作者: Božidar Potočnik , Damjan Zazula
DOI: 10.1016/S0262-8856(01)00096-8
关键词:
摘要: Abstract An improved algorithm is presented for ovarian follicle detection in ultrasound images. This fully automated recognition composed of three successive steps. First, initial homogeneous regions are determined. Then, these grown. The growing controlled by average grey-level and a newly introduced weighted image gradient. In the last stage, those extracted that probably correspond to follicles. has been tested on 50 rate follicles using this procedure was around 78%. A possible extension deals with entire information sequence, which covered Part II paper.