCV. In: Control Conference (2014)Google Scholar
- 7.Lin, M., Xu, G., Ren, X., et al.: Cylindrical panoramic image stitching method based on multi-cameras. In: IEEE International Conference on Cyber Technology in Automation (2015)Google Scholar
- 12.Burt, P.J., Adelson, E.H.: Merging images through pattern decomposition. In: Applications of Digital Image Processing VIII (1985)Google Scholar
- 13.Zhang, B.: Study on image fusion based on different fusion rules of wavelet transform. In: Proceedings of the 3rd International Conference on Advanced Computer Theory and Engineering (ICACTE) (2010)Google Scholar
- 14.Daza, R.J.M., Upegui, E.: Image fusion using the wavelet TRW and Haar transforms: enhancement of spatial resolution for the Ikonos images from Ortophotos. In: 7th IEEE International Conference on Software Engineering and Service Science (ICSESS) (2016)Google Scholar