The invention belongs to the technical field of image segmentation, and particularly relates to an image segmentation method based on a secondary confinement region growth method, which comprises thefollowing steps: step 1, converting an image from an RGB space into a Lab space; step 2, setting the number of seed points and a threshold value, throwing the seed points, and marking the image by using a limited area growth method and the threshold value; step 3, traversing the whole image according to a grating scanning sequence to carry out secondary limited region growth, and marking each unmarked point; step 4, calculating a mean value of wave bands of the superpixel blocks divided in the last two steps; And step 5, setting a predicted classification number, and combining the superpixel results obtained in the step 3 by using a simulated annealing algorithm based on a hidden Markov model, an Isinuous model and a Gaussian function to obtain a final segmentation result. According to theimage segmentation method disclosed by the invention, a region growth limiting method is used, so that each seed point performs region growth in an image range of the step size multiplied by the stepsize, the calculation workload is reduced, and the operation speed is increased.