摘要
准确检测并分离甜瓜瓜蒂,对于基于计算机图像处理的甜瓜品质分级系统具有重要意义。提出了一种基于角点检测的瓜蒂检测和分离方法,该方法利用瓜蒂区域和甜瓜其他部分角点分布差异较大特点,准确地找到并擦除瓜蒂,算法对瓜蒂形状、长短、粗细不敏感,有较好的适应性。与多种已知瓜蒂检测算法的对比实验表明,算法具有很高的识别率和较小的耗时。
Accurate detection and segmentation of the pedicels are important tasks in a melon quality-rating system which is based on image processing.A novel method is presented to detect pedicels in a melon images using corner detection.The statistics show that most corners of the melon image distributes around pedicel.Utilizing this feature,the pedicel can exactly be detected and erased.The proposed method is not sensitive to variations of pedicel's shape,length and thickness,and it is robust.The experimental results show that,compared with the several existing approaches,the accuracy of the proposed method is improved and the computational overload is reduced.
出处
《计算机工程与应用》
CSCD
北大核心
2011年第22期188-190,194,共4页
Computer Engineering and Applications
基金
国家自然科学基金No.61062012~~
关键词
图像处理
甜瓜瓜蒂
角点检测
image processing
melon pedicel
corner detection