Geographical traceability of soybean: An electronic nose coupled with an effective deep learning method.

The quality of soybeans is correlated with their geographical origin. It is a common phenomenon to replace low-quality soybeans from substandard origins with superior ones. This paper proposes the adaptive convolutional kernel channel attention network (AKCA-Net) combined with an electronic nose (e-nose) to achieve soybean quality traceability. First, the e-nose system is used to collect soybean gas information from different origins. Second, depending on the characteristics of the gas information, we propose the adaptive convolutional kernel channel attention (AKCA) module, which focuses on key gas channel features adaptively. Finally, the AKCA-Net is proposed, which is capable of modeling deep gas channel interdependency efficiently, realizing high-precision recognition of soybean quality. In comparative experiments with other attention mechanisms, AKCA-Net demonstrated superior performance, achieving an accuracy of 98.21%, precision of 98.57%, and recall of 98.60%. In conclusion, the combination of the AKCA-Net and e-nose provides an effective strategy for soybean quality traceability.

Autofocus methods based on laser illumination.

Autofocusing system plays an important role in microscopic measurement. However, natural-image-based autofocus methods encounter difficulties in improving focusing accuracy and robustness due to the diversity of detection objects. In this paper, a high-precision autofocus method with laser illumination was proposed, termed laser split-image autofocus (LSA), which actively endows the detection scene with image features. The common non-learning-based and learning-based methods for LSA were quantitatively analyzed and evaluated. Furthermore, a lightweight comparative framework model for LSA, termed split-image comparison model (SCM), was proposed to further improve the focusing accuracy and robustness, and a realistic split-image dataset of sufficient size was made to train all models. The experiment showed LSA has better focusing performance than natural-image-based method. In addition, SCM has a great improvement in accuracy and robustness compared with previous learning and non-learning methods, with a mean focusing error of 0.317µm in complex scenes. Therefore, SCM is more suitable for industrial measurement.

High-precision microscopic autofocus with a single natural image.

In industrial microscopic detection, learning-based autofocus methods have empowered operators to acquire high-quality images quickly. However, there are two parts of errors in Learning-based methods: the fitting error of the network model and the making error of the prior dataset, which limits the potential for further improvements in focusing accuracy. In this paper, a high-precision autofocus pipeline was introduced, which predicts the defocus distance from a single natural image. A new method for making datasets was proposed, which overcomes the limitations of the sharpness metric itself and improves the overall accuracy of the dataset. Furthermore, a lightweight regression network was built, namely Natural-image Defocus Prediction Model (NDPM), to improve the focusing accuracy. A realistic dataset of sufficient size was made to train all models. The experiment shows NDPM has better focusing performance compared with other models, with a mean focusing error of 0.422µm.