基于分水岭范式的图像分割算法
项目描述
请参阅模块 API 页面
https://engineering.purdue.edu/kak/distWatershed/Watershed-2.2.2.html
获取与此模块相关的所有信息，包括与代码的最新更改相关的信息。上面显示的 URL 中的页面列出了您可以在自己的代码中调用的所有模块功能。该页面还介绍了如何在自己的代码中直接访问分段的 blob，以及如何在图像分段之前将滤色器应用于图像。
关于模块的基本用途，它是用于图像分割的分水岭算法的 Python 实现。此实现允许对图像进行全自动和标记辅助分割。
典型使用语法：
from Watershed import *
shed = Watershed(
data_image = "orchid0001.jpg",
binary_or_gray_or_color = "color",
size_for_calculations = 128,
sigma = 1,
gradient_threshold_as_fraction = 0.1,
level_decimation_factor = 16,
padding = 20,
)
shed.extract_data_pixels()
shed.display_data_image()
shed.mark_image_regions_for_gradient_mods() #(A)
shed.compute_gradient_image()
shed.modify_gradients_with_marker_minima() #(B)
shed.compute_Z_level_sets_for_gradient_image()
shed.propagate_influence_zones_from_bottom_to_top_of_Z_levels()
shed.display_watershed()
shed.display_watershed_in_color()
shed.extract_watershed_contours_seperated()
shed.display_watershed_contours_in_color()
The statements in lines (A) and (B) are needed only for marker-assisted
segmentation with the module. For a fully automated implemented of the
BLM algorithm, you would need to delete those two statements.
