In recent years, due to the shortage of timber resources, it has become necessary to reduce the excessive consumption of forest resources. Non-destructive testing technology can quickly find wood defects and effectively improve wood utilization. Deep learning has achieved significant results as one of the most commonly used methods in the detection of wood knots. However, compared with convolutional neural networks in other fields, the depth of deep learning models for the detection of wood knots is still very shallow. This is because the number of samples marked in the wood detection is too small, which limits the accuracy of the final prediction of the results. In this paper, ResNet-34 is combined with transfer learning, and a new TL-ResNet34 deep learning model with 35 convolution depths is proposed to detect wood knot defects. Among them, ResNet-34 is used as a feature extractor for wood knot defects. At the same time, a new method TL-ResNet34 is proposed, which combines ResNet-34 with transfer learning. After that, the wood knot defect dataset was applied to TL-ResNet34 for testing. The results show that the detection accuracy of the dataset trained by TL-ResNet34 is significantly higher than that of other methods. This shows that the final prediction accuracy of the detection of wood knot defects can be improved by TL-ResNet34.

No abstract

Fano resonance is a pervasive resonance phenomenon which can be applied to high sensitivity sensing, perfect absorption, electromagnetic-induced transparency, and slow-light photonic devices. In this paper, we propose a metal–insulator–metal (MIM) waveguide structure consisting of a D-shaped cavity and a bus waveguide with a silver–air–silver barrier. The Fano resonance can be achieved by the interaction between the D-shaped cavity and the bus waveguide. The finite element method is used to analyze the transmission characteristics and magnetic-field distributions of the structure in detail. Simulation results show the Fano resonance can be adjusted by altering the geometric parameters of the MIM waveguide structure or the refractive index of the D-shaped cavity. The maximum refractive index sensitivity of the structure can reach up to 1510 nm/RIU, and there is a good linear relationship between resonance wavelength and refractive index. Since it has good sensitivity and tunability, the MIM waveguide structure can be used in bio-sensing, such as human hemoglobin detection. We show its applicability for the detection of three different human blood groups as well.

In this paper, a metal–insulator–metal (MIM) waveguide structure consisting of a side-coupled rectangular cavity (SCRC), a rightward opening semi-ring cavity (ROSRC), and a bus waveguide is reported. The finite element method is used to analyze the transmission characteristics and magnetic-field distributions of the structure in detail. The structure can support triple Fano resonances, and the Fano resonances can be tuned independently by altering the geometric parameters of the structure. Moreover, the structure can be applied in refractive index sensing and biosensing. The maximum sensitivity of refractive index sensing is up to 1550.38 nm/RIU, and there is a good linear relationship between resonance wavelength and refractive index. The MIM waveguide structure has potential applications in optical on-chip nano-sensing.

A plasmonic metal-insulator-metal (MIM) waveguide system is proposed, which is composed of a symmetrical X-shaped resonant cavity and a bus waveguide with a baffle, and its Fano resonance and optical sensing characteristics are investigated by using the finite element method (FEM). The results show that the system allows easy implementation of up to four Fano resonances, and the maximum refractive index sensitivity and figure of merit are 1303 nm/RIU and 3113, respectively. The influences of the geometric parameters of the system on the Fano resonances are also investigated, and further the independent adjustments of the Fano resonance line shape and wavelength are realized. Moreover, when an additional X-shaped resonant cavity is added to the system, more ultrasharp Fano resonances with considerable performances are obtained, which may enhance the parallel processing capability of the system. The proposed plasmonic MIM waveguide system may have potential applications in integrated photonic devices and nanoscale optical sensing.