Segmentation of natural scenes

作者:

Highlights:

摘要

A new simple and computationally efficient approach to image segmentation via recursive region splitting and merging is presented. Unlike other techniques the criterion for splitting is based on a generalization of a two-class gradient relaxation method and merging uses a test for mean gray level equivalency for adjacent regions. The technique is illustrated by providing results for both synthetic and natural scenes.

论文关键词:Image understanding,Multiclass images,Outdoor natural scenes,Relaxation,Image segmentation,Split and merge,Thresholding

论文评审过程:Received 26 November 1985, Revised 5 February 1987, Available online 19 May 2003.

论文官网地址:https://doi.org/10.1016/0031-3203(87)90076-8