华南理工大学学报（自然科学版）
華南理工大學學報（自然科學版）
화남리공대학학보（자연과학판）
JOURNAL OF SOUTH CHINA UNIVERSITY OF TECHNOLOGY(NATURAL SCIENCE EDITION)
2010年
2期
132-136,148
,共6页
拐点检测%弯曲度%图像拐点%曲率
枴點檢測%彎麯度%圖像枴點%麯率
괴점검측%만곡도%도상괴점%곡솔
corner detection%bending degree%image corner%curvature
针对拐点处与非拐点处的弯曲度值差别小的问题,文中提出了一种基于双重弯曲度积的图像拐点检测算法,通过第一重弯曲度与第二重弯曲度的乘积扩大拐点处与非拐点处的弯曲度值的差别,并对数字图像进行拐点检测实验.结果表明,该算法不仅简单有效,而且具有较高的稳定性和准确性,能够解决实际的图像拐点检测问题.
針對枴點處與非枴點處的彎麯度值差彆小的問題,文中提齣瞭一種基于雙重彎麯度積的圖像枴點檢測算法,通過第一重彎麯度與第二重彎麯度的乘積擴大枴點處與非枴點處的彎麯度值的差彆,併對數字圖像進行枴點檢測實驗.結果錶明,該算法不僅簡單有效,而且具有較高的穩定性和準確性,能夠解決實際的圖像枴點檢測問題.
침대괴점처여비괴점처적만곡도치차별소적문제,문중제출료일충기우쌍중만곡도적적도상괴점검측산법,통과제일중만곡도여제이중만곡도적승적확대괴점처여비괴점처적만곡도치적차별,병대수자도상진행괴점검측실험.결과표명,해산법불부간단유효,이차구유교고적은정성화준학성,능구해결실제적도상괴점검측문제.
As the difference in bending degree between corner points and non-corner points is not large enough for image detection, an algorithm of image corner detection based on the product of two bending degrees is proposed. The proposed algorithm enlarges the differences in bending degree by multiplying the first bending degree and the second bending degree. Then, the corner detection for digital images is conducted. Experimental results show that the proposed algorithm is simple and effective, and that it helps to detect image corners with good stability and high precision.
