Skin diseases, a significant category in the medical field, have always been challenging to diagnose and have a high misdiagnosis rate. Deep learning for skin disease classification has considerable value in clinical diagnosis and treatment. This study proposes a skin disease classification model based on multi-scale channel attention. The network architecture of the model consists of three main parts: an input module, four processing blocks, and an output module. Firstly, the model has improved the pyramid segmentation attention module to extract multi-scale features of the image entirely. Secondly, the reverse residual structure is used to replace the residual structure in the backbone network, and the attention module is integrated into the reverse residual structure to achieve better multi-scale feature extraction. Finally, the output module consists of an adaptive average pool and a fully connected layer, which convert the aggregated global features into several categories to generate the final output for the classification task. To verify the performance of the proposed model, this study used two commonly used skin disease datasets, ISIC2019 and HAM10000, for validation. The experimental results showed that the accuracy of this study was 77.6\(\%\) on the ISIC2019 skin disease series dataset and 88.2\(\%\) on the HAM10000 skin disease dataset. External validation data was added for evaluation to validate the model further, and the comprehensive evaluation results proved the effectiveness of the proposed model in this paper.
Human pose estimation (HPE) is a fundamental problem in computer vision, aiming to obtain the spatial coordinates of human joints from images or videos. Despite significant progress, traditional methods often struggle with real-time performance due to their computational complexity. In this paper, we propose a lightweight 3D human pose estimation and visualization system based on the BlazePose+SYS model, which employs an encoding-decoding architecture. Our system can detect human key points and reconstruct 3D human poses in real-time, providing high-precision and real-time solutions for various applications such as action recognition, virtual reality, and sports training. By discarding the heatmap branch during inference, our model achieves lightweight performance suitable for mobile devices and edge computing environments. Experimental results on public datasets demonstrate the effectiveness and accuracy of our system in real-time human pose estimation tasks. This work contributes to advancing the field of HPE by providing a practical and efficient solution.