基于颜色信息的水稻稻曲病图像分割算法研究

RESEARCH ON IMAGE SEGMENTATION ALGORITHM BASED ON COLOR INFORMATION OF RICE FALSE SMUT

提出一种从颜色空间进行稻曲病图像的稻曲球分割算法,通过研究稻曲病图像颜色空间的各颜色分量对应坐标值的比值,分析颜色分量的色差模型,找到稻曲球、稻穗和叶片之间颜色信息的不同分布区域,采用动态阈值法有效分割稻曲球。图像分割实验结果表明所提算法的有效性,为后续进一步研究稻曲病的图像特征提取与图像识别等提供研究基础。

We propose a novel algorithm of chiamydospore segmentation based on color space of rice false smut color image.Due to discussing the mutual coordinate values of three color components about rice false smut color image,and analyzing the color difference mode of color components,the different distribution region of chiamydospore,ear of rice and the rice leaves will be found.Then chiamydospore can be correctly segmented through the dynamic threshold.The results of segmentation experiment show that the proposed method is effective,which can provide the research basic for further studying on image feature extraction and pattern recognition of rice false smut.