We have seen that segmentation consists of dividing an image into several homogeneous regions. The homogeneity of a region is based on color, texture, contours, etc.
The methods for segmentation are very diverse, and we have only seen a few of them. Other existing methods include active contours (also known as snakes), level sets, Markovian models, etc. In addition to these “model-based” methods, deep learning methods obtained significant increases in the results.
At last, we list some criteria used to evaluate the quality of a segmentation method. These criteria are useful to comparing different segmentation methods.