Abstract
In this letter, a segment algorithm based on color feature of images is proposed. The algorithm separates the weed area from soil background according to the color eigenvalue, which is obtained by analyzing the color difference between the weeds and background in three color spaces RGB, rgb and HSI. The results of the experiment show that it can get notable effect in segmentation according to the color feature, and the possibility of successful segmentation is 87%–93%. This method can also be widely used in other fields which are complicated in the background of the image and facilely influenced in illumination, such as weed identification, tree species discrimination, fruit picking and so on.
Similar content being viewed by others
References
George E. Meyer, Joao Camargo Neto, David D. Jones. Intensified fuzzy clusters for classifying plant soil and residue regions of interest from color images. Computers and Electronics in Agriculture. 42(2004)1, 161–180.
D. M. Woebbecke, G. E. Meyer, Von Bargen, et al. Color indices for weed identification under various soil, residue and lighting conditions. Transactions of the ASAE, 38(1995)1, 259–269.
L. Tang, L. Tian, B. L. Steward. Color image segmentation with genetic algorithm for in-field weed sensing. Transactions of the ASAE, 43(2000)4, 1019–1027.
C. C. Yang, S. O. Prasher. Development of neural networks for weed recognition in corn fields. Transactions of the ASAE. 45(2002)3, 859–864.
B. L. Steward, L. F. Tian. Machine-vision weed density estimation for real-time, outdoor lighting conditions. Transactions of the ASAE, 42(1999)6, 1897–1910.
Tao Linmi, Xu Guangyou. Color research and application in computer vision. Chinese Science Bulletion, 46(2001)3, 178–190, (in Chinese). 陶霖密,徐光祐. 机器视觉中的颜色问题及应用. 科学通报, 46(2001)3, 178–190.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Liu, Y., Yang, F., Yang, R. et al. Research on segmentation of weed images based on computer vision. J. of Electron.(China) 24, 285–288 (2007). https://doi.org/10.1007/s11767-006-0151-0
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11767-006-0151-0