Pu Yan

In view of the existing traditional license plate recognition methods, under the specific condition that the license plate character is complexly altered. It is impossible to distinguish the altered character close to the background color only from the perspective of image processing, thus resulting in misjudgment. We propose a method of altered license plate recognition (LPR) based on active and passive polarization imaging. The proposed method consists of three steps. First, the polarizing image is obtained by natural light irradiation to the polarizing film, and the system we developed can directly recognize the altered license plate through the polarizing image of natural light. Second, the system starts with the construction of active optical polarization imaging. The license plate is polarized by using the LCD light source, which avoids lightless conditions. The active optical polarization imaging system includes two polarizing films to produce polarization images by rotating at different angles. Finally, combining the image segmentation algorithm can recognize the license plate. Compared with the traditional method, the image processing algorithm is combined with the theory of optical polarization from the perspective of image acquisition. The altered LPR system improves the recognition efficiency of the license plate recognition system and avoids misidentification caused by deliberate alteration.

Skin cancer has a high mortality rate, and early detection can greatly reduce patient mortality. Convolutional neural network (CNN) has been widely applied in the field of computer‐aided diagnosis. To improve the ability of convolutional neural networks to accurately classify skin lesions, we propose a multiscale feature fusion model for skin lesion classification. We use a two‐stream network, which are a densely connected network (DenseNet‐121) and improved visual geometry group network (VGG‐16). In the feature fusion module, we construct multireceptive fields to obtain multiscale pathological information and use generalized mean pooling (GeM pooling) to reduce the spatial dimensionality of lesion features. Finally, we built and tested a system with the developed skin lesion classification model. The experiments were performed on the dataset ISIC2018, which can achieve a good classification performance with a test accuracy of 91.24% and macroaverages of 95%.

Person re-identification (ReID) is a crucial task in identifying pedestrians of interest across multiple surveillance camera views. ReID methods in recent years have shown that using global features or part features of the pedestrian is extremely effective, but many models do not have further design models to make more reasonable use of global and part features. A new model is proposed to use global features more rationally and extract more fine-grained part features. Specifically, our model captures global features by using a multi-scale attention global feature extraction module, and we design a new context-based adaptive part feature extraction module to consider continuity between different body parts of pedestrians. In addition, we have added additional enhancement modules to the model to enhance its performance. Experiments show that our model achieves competitive results on the Market1501, Dukemtmc-ReID, and MSMT17 datasets. The ablation experiments demonstrate the effectiveness of each module of our model. The code of our model is available at: https://github.com/davidtqw/Person-Re-Identification.