基于GVF模型的蔬果图像快速分割方法

在结合贪婪算法的基础上,利用一种改进的梯度矢量流（GVF）算法,提出了一种对各种蔬果图像进行轮廓提取的新算法。试验表明,该方法在保持GVF模型原有特性的基础上大大提高了模型收敛的速度,且较好地限制了非目标边缘和噪声干扰的影响,能够满足果蔬采摘机器人对视觉系统的精度和实时性要求。

A Fast Segmentation Method for the Fruit and Vegetable Image Segmentation Based on the GVF model

Based on the greedy search algorithm,the improved fast gradient vector flow is introduced to present a fast active contour model for the fruit and vegetable image segmentation.A new algorithm of contour extraction to each kind of fruit and vegetable images was put forward.Experiments proved that the new model show fast speed on the basis of keeping the characteristic of GVF model,limiting the influence of false edge and noise disturbance,and meeting the accuracy and real-time requirements of the automatic r...