基于Prewitt算子的苹果分类研究
Research on apple classification based on Prewitt operator
-
摘要: 提出一种简单实用的基于Prewitt算子的苹果分类算法.该算法利用Prewitt算法检测苹果图像的边缘,利用阈值方法对苹果图像进行分割,通过计算连接区域确定苹果是否有损伤.该方法不仅可以精确定位苹果的茎部和损伤部位,而且能够消除苹果图像中的阴影.100个测试样本的实验表明,该算法能够快速地对苹果进行准确分类,准确率可以达到99%.Abstract: A simple and practical apple classification algorithm was proposed.The Prewitt algorithm is employed to detect the edge boundary of the given apple image,and then the threshold segmentation is employed to segment it,whether the apple has scars is determined by calculating connected regions.The experiment results showed that the method not only can exactly locate the scar and stem areas of the apple images,but also can remove the shadow of the apple.The experiment on 100 samples proves that the algorithm can classify the apples quickly and the correct rate can reach 99%.
-
Key words:
- edge extracting /
- Prewitt operator /
- threshold segmentation
-
-
[1]
Zaid Abdullah M,Abdul Aziz S,Dos-Mohamed A M. Quality inspection of bakery products using a color-based machine vision system[J]. J of Food Quality,2000,23(1):39.
-
[2]
Du C J, Sun D W. Learning techniques used in computer vision for food quality evaluation:a review[J]. J of Food Eng,2006,72:39.
-
[3]
陈英.基于计算机视觉的葡萄检测分级系统[J].农业机械学报,2010,41(3):169.
-
[4]
Brosnan T, Sun D W. Inspection and grading of agricultur al and food products by computer vision systems:a review[J]. Comp and Electr in Agr,2002,36:193.
-
[5]
Kavdir I, Guyer D E. Apple sorting using artificial neural networks and spectral imaging[J]. Trans of the ASAE, 2002,45(6):1995.
-
[6]
胡学刚,吴勇.基于轮廓结构元素和阈值分割的形态学去噪[J].计算机工程,2009,35(23):212.
-
[7]
王暄,张小景,马进明.Contourlet域中邻域窗最优阈值滤噪算法[J].计算机工程,2010,36(5):223.
-
[8]
黄敏,姜静.基于多特征自适应阈值检测的关键帧提取[J].郑州轻工业学院学报:自然科学版,2009,24(6):82.
-
[9]
范伟.基于区域生长的彩色图像分割算法[J].计算机工程,2010,36(13):192.
-
[1]
计量
- PDF下载量: 22
- 文章访问数: 733
- 引证文献数: 0