In this paper, an advanced YOLOv7 model is proposed to tackle the challenges associated with ship detection and recognition tasks, such as the irregular shapes and varying sizes of ships. The improved model replaces the fixed anchor boxes utilized in conventional YOLOv7 models with a set of more suitable anchor boxes specifically designed based on the size distribution of ships in the dataset. This paper also introduces a novel multi-scale feature fusion module, which comprises Path Aggregation Network (PAN) modules, enabling the efficient capture of ship features across different scales. Furthermore, data preprocessing is enhanced through the application of data augmentation techniques, including random rotation, scaling, and cropping, which serve to bolster data diversity and robustness. The distribution of positive and negative samples in the dataset is balanced using random sampling, ensuring a more accurate representation of real-world scenarios. Comprehensive experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches in terms of both detection accuracy and robustness, highlighting the potential of the improved YOLOv7 model for practical applications in the maritime domain.

Breast cancer has become the most common cancer in the world, and biopsy is the most reliable and widely used technique for detecting breast cancer. However, observation of histopathological images is time-consuming and labor-intensive. Currently, CNN has become the mainstream method for breast cancer histopathological image classification research. However, some studies have found that the optical microscope-generated histopathological images have noise, and the output of a well-trained convolutional neural network in image classification tasks can change drastically due to small variations in the input. Therefore, the quality of the image significantly affects the accuracy of the classification. Wavelet transform is a commonly used denoising method, but the selection of the threshold is a difficult problem, and traditional methods are difficult to find the appropriate threshold quickly and accurately. This paper proposes an adaptive threshold selection method that combines threshold selection steps with deep learning methods by using the threshold as a parameter in the CNN model to train. In this way, we associate the threshold with the classification result of the model and find the appropriate value for that image and task by back-propagation in training. The method was experimented on publicly available datasets BreaKHis and BACH. The results in BreaKHis (40x: 94.37, 100x: 93.85, 200x: 91.63, 400x: 93.31), and BACH (91.25) demonstrate that our adaptive threshold selection method can improve classification accuracy and is significantly superior to traditional threshold selection methods.