Detection of Herbs using Image Processing

M. Lakshmi Surekha*, N. Kamala Kumari **, Y. Deepika ***, U. V. Ramesh ****
*-**** Department of Computer Science Engineering, Pragati Engineering College, Surrampalem, Andhra Pradesh, India.
Periodicity:January - June'2020
DOI : https://doi.org/10.26634/jpr.7.1.17273

Abstract

Knowledge about the distribution of herbs (weeds) within a specific area might be a prerequisite for specific treatment. The herbs are taken out from images using image processing described by shape features. A classification based on the features reveals the type and number of weeds for each image. For the classification we use only a maximum of 16 features out of the 81 computed ones. The selection has been done using processing algorithms, which rate the definiteness of the features of prototypes. If no prototypes are available, clustering algorithms are accustomed automatically to generate clusters. In the next step weed classes are assigned to the clusters. Weed maps are generated using the system. Weed maps are compared with the results of a manual weed sampling.

Keywords

Thresholding, Image Processing, Weed, Segmentation, Feature Extraction.

How to Cite this Article?

Surekha, M. L., Kumari, N. K.. Deepika, Y., and Ramesh, U. V.(2020). Detection of Herbs using Image Processing. i-manager's Journal on Pattern Recognition, 7(1), 18-23. https://doi.org/10.26634/jpr.7.1.17273

References

[1]. Cappellato, L., Ferro, N., Halvey, M., & Kraaij, W. (2014). CLEF 2014: Information access evaluation meets multilinguality, multimodality, and interaction. ACM SIGIR Forum, 48(2), 56-62. https://dx.doi.org/10.1145/2701583. 2701589
[2]. Chen, Q., Abedini, M., Garnavi, R., & Liang, X. (2014). IBM research australia at LifeCLEF 2014: Plant identification task. In Working notes of CLEF 2014 conference (pp. 693-704).
[3]. EU Directive. (2009). Establishing a framework for community action to achieve the sustainable use of pesticides (Derivative 128/EC). European Union, Brussels. Retrieved from http://data.europa.eu/eli/dir/2009/128/oj
[4]. GitHub. (2016). Itseez. Open source computer vision library (openCV-itseez). Retrieved from https://github. com/gongzg/opencv-itseez.
[5]. Melander, B., Munier-Jolain, N., Charles, R., Wirth, J., Schwarz, J., vander Weide, R., ... & Kudsk, P. (2013). European perspectives on the adoption of nonchemical weed management in reduced-tillage systems for arable crops. Weed Technology, 27(1), 231-240. https://doi.org/ 10.1614/WT-D-12-00066.1
[6]. Olsen, S. I., Nielsen, J., & Rasmussen, J. (2017, June). Thistle detection. In Scandinavian Conference on Image Analysis (pp. 413-425). Springer, Cham. https://doi.org/ 10.1007/978-3-319-59129-2_35
[7]. Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014). CNN features off-the-shelf: An astounding baseline for recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 806-813). https://doi.org/10.1109/CVPRW. 2014.131
[8]. Rouhi, R., Jafari, M., Kasaei, S., & Keshavarzian, P. (2015). Benign and malignant breast tumors classification based on region growing and CNN segmentation. Expert Systems with Applications, 42(3), 990-1002. https://doi. org/10.1016/j.eswa.2014.09.020
[9]. Soos, B. G., Rak, A., Veres, J., & Cserey, G. (2008, July). GPU powered simulator (SIMCNN) with graphical flow based programmability. In 2008, 11th International Workshop on Cellular Neural Networks and Their Applications (pp. 163-168). IEEE. https://doi.org/10.1109/ CNNA.2008.4588671
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Online 15 15

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.