Extracting character information from complex images has always been a research hotspot and a difficult topic in thefield of computer vision. Natural scene number is severely distorted due to blurred image, uneven illumination, weakillumination, which makes it difficult to achieve ideal results for character recognition, especially identifying charactersof arbitrary length. In this paper, we use the convolutional network to automatically extract the advantages of features,and construct a convolutional neural network that recognizes single digits. In order to highlight important features, wealso use grayscale methods to weaken the background information in natural scenes and apply certain ProportionalDropout strategy to prevent overfitting. We use a cyclic network to generate character sequences and construct a deepconvolutional neural network that recognizes sequence numbers and without split character characters. We construct adeep convolutional neural network that uses convolutional networks and cyclic network fusion to simultaneouslyidentify multiple digits. We verify on the SVHN data set, we achieve better results in accuracy, we get the recognitionrate of single digital house number is 95.72%, better than most algorithms in existing articles and the recognition rate ofserial digital house number is 89.14%.
展开▼