A segmentation method of red apple image

Apple image segmentation based on convex hull center priori and Markov adsorption chain is proposed in this paper. First, the convex hull, containing Harris points of interest, is approximated as a significant target area. Significant measurements were performed using convex hull center priori to obtain a preliminary saliency map with binary segmentation. Foreground points in the salient region were selected as absorbing nodes for an adsorbing Markov chain, and the remaining points were transfer nodes for an absorbing Markov chain, thus strengthening the salient regions by constructing a Markov chain. An ideal saliency map was obtained by optimization. Finally, a threshold obtained using the Otsu algorithm was used for adaptive apple image segmentation of the salient region. A comparison of different algorithms shows that the method has some advantages in terms of performance and efficiency.