基于自适应Canny算子的柑橘边缘检测

Orange edge detection based on adaptive Canny operator

针对传统的Canny算子进行柑橘边缘检测存在假边缘的同时还会丢失灰度值变化缓慢的局部边缘问题,该文根据柑橘图像边缘梯度特征信息,提出了利用信息熵来自适应确定Canny算子的高、低阈值。试验结果表明:自适应Canny算子比传统的边缘检测方法得到的边缘连通性好,定位精度高,抗噪性能强,同时该方法提高了柑橘边缘检测的自动化程度。

To overcome the problems of detecting the false edge as well as losing local edge with slow variation of grey value while detecting the orange edge with traditional Canny operator, a new method is proposed in this paper to adaptively determine the high and low thresholds of Canny operator using information entropy by the edge gradient feature of the orange image. Experimental results show that, the obtained edge by using the adaptive Canny operator has good connectivity, high positioning precision and strong anti-noise capability compared with traditional edge detecting methods. Furthermore, this method improves the automatic degree of the orange edge detection.