ABSTRACT

Shu, J.; Chen, Z.; Xu, C., and Liu, W., 2018. Recognition method of fish image with dynamic deformation based on depth learning network model. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 397–401. Coconut Creek (Florida), ISSN 0749-0208.

Due to the failure distortion correction of the fish image with dynamic deformation, there cognition accuracy of traditional fish image with dynamic deformation is not high, therefore, a recognition method of fish image with dynamic deformation based on deep learning network model is proposed in this paper. By dividing the fish image with dynamic deformation, the segmented image is made rotation synthesis, to realize the deformation correction. Based on the deep learning network model algorithm, the partial derivative value of each parameter of fish image with dynamic deformation is calculated, to determine the characteristics distribution point of the fish image with dynamic deformation, and realize the fish image recognition. The experimental results show that the proposed method can accurately recognize the fish image with dynamic deformation, and the recognition results are better.

This content is only available as a PDF.
You do not currently have access to this content.