Computer vision researchers have been expecting that neural networks have spatial transformation ability to eliminate the interference caused by geometric distortion for a long time. Emergence of spatial transformer network makes dream come true. Spatial transformer network and its variants can handle global displacement well, but lack the ability to deal with local spatial variance. Hence how to achieve a better manner of deformation in the neural network has become a pressing matter of the moment. To address this issue, we analyze the advantages and disadvantages of approximation theory and optical flow theory, then we combine them to propose a novel way to achieve image deformation and implement it with a hierarchical convolutional neural network. This new approach solves for a linear deformation along with an optical flow field to model image deformation. In the experiments of cluttered MNIST handwritten digits classification and image plane alignment, our method outperforms baseline methods by a large margin.
Classical rough sets method makes knowledge absence in the key domain and affects the comprehensiveness of the index system after simplification, so an improved variable precision rough sets weighting model is proposed on the basis of variable precision rough sets theory. In the model, attributes are divided into first-class core attributes and second-class attributes, and core attributes are still calculated by the importance of the attributes in rough sets theory. The importance of second-class attribute is μ times of the core attributes’ minimum importance degree. Then normalize the importance degrees and convert them to weights. In the evaluation of the health of sound living environment, the model we proposed has lower error rates compared to other methods and the evaluation results demonstrate to be valid.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.