The expanding market demand and high commercial value of Citri Reticulatae Pericarpium (CRP) have led to frequent counterfeiting. Rapid and non‐destructive identification of counterfeit CRP is therefore essential. This study proposes a novel detection model that integrates visible/near‐infrared (Vis/NIR) spectroscopy with deep learning algorithms. Authentic CRP and four types of counterfeit CRP samples were collected, and their multispectral Vis/NIR data were acquired. Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN‐GP) data augmentation enhanced model generalization, further improving classification robustness. After spectral preprocessing, deep learning models were applied to classify and detect different CRP types, aiming to identify the optimal network for counterfeit discrimination. The experimental results demonstrated that the Inception‐ResNet model achieved the test set accuracy of 96.56% in identifying authentic CRP from four counterfeit categories, outperforming conventional machine learning approaches. This study provides a precise and efficient model for non‐destructive authentication and adulteration analysis of CRP.

In multispectral imaging systems incorporating multiple illumination sources, conventional autofocus algorithms often suffer from poor efficiency and are prone to becoming trapped in local extrema. To address these challenges, we introduce a hybrid coarse-to-fine focus search algorithm enhanced by the Pearson correlation coefficient (PCHC-FocusSearch). The proposed algorithm integrates the global search algorithm with hill-climbing, leveraging Pearson correlation coefficients to identify the optimal sequence of wavelength channels for precise focus. An experimental platform featuring programmable LED arrays, an industrial camera, and a motorized zoom lens was assembled to quantify spectral correlations and validate the algorithm’s performance. Compared to golden section search, Fibonacci search, and the HC-FocusSearch variant, PCHC-FocusSearch reduces the average number of focus steps by 40%. It also decreases total focusing time by 45% and consistently converges to the true focal plane across all spectral bands. The results show that the algorithm accelerates the autofocus process while maintaining high accuracy under complex and variable illumination conditions. Consequently, it provides a robust solution for real-time multispectral imaging applications.

Aiming at the problems of a large number of network parameters and high computational complexity of human key point detection models in the fields of human-machine collaboration and action recognition, a lightweight human key point detection model was proposed. First, we fine-tune MobileNetV3 as the backbone network to reduce the overall parameter amount of the model; Second, we propose a Feature Pyramid Network (FPN) and an adaptive upsampling module to improve the model detection accuracy with the introduction of a small number of parameters; Third, we combine the joint length information loss function with the MSE loss function to accelerate the convergence of the model during training to improve the prediction accuracy. Ablation experiments verified the effectiveness of each module. The experimental results on the COCO2017 dataset showed that the average accuracy of the algorithm proposed in this paper is 68.6%, the number of model parameters is 2.2M, the computational complexity is 1.8G, and the inference speed on a single CPU platform reaches 36 frames/s, meeting the real-time requirements.

The use of inexpensive black and white cameras in conjunction with multi-band lighting offers the highest accuracy and cost benefits among the several techniques for accomplishing multispectral images. The focus point shifts with varied wavelength illumination, since the lens optical glass has varying refractive indices for different wavelength light sources. Thus, quick and precise focusing is essential for enhancing system efficiency as a whole. To solve this problem, this study proposes a multispectral quick focusing method. First, analyzes the current methods for evaluating image sharpness and proposes an improved Tenengrad function for the focused scene that could extract gradient information from the image in several directions and improve sharpness evaluation. The improved gradient extraction method combines the Scale Invariant Feature Transformation (SIFT) algorithm to form a new multi-scale image sharpness evaluation function, SIFT Quad-Tenen. To improve the focusing efficiency and optimize the focusing process, a search strategy combining a climbing search algorithm and a traversal method was proposed. Finally, considering the similarity of images between different wavelength bands under multi-light source conditions, the Pearson correlation coefficient is introduced to improve the focusing speed and accuracy. The experimental results demonstrate the superiority of the SIFT Quad-Tenen evaluation function in terms of stability and sensitivity, as well as the significant improvement of the focusing speed and accuracy of the Pearson-Hill climbing algorithm.