A key prerequisite for the establishment of digitalized sheep farms and precision animal husbandry is the accurate identification of each sheep’s identity. Due to the uncertainty in recognizing sheep faces, the differences in sheep posture and shooting angle in the recognition process have an impact on the recognition accuracy. In this study, we propose a deep learning model based on the RepVGG algorithm and bilinear feature extraction and fusion for the recognition of sheep faces. The model training and testing datasets consist of photos of sheep faces at different distances and angles. We first design a feature extraction channel with an attention mechanism and RepVGG blocks. The RepVGG block reparameterization mechanism is used to achieve lossless compression of the model, thus improving its recognition efficiency. Second, two feature extraction channels are used to form a bilinear feature extraction network, which extracts important features for different poses and angles of the sheep face. Finally, features at the same scale from different images are fused to enhance the feature information, improving the recognition ability and robustness of the network. The test results demonstrate that the proposed model can effectively reduce the effect of sheep face pose on the recognition accuracy, with recognition rates reaching 95.95%, 97.64%, and 99.43% for the sheep side-, front-, and full-face datasets, respectively, outperforming several state-of-the-art sheep face recognition models.

To address the challenge of recognizing sheep faces of the same type, which exhibit significant similarities and varying performance of RGB images under different lighting conditions and angles, this paper proposes a dual-branch multi-modal sheep face recognition model based on the ResNet18 architecture. This model effectively learns geometric features from depth data and texture features from RGB data, thereby enhancing recognition accuracy. Initially, the model employs two InceptionV2 layers, one for the RGB channel and another for the depth channel, to extract specific features from both modalities. Subsequently, the losses from the two modalities are computed. In the mid-stage, the two modalities are fused using the Convolutional Block Attention Module (CBAM), and in the final stage, a residual network is utilized to learn the complementary features between the modalities. Experimental results demonstrate that this model benefits from effective multi-modal fusion, achieving high accuracy in sheep face recognition under complex lighting conditions and various angles.

Silica/cellulose composite aerogels with increased optical transmittance were prepared by incorporation of silica in the matrix, and the obtained aerogels had increased homogeneous microstructure, high porosity and surface area, low density. It indicated that the incorporated silica had an obvious influence on the microstructure of the composite aerogels, the composite aerogels with small content of silica had transmittance about 66% at 550 nm, while for pure cellulose aerogels it was about 44%. Moreover, the composite aerogels had low thermal conductivity (0.04–0.05 W/m k) at ambient conditions. The developed method for the preparation of the cellulose-based aerogels with improved thermal stability, mechanical properties and transmittance, as well as ultralow thermal conductivity made the aerogels as promising candidates for transparent insulators.