Receptive Field Based Image Modeling Method for Interactive Segmentation
Bin Yang, Qiyang Zhao, Rui Zhang, Baolin Yin · 2009
In current interactive segmentation algorithms, image models are constructed and simplified to be independent of spatial features of images. This conflicts with receptive field hypothesis of human vision systems, and causes oversegmentation and under-segmentation. Based on receptive field hypothesis, the paper establishes an image modeling method in which spatial distances are taken into account, and a conservative factor is introduced into the image energy function to improve the segmentation veracity. It is shown by experiments that the method is more accurate than its counterparts.