The determination of the healthiness of a crop is relevant in ensuring a high agricultural yield. The growth rate and the productivity are the factors that can help to establish the expected yield. This is done by computing the crop assessment index. The main objective of this study is to develop a simple color recognition algorithm using digital image processing techniques. This will eliminate subjectiveness in the classification of healthy and unhealthy lettuce. Moreover, this can help the farmers to assess the quality of the crops while growing them. The crop used in this study is romaine lettuce. The image processing was built using LabView Vision Assistant through RGB acquisition. The backpropagation of the artificial neural network was used to increase the efficiency of the system in assessing the quality of the lettuce. The total number of images used in the study is 280 wherein 15% were used for validation, 15% were used for testing, and 70% were used for training. The developed system proves to provide a better assessment of the lettuce crop health.
Keywords: lettuce, crop health assessment, ANN, backpropagation[1] “Crop condition monitoring, assessment and forecast,” Global Agricultural Crop, 2016. [Online]. Available: http:// www.gdacorp.com/crop-condition-and-health. [Accessed: Aug. 4, 2016].
[2] J. W. Rushing, Improving the Safety and Quality of Fresh Fruits and Vegetables: A Training Manual for Trainers. University of Maryland: Joint Institute for Food Safety and Applied Nutrition, 2010.
[3] “Crop monitoring and damage assessment,” National Resources Canada, Nov. 25, 2015. [Online]. Available: http://www.nrcan.gc.ca/earth-sciences/geomatics/satelliteimagery-air-photos/satellite-imagery-products/educationalresources/14652. [Accessed: Aug. 4, 2016].
[4] S. N. Bartee, “Evaluation of crop health during late-season grainfill,” Helena, Aug. 1, 2014. [Online]. Available: http:// www.helenachemical.com/about-us/articles/evaluation-ofcrop-health-during-late-season-grainfill/. [Accessed: Aug. 4, 2016].
[5] A. T. Nieuwenhuizen, “Automated detection and control of volunteer potato plants,” Dissertation, Institute of Farm Technology, Wageningen University, 2009.
[6] F. D. Smedt, I. Billauws, and T. Goedeme, “Neural networks and low-cost optical filters for plant segmentation,” International Journal of Computer Systems and Industrial Management Applications, vol. 3, pp. 804–811, 2011.
[7] R. Brivot and J. A. Marchant, “Segmentation of plants and weeds for a precision crop protection robot using infrared images,” IEEE Proceedings–Vision, Image and Signal Processing, vol. 143, no. 2, pp. 118–124, 1996.
[8] A. Tellaeche, X. P. Burgos-Srtizzu, G. Pajares, and A. Ribeiro, “On combining support vector machines and fuzzy K-means in vision based precision agriculture,” World Academy of Science, Engineering and Technology, vol. 28, pp. 33–38, 2007.
[9] D. S. Shrestha and B. Steward, “Segmentation of plant from background using neural network approach,” in Proceedings of ANNIE, pp. 903–908, 2001.
[10] B. Garcia-Salgado and V. Ponomaryov, “Feature Extraction Scheme for a Textural Hyperspectral Image Classification using Gray-Scaled HSV and NDVI Image Features Vectors Fusion,” 2016 International Conference on Electronics, Communications and Computers (CONIELECOMP) 2016, pp. 186–191.
[11] J. F. Molina, R. Gily, C. Bojacáy, G. Díazz, and H. Francox, “Color and size image dataset normalization protocol for natural image classification: A case study in tomato crop pathologies,” in Symposium of Signals, Images and Artificial Vision—2013: STSIVA—2013. Bogota: IEEE, 2013, pp. 1–5.