Collecting information on the flotation foam characteristics is important for controlling flotation production conditions. Foam images acquired during coal slurry flotation are affected by factors such as ambient lighting, contributing to uneven grayscale images with low brightness and contrast. Brightness enhancement of foam images is often required when using network models to extract feature information from the images. The paper proposes a foam image brightness enhancement algorithm based on a multiscale convolutional neural network. The method employs a skip connection structure based on a summation connection design based on logarithmic functions and introduces a loss function based on logarithmic transformation in the network. At the same time, branching networks of different complexity are designed in the network to further help alleviate the gradient vanishing problem. The experimental results show that when evaluating the quality of images after brightness enhancement of foam images and the public dataset MIT, the numerical results of using the proposed skip connection structure in the proposed network are overall better than using the resblock structure, and the proposed loss function is better than is better than using the L2 loss function. The proposed network greatly improves the visual effect of flotation foam images and lays the foundation for feature extraction of flotation foam images and intelligent flotation production.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Manual delineation of tumours in breast histopathology images is generally time-consuming and laborious. Computer-aided detection systems can assist pathologists by detecting abnormalities faster and more efficiently. Convolutional Neural Networks (CNN) and transfer learning have shown good results in breast cancer classification. Most of the existing research works employed State-of-the-art pre-trained architectures for classification. But the performance of these methods needs to be improved in the context of effective feature learning and refinement. In this work, we propose an ensemble of two CNN architectures integrated with Channel and Spatial attention. Features from the histopathology images are extracted parallelly by two powerful custom deep architectures namely, CSAResnet and DAMCNN. Finally, ensemble learning is employed for further performance improvement. The proposed framework was able to achieve a classification accuracy of 99.55% on the BreakHis dataset.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.