Han, P. and Han, Y., 2018. Noise reduction and recovery algorithm for underwater distorted image. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 720–723. Coconut Creek (Florida), ISSN 0749-0208.

Due to some unavoidable internal factors of digital cameras and other imaging equipment, as well as human and environmental external factors, the underwater photographing images will be distorted, thus affecting the recognition effect of optical character recognition. The traditional noise reduction algorithm has low efficiency and short time-consuming. Therefore, in this paper, a document image distortion recognition algorithm based on full automatic image splicing is proposed. Firstly, two distorted images captured from different angles for the same document page are processed by feature extraction, image registration, transformation and so on, and then spliced into a nearly non-deformation document image. The experimental results show that the algorithm proposed in this paper can effectively deal with the problem of document image distortion recognition, and has a very high development prospect.