计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (33): 192-194.

• 图形、图像、模式识别 • 上一篇    下一篇

基于H分量旋转的荔枝图像分割算法

毛 亮,薛月菊,孔德运,刘国瑛,卢启福,王 楷   

  1. 华南农业大学 工程学院,南方农业机械与装备关键技术省部共建教育部重点实验室,广州 510642
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-21 发布日期:2011-11-21

Litchi image segmentation algorithm based on rotation of hue component of HSV color space

MAO Liang,XUE Yueju,KONG Deyun,LIU Guoying,LU Qifu,WANG Kai   

  1. Key Lab of Key Technology on Agricultural Machine and Equipment Ministry of Education,College of Engineering,South China Agricultural University,Guangzhou 510642,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-21 Published:2011-11-21

摘要: 自然场景下荔枝图像分割,因果实与背景之间的颜色特征以及本身的形状特性的差异,表面会出现亮度不均匀,对分割造成非常大的影响。为了减少亮度不均匀给荔枝图像分割带来的影响,选择HSV彩色空间中色调H分量,并对H分量进行旋转作为图像分割的特征;通过模糊聚类算法和马氏空间约束条件来进行图像分割,利用形态学滤波消除分割后的随机噪声,并对分割区域标记,利用图像标记来恢复分割区域的原始图像。结果表明,该算法能很好地解决亮度不均匀造成的影响,对成熟荔枝分割的正确率达到了90.4%。

关键词: 荔枝, HSV彩色空间, 图像分割, 模糊聚类, 马氏空间约束

Abstract: Due to the diversity of the color feature difference between fruit and background and shape feature difference,the surface of Litchi appears uneven illumination that strongly influences litchi image segmentation under natural scene.To reduce influences resulted from uneven illumination,hue component of HSV color space is selected,and the rotation of hue is used as the feature for image segmentation.Fuzzy clustering algorithm and Markov spatial constraint conditions are utilized to segment litchi image under natural scene.Morphological filtering is used to eliminate the random noise and the segmentation regions are labeled.The label image can restore the original image of the segmented regions.The result shows that the proposed algorithm can overcome the influence of uneven illumination on litchi image segmentation,and the correct segmentation rate is up to 90.4%.

Key words: litchi, HSV color space, image segmentation, fuzzy clustering, Markov spatial constraint