摘要
为了解决目前杂草识别中受光照影响大、环境适应性差等问题,提出了基于颜色特征的分割算法。此算法在统计分析杂草和土壤背景各颜色因子的基础上,得到适于杂草图像分割的颜色分量,实现了复杂场景、光照条件下杂草区和背景区的分割。实验结果表明:R-G,2G-R-B,Hmean,Smean,Hmean+Smean颜色特征对于杂草区和背景区的分割能够取得很好的效果,可广泛应用于田间杂草识别、树种识别、人脸识别等受光照变化影响较大的领域。
In order to solve the problem of illumination infection and adaptability of environment in weed identification at present, a segment algorithm based on color feature is presented in this paper. The algorithm separates the weed area from soil background according to the color eigenvalue, which is got by analyzing the color difference between weeds and background. The results of the experiment show that 2G-R-B,R-G, Hmean, Smean and Hmean＋Smean can get notable effect in segmentation. It can be wildly used in the fields which are facilely influenced in lighting conditions, such as tree species discrimination, face recognition and so on.
出处
《微计算机信息》
北大核心
2007年第18期269-271,共3页
Control & Automation
基金
黑龙江省自然科学基金资助课题(F01-04)
关键词
杂草图像
颜色特征
复杂光照
图像分割
weed images, color feature, complex lighting conditions, segment
