Document Type : Original Article
Abstract
Variations in lighting are a problem for visual systems. In the current research, a new thresholding method using a 3D Euclidian elliptical surface was defined and applied for plant detection purposes. The results showed that this method had lower type I error, type II error, total error and mean square error compared with those of conventional segmentation methods. The method was evaluated for detection of cabbage and lettuce from images. The results showed the proposed method located cabbages in the images with 85.26% accuracy. When the proposed method was combined with image-based shape features it identified lettuce from the images at 66.67% accuracy.
Keywords
Ahmed, F., Kabir, H., Bhuyan, S. A., Bari, H. and Hossain, E. 2012. Automated weed classification with local pattern-based texture descriptors. Int. Arab J. Info. Technol. 11(1): 87-94.
Blasco, J., Aleixos, N., Roger, J., Rabatel, G. and Molto, E. 2002. Robotic weed control using machine vision. Biosys. Eng. 83, 149-157.
Camargo, A. and Smith, J. 2009. Image pattern classification for the identification of disease causing agents in plants. Comput. Electron. Agr. 66, 121-125.
Cope, J. S., Corney, D., Clark, J. Y., Remagnino, P. and Wilkin, P. 2012. Plant species identification using digital morphometrics: a review. Expert Syst. Appl. 39, 7562-7573.
Golzarian, M. R., Fielke, J. and Desbiolles, J. 2007. A novel approach to improve the plant-background segmentation in computer vision systems. National Conference: Agriculture and Engineering: Challenge Today, Technology Tomorrow. Society for Engineering in Agriculture. Australian Society of Engineering in Agriculture.Canberra. Australia.
Golzarian, M., Lee, M. K. and Desbiolles, J. 2012. Evaluation of color indices for improved segmentation of plant images. Trans. ASABE. 55, 261-273.
Gonzalez, R. C. and Richard, E. W. 2008. Digital Image Processing. 2nd Ed. Adison-Wesley, Reading.
Guo, W., Rage, U. K. and Ninomiya, S. 2013. Illumination invariant segmentation of vegetation for time series wheat images based on decision tree model. Comput. Electron. Agr. 96, 58-66.
Kargar, B., Amir, H. and Shirzadifar, A. M. 2013. Automatic weed detection system and smart herbicide sprayer robot for corn fields. First RSI/ISM International Conference on Robotics and Mechatronics. Feb. 13-15. Tehran. Iran.
Kheng, L. W. 2002. Color spaces and color-difference equations. Color Res. Appl. 24, 186-198.
Khojastehnazhand, M., Omid, M. and Tabatabaeefar, A. 2010. Development of a lemon sorting system based on color and size. African J. Plant Sci. 4, 122-127.
Liming, X. and Yanchao, Z. 2010. Automated strawberry grading system based on image processing. Comput. Electron. Agr. 71, S32-S39.
Meyer, G. E. and Neto, J. C. 2008. Verification of color vegetation indices for automated crop imaging applications. Comput. Electron. Agr. 63, 282-293.
Mizushima, A. and Lu, R. 2013. An image segmentation method for apple sorting and grading using support vector machine and Otsu’s method. Comput. Electron. Agr. 94, 29-37.
Muangkasem, A., Thainimit, S., Keinprasit, R. and Isshiki, T. 2010. Weed detection over between-row of sugarcane fields using machine vision with shadow robustness technique for variable rate herbicide applicator. Energy Res. J. 1, 141-145.
Polder, G., van der Heijden, G. W. A. M., van Doorn, J. and Baltissen, T. A. H. M. C. 2014. Automatic detection of tulip breaking virus (TBV) in tulip fields using machine vision. Biosys. Eng. 117, 35-42.
Russ, J. C. 1999. The Image Processing Handbook. 3rd Ed. Boca Raton: CRC Press.
Tang, L., Tian, L. and Steward, B. 2003. Classification of broadleaf and grass weeds using Gabor wavelets and an artificial neural network. Trans. ASAE. 46(4): 1247-1254.
Tian, L. F., Slaughter, D. C. and Norris, R. F. 2002. Machine vision identification of tomato seedlings for automated weed control. Trans. ASAE. 40(6): 1761-1768.
Wang, Z. and Zhang, D. 1999. Progressive switching median filter for the removal of impulse noise from highly corrupted images. Circuits and Systems II: Analog and Digital Signal Processing, IEEE Trans. 46, 78-80.
Woebbecke, D., Meyer, G., Von Bargen, K. and Mortensen, D. 1995a. Color indices for weed identification under various soil, residue, and lighting conditions. Trans. ASAE. 38, 259-269.
Woebbecke, D., Meyer, G., Von Bargen, K. and Mortensen, D. 1995b. Shape features for identifying young weeds using image analysis. Trans. ASAE. 38, 271-281.
)