The invention discloses a method for detecting characters in a complex natural scene image, belongs to the field of computer vision and pattern recognition, and relates to the technical field of neural networks and computer vision, in particular to a method for realizing character detection in a complex scene based on deep learning. The character detection method based on character annotation andthe character detection method based on word annotation are fused, the combined characteristics between characters are learned, the false detection rate of the characters can be reduced, the redundancy of a detection box is reduced, and the method has the capacity of flexibly coping with the characters of any shape. The invention discloses a character detection method in a complex scene. The method comprises the following steps: preprocessing image data, constructing a network framework, pre-training a model, and training the network framework; and generating the character real label, inputting a character image to be detected in a natural scene, carrying out feature extraction, carrying out image judgment and using a character correction module.