Hostname: page-component-745bb68f8f-v2bm5 Total loading time: 0 Render date: 2025-01-10T20:39:09.667Z Has data issue: false hasContentIssue false
  • English
  • Français

Influence of weed maturity levels on species classification using machine vision

Published online by Cambridge University Press:  20 January 2017

T. F. Burks ,
S. A. Shearer ,
J. D. Green  and
J. R. Heath
S. A. Shearer
Affiliation:
Department of Biosystems and Agricultural Engineering, University of Kentucky, Lexington, KY 40546-0276
J. D. Green
Affiliation:
Department of Agronomy, University of Kentucky, Lexington, KY 40546-0091
J. R. Heath
Affiliation:
Department of Electrical Engineering, University of Kentucky, Lexington, KY 40546-0046
Get access Rights & Permissions [Opens in a new window]

Abstract

The environmental effect of weed control systems has stimulated research into new practices for weed control, such as selective herbicide application methods on weed-infested crop areas. This research used the color co-occurrence method (CCM) texture analysis to determine the effects of plant maturity on the accuracy of weed species classification of digitized images. Two different experimental combinations of weed species and maturity level were examined. The weed species evaluated were ivyleaf morningglory, giant foxtail, large crabgrass, and velvetleaf, with soil image sets added to each experiment. One study examined classification accuracies for two weed species at three maturity levels, and the second study examined four weed species at two maturity levels. For each species-maturity level combination, 40 digital images were collected from a manually seeded outdoor plant bed. Digitized images were transformed from the red–green–blue (RGB) color format into hue–saturation–intensity (HSI) format to generate CCM texture feature data. Stepwise variable reduction procedures were used to select texture variables with the greatest discriminant capacity. Then discriminant analysis was used to determine the classification accuracy for the two different experiments. When using HSI texture statistics, discriminant analysis correctly classified weed species within and across maturity levels with an accuracy above 97% for both experimental groups. These image processing algorithms demonstrate potential use for weed scouting, weed infestation mapping, and weed control applications using site-specific farming technology.

Keywords

Ivyleaf morningglory, Ipomoea hederacea (L.) Jacq. IPOHEgiant foxtail, Setaria faberi Hermm. SETFAlarge crabgrass, Digitaria sanguinalis (L.) Scop. DIGSAvelvetleaf, Abutilon theophrasti Medik. ABUTHImage processingweed identificationcolor texture analysissite-specific farmingprecision agriculture
Type
Research Article
Information
Weed Science , Volume 50 , Issue 6 , December 2002 , pp. 802 - 811
Copyright
Copyright © Weed Science Society of America 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Literature Cited

Blackshaw, R. E., Molnar, L. J., and Lindwall, C. W. 1998. Merits of a weed-sensing sprayer to control weeds in conservation fallow and cropping systems. Weed Sci. 46:120–126.CrossRefGoogle Scholar
Burks, T. F. 1997. Color Image Texture Analysis and Neural Network Classification of Weed Species. Ph.D. dissertation. University of Kentucky. Lexington, KY.Google Scholar
Burks, T. F. and Shearer, S. A. 1996. Color Texture Analysis for Weed Identification Using Machine Vision. SAE Off-Highway & Powerplant Congress & Exposition. SAE Paper No. 961795. Indianapolis, IN. 337 p.Google Scholar
Everitt, J. H., Escobar, D. E., Alaniz, M. A., Davis, M. R., and Richerson, J. V. 1996. Using spatial information technologies to map Chinese tamarisk (Tamarix chinensis) infestations. Weed Sci. 44:194–201.CrossRefGoogle Scholar
Everitt, J. H., Richerson, J. V., Alaniz, M. A., Escobar, D. E., Villarreal, R., and Davis, M. R. 1994. Light reflectance characteristics and remote sensing of Big Bend loco (Astragalus mollissimus var. earlei) and Wooton loco (Astragalus wootonii). Weed Sci. 42:115–122.Google Scholar
Franz, E., Gebhardt, M. R., and Unklesbay, K. B. 1990. Shape Description of Completely Visible and Partially Occluded Leaves for Identifying Plants in Digital Images. ASAE Paper No. 90–7040. St. Joseph, MI: American Society of Agricultural Engineers.Google Scholar
Franz, E., Gebhardt, M. R., and Unklesbay, K. B. 1991. The use of local spectral properties of leaves as an aid for identifying weed seedling in digital images. Trans. Am. Soc. Agric. Eng. 34:682–687.CrossRefGoogle Scholar
Haralick, R. M. and Shanmugam, K. 1974. Combined spectral and spatial processing of ERTS imagery data. J. Remote Sensing Environ. 3:3–13.Google Scholar
Johnson, G. A., Mortensen, D. A., and Martin, A. R. 1995. A simulation of herbicide use based on weed spatial distribution. Weed Res. 35:197–205.CrossRefGoogle Scholar
Julesz, B. 1962. Visual pattern discrimination. IRE Trans. Informat. Theory. 8:84–92.CrossRefGoogle Scholar
Lindquist, J. L., Dieleman, J. A., Mortensen, D. A., Johnson, G. A., and Wyse-Pester, D. Y. 1998. Economic importance of managing spatially heterogeneous weed populations. Weed Technol. 12:7–13.Google Scholar
Meyer, G. E., Mehta, T., Kocher, M. F., Mortensen, D. A., and Samal, A. 1998. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying. Trans. Am. Soc. Agric. Eng. 41:1189–1197.CrossRefGoogle Scholar
Ohta, Y. 1985. Knowledge-Based Interpretation of Outdoor Natural Color Scenes. Marshfield, MA: Pitman Publishing. 136 p.Google Scholar
[SAS] Statistical Analysis Systems. 1985. SAS User's Guide; Statistics. 5th ed. Cary, NC: Statistical Analysis Systems Institute.Google Scholar
Shearer, S. A. 1986. Plant Identification Using Color Co-Occurrence Matrices Derived From Digitized Images. Ph.D. dissertation. Ohio State University, Columbus, OH. 177 p.Google Scholar
Shearer, S. A. and Holmes, R. G. 1990. Plant identification using color co-occurrence matrices. Trans. Am. Soc. Agric. Eng. 33:2037–2044.CrossRefGoogle Scholar
Tang, L., Tian, L. F., Steward, B. L., and Reid, J. F. 1999. Texture-Based Weed Classification Using Gabor Wavelets and Neural Network for Real-time Selective Herbicide Applications. Am. Soc. Agric. Eng. Paper No. 90–7040. St. Joseph, MI: American Society of Agricultural Engineers.Google Scholar
Thompson, J. F., Stafford, J. V., and Miller, P.C.H. 1991. Potential for automatic weed detection and selective herbicide application. Crop Prod. 10:254–259.Google Scholar
[USDA-SCS] U.S. Department of Agriculture, Soil Conservation Service. 1968. Soil Survey: Fayette County, Kentucky. U.S. Department of Agriculture, Soil Conservation Service. Sheet No. 30.Google Scholar
Wicks, G. A., Felton, W. L., Murison, R. D., Hanson, G. E., and Nash, P. G. 1998. Efficiency of an optically controlled sprayer for controlling weeds in fallow. Weed Technol. 12:638–645.CrossRefGoogle Scholar
Woebbecke, D. M., Meyer, G. E., Von Bargen, K., and Mortensen, D. A. 1995a. Color indices for weed identification under various soil, residue, and lighting conditions. Trans. Am. Soc. Agric. Eng. 38:259–269.Google Scholar
Woebbecke, D. M., Meyer, G. E., Von Bargen, K., and Mortensen, D. A. 1995b. Shape features for identifying young weeds using image analysis. Trans. Am. Soc. Agric. Eng. 38:271–281.CrossRefGoogle Scholar
Wyszecki, G. and Stiles, W. S. 1992. Color Science; Concepts and Methods, Quantitative Data and Formulae. 2nd ed. New York: J. Wiley. pp. 117–137.Google Scholar
Zhang, N. and Chaisattapagon, C. 1995. Effective criteria for weed identification in wheat fields using machine vision. Trans. Am. Soc. Agric. Eng. 38:965–974.Google Scholar