Affiliations: [a] Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China | [b] Institute of mathematical, China University of Geosciences, Beijing, China | [c] National Engineering Research Center of Agricultural Informatization, Beijing, China
Correspondence:
[*]
Corresponding author: Qifeng Li, National Engineering Research Center of Agricultural Informatization, 100097, Beijing, China. E-mail: liqf@nercita.org.cn.
Abstract: To solve the problem that individual visual features could not be accurately extracted from low-light and high-noise pig face images in intensive farming, the optimal fitting curve parameters of image brightness enhancement were defined, and the Zero-DCE model was improved and Denoise-Net was introduced to achieve brightness enhancement and high-noise suppression of a single low-light pig face image. The experimental results show that, compared with EnlightGAN, Zero-DCE, Retinex, and SSE, the algorithm in this paper (DCE-Denoise-Net) has good results on image quality metrics such as information entropy, Brisque, NIQE, and PIQE in the absence of reference images. The image quality is improved. On the basis of improving the low visibility of low-light images, denoising was achieved. It is more suitable for low-light pig face image enhancement in a real breeding environment.
