棉花苗叶片复杂背景图像的联合分割算法-计算机辅助设计与图形学学报.pdf

29 10 Vol.29 No.10 2017 10 Journal of Computer-Aided Design Computer Graphics Oct. 2017 棉花苗叶片复杂背景图像的联合分割算法 1,2) 1)* 2) 李 凯 , 冯 全 , 张建华 1) (甘肃农业大学机电工程学院 兰州 730070) 2) ( 中国农业科学院农业信息研究所 北京 100081) (fquan@) : 为了实现自然光条件下棉花叶片的自动、普适和精确分割, 提出一种基于马尔可夫随机场最优化模型的联 合分割算法. 首先用非监督的共同显著性检测算法为一组棉花苗叶片图像中每幅图像生成共同显著性图, 这些显著 性图被用来构造马尔科夫随机场中的内部图像能量函数; 然后采用混合高斯模型对该组图像全部显著性图的共同目 标(叶片)与单幅图像中叶片的差异进行建模, 将其作为马尔可夫随机场最优化模型的一个新的全局约束去构造全局 能量项; 最后通过标准图割算法(Grabcut)和迭代使得能量函数最小化, 以实现对棉花苗叶片图像的分割. 按不同天 气条件和不同背景拍摄 600 幅棉花苗叶片图像构建了数据库, 在该库上的实验结果表明, 该算法对于晴天、阴天和雨 后图像中目标的平均正确分割率达到 84.8%, 87.7%和91.6%, 比经典的Grabcut 分别提高了 10.7%, 3%和 10%. : 棉花苗叶片; 马尔可夫随机场; 显著性检测; 图像分割 : TP391.41 Co-Segmentation Algorithm for Complex Background Image of Cotton Seedling Leaves Li Kai1,2), Feng Quan1)*, and Zhang Jianhua2) 1) (Mechanical and Electrical Engineering College, Gansu Agricultural University, Lanzhou 730070) 2) (Institute of Agricultural Information, Chinese Academy of Agricultural Sciences, Beijing 100081) Abstract: In order to realize the automatic, universal and accurate image segmentation of the cotton leaves under the natural lighting condition, a co-segmentation algorithm was put forward based on the optimization model of Markov random field. We made use of a co-saliency detection algorithm, which was unsupervised, to generate the co-saliency map for each blade in an set including multiple images of cotton seedling leaves. These maps were used to construct an interior energy function over Markov random field since the co-saliency was able to highligh