Yongsheng Zhang

For surveillance video management in university laboratories, issues such as occlusion and low-resolution face capture often arise. Traditional face recognition algorithms are typically static and rely heavily on clear images, resulting in inaccurate recognition for low-resolution, small-sized faces. To address the challenges of occlusion and low-resolution person identification, this paper proposes a new face recognition framework by reconstructing Retinaface-Resnet and combining it with Quality-Adaptive Margin (adaface). Currently, although there are many target detection algorithms, they all require a large amount of data for training. However, datasets for low-resolution face detection are scarce, leading to poor detection performance of the models. This paper aims to solve Retinaface’s weak face recognition capability in low-resolution scenarios and its potential inaccuracies in face bounding box localization when faces are at extreme angles or partially occluded. To this end, Spatial Depth-wise Separable Convolutions are introduced. Retinaface-Resnet is designed for face detection and localization, while adaface is employed to address low-resolution face recognition by using feature norm approximation to estimate image quality and applying an adaptive margin function. Additionally, a multi-object tracking algorithm is used to solve the problem of moving occlusion. Experimental results demonstrate significant improvements, achieving an accuracy of 96.12% on the WiderFace dataset and a recognition accuracy of 84.36% in practical laboratory applications.

To solve the problem that existing dehazing algorithms have difficulty in capturing paired hazy and clear images in the real world, while unpaired real-world hazy and clear images are readily obtained. In this study, unpaired real-world hazy and clear images are used to realize unsupervised dehazing. Inspired by the Generative Adversarial Network framework, the generator network combines multi-scale dense blocks and attention mechanism and uses adaptive blending operation to speed up network training while ensuring effective delivery of image details. By incorporating contrast learning, a weighted contrastive loss function is introduced, which encourages the recovered image to be close to positive samples and away from negative samples in the embedding space. Meanwhile, multiple loss functions are combined to enhance the generalization ability of the generative adversarial network in order to train the network more effectively. The proposed algorithm is tested on an outdoor public dataset, and the experimental results show that the algorithm has better performance than existing unsupervised dehazing algorithms.