Image multi-task feature extraction and classification system based on deep learning

The invention discloses an image multi-task feature extraction and classification system based on deep learning. The system comprises an image preprocessing module, a general feature extraction module, a specific task feature extraction module and a classification module. The image preprocessing module is used for preprocessing a to-be-recognized medical image; the general feature extraction module is used for extracting general features; the specific task feature extraction module is used for extracting specific features; and the classification module is used for classifying the to-be-identified image according to the general features and the specific features. The design of the invention is a general framework, and supports wide image analysis tasks, such as image type identification, abnormal region detection in images, automatic evaluation of image features and the like, so that knowledge sharing and performance improvement in different tasks are realized. 本发明公开了一种基于深度学习的图像多任务特征提取及分类系统，包括：图像预处理模块、通用特征提取模块