Tobacco leaf vein is an important feature of tobacco, which is of great significance for the analysis of tobacco growth status, variety identification and phenotypic research. This paper provides a leaf vein detection method based on image processing, which is logical, safe, effective, reliable and easy to operate, and can accurately and efficiently detect clear leaf vein images. By analyzing the leaf vein images of tobacco leaves, it helps to scientifically study the structure and growth of tobacco plants of various varieties, as well as the genetic research and identification of tobacco varieties. We use the integral gradient algorithm to extract the leaf region image and combine with the adaptive threshold segmentation algorithm to obtain the final leaf vein segmentation results. The experimental results show that this method has good performance in leaf vein segmentation of tobacco leaf.