Aiming to address the issue of low efficiency and a high false-detection rate in artificial defect detection in nitrile medical gloves, CCA-YOLO was proposed on the basis of YOLOv5 to realize the detection of tear and scratch defects. CCA-YOLO added a small-target detection layer to the YOLOv5 network backbone and further proposed an innovative channel coordinate attention mechanism. According to the different characteristics of tears and scratches, focal and efficient IoU loss and α-IoU loss functions were introduced to further improve the positioning accuracy. The data enhancement method was used to generate a dataset of nitrile gloves, which was divided into datasets for horizontal angular tear detection, vertical angular tear detection, and scratch detection. The problem of class imbalance with few defect samples was solved. Our experiments show that CCA-YOLO can effectively identify tear and scratch defects in nitrile medical gloves in the self-made datasets. Compared with YOLOv5, the mean average precision (mAP) of the three models for horizontal angular tear detection, vertical angular tear detection, and scratch detection can reach 99.3%, 99.8%, and 99.6%, showing increments of 4.2%, 5.3%, and 12.4%, respectively, thereby meeting the performance requirements of glove defect detection.