基于掩模及亮度校正算法的脐橙表面缺陷分割

张明,李鹏,邓烈,何绍兰,易时来,郑永强,谢让金,马岩岩,吕强

Segmentation of Navel Orange Surface Defects Based on Mask and Brightness Correction Algorithm

ZHANG Ming,LI Peng,DENG Lie,HE ShaoLan,YI ShiLai,ZHENG YongQiang,XIE RangJin,MA YanYan,LÜ Qiang

表2 基于多尺度高斯函数图像亮度校正算法的单阈值缺陷分割结果

Table 2 Single threshold defect segmentation result based on multi-scale Gaussian function image brightness correction algorithm

表皮类型 Epidermis type 样本数 Number of samples 分割结果 Segmentation result 识别率 Recognition rate (%) 正常果 Normal fruit 65 58 89.2 溃疡果 Canker fruit 49 45 91.8 蓟马果 Thrips fruit 48 43 89.6 油斑病果 Oil spotting fruit 35 31 88.6 黑斑病果 Blackspot fruit 76 74 97.4 风伤果 Wind damage fruit 61 54 88.5 炭疽病果 Anthracnose fruit 66 66 100.0 合计 Total 400 371 92.7