Crop leaf segmentation was one important research content in agricultural machine vision applications. In order to study and solve the segmentation problem of occlusive leaves, an improved watershed algorithm was proposed in this paper. Firstly, the color threshold component (G−R)/(G+R) was used to extract the green component of the cotton leaf image and remove the shadow and invalid background. Then the lifting wavelet algorithm and Canny operator were applied to extract the edge of the pre-processed image to extract cotton leaf region and enhance the leaf edge. Finally, the image of the leaf was labeled with morphological methods to improve the traditional watershed algorithm. By comparing the cotton leaf area segmented using the proposed algorithm with the manually extracted cotton leaf area, successful rates for all the images were higher than 97 %. The results not only demonstrated the effectiveness of the algorithm, but also laid the foundation for the construction of cotton growth monitoring system.