Chicken carcass defect hyperspectral image detection method based on deep learning

The invention belongs to the field of machine vision hyperspectral image detection, and discloses a deep learning-based chicken carcass defect hyperspectral image detection method, which comprises a hyperspectral data processing module for processing chicken carcass hyperspectral image data; the image processing and data set making module is used for performing image processing on the original image output by the hyperspectral data processing module and making a data set; the target detection module is used for constructing an improved Faster RCNN model for detecting and frame-selecting a chicken carcass defect target; and the semantic segmentation module is used for carrying out defect accurate segmentation on the bounding box image output by the target detection module by using an improved U-net model. According to the method, aiming at the characteristics of the chicken carcass defects, the Faster RCNN model and the U-net model are combined for use, so that the rapidity of the Faster RCNN model and the adv