In this digital era, with the advancements of technology a major role is being played by Information and Communication Technology in agriculture. Especially the issues related to agriculture such as real-time crop detection and monitoring, leaf identification is still a challenging task for the researchers and practitioners. Automatic detection of the crop type and its growth by analysing the colour and size of the leaves helps the farmers to take immediate advice from the botanical domain expert. The work in this paper deals with study and implementation of texture based classification and annotation of groundnut crop leaves using machine learning algorithms like HAAR, HOG and LBP. A set of trained and untrained images are employed in this task. Experiments are conducted using the cascade trainer tool in MATLAB 2016 by varying several parameters and selecting regions-of-interest on the crop for training. Later, the impact of each of the parameters on the above algorithms are recorded and well described in this paper. Furthermore, from the perspective of number of objects detected, it is noticed that LBP has yielded better results than HAAR and HOG.

Computer vision, ICT, leaf identification, HAAR, HOG, LBP, machine learning

[1] Brosnan, T. and Sun, D.W.,. “Inspection and grading of agricultural and food products by computer vision systems—a review. “ Computers and electronics in agriculture, 36(2), pp.193-213, 2002.
[2] Bourgeois, R.. “ A Preliminary Assessment of the Potential Role of Information and Communication Technology in Support of Poverty Alleviation Policies for Rural Populations”--AGRI-ICT Project Report (No. 32660), 2004.
[3] Kidd, P.T.,. “The role of the internet of things in enabling sustainable agriculture in Europe.” International Journal of RF Technologies, 3(1), pp.67-83, 2012.
[4] Zacepins, A., Brusbardis, V., Meitalovs, J. and Stalidzans, E., “Challenges in the development of Precision Beekeeping.” Biosystems Engineering, 130, pp.60-71., 2015.
[5] Rosenzweig, C. and Parry, M.L.,. “Potential impact of climate change on world food supply.“ Nature, 367(6459), pp.133-138, 1994.
[6] Mall, R.K., Singh, R., Gupta, A., Srinivasan, G. and Rathore, L.S., “Impact of climate change on Indian agriculture: a review.” Climatic Change, 78(2-4), pp.445-478, 2006.
[7] Meera, S.N., Balaji, V., Muthuraman, P., Sailaja, B. and Dixit, S., “Changing roles of agricultural extension: harnessing information and communication technology (ICT) for adapting to stresses envisaged under climate change.” In Crop Stress and its Management: Perspectives and Strategies (pp. 585-605). Springer Netherlands, 2012.
[8] McBratney, A., Whelan, B., Ancev, T. and Bouma, J.,. “Future directions of precision agriculture.” Precision agriculture,”6(1), pp.7-23, 2005.
[9] Dong, X., Vuran, M.C. and Irmak, S., “Autonomous precision agriculture through integration of wireless underground sensor networks with center pivot irrigation systems.” Ad Hoc Networks, 11(7), pp.1975-1987, 2013.
[10] Rajkumar, R.R., Lee, I., Sha, L. and Stankovic, J.,.”Cyber-physical systems: the next computing revolution.” In Proceedings of the 47th Design Automation Conference (pp. 731-736).ACM, 2010.
[11] Chen, N., Zhang, X. and Wang, C., “Integrated open geospatial web service enabled cyber-physical information infrastructure for precision agriculture monitoring.” Computers and Electronics in Agriculture, 111, pp.78-91, 2015.
[12] Gómez-Candón, D., De Castro, A.I. and López-Granados, F., “Assessing the accuracy of mosaics from unmanned aerial vehicle (UAV) imagery for precision agriculture purposes in wheat.” Precision Agriculture, 15(1), pp.44-56, 2014.
[13] Rad, C.R., Hancu, O., Takacs, I.A. and Olteanu, G.,. “Smart monitoring of potato crop: a cyber-physical system architecture model in the field of precision agriculture. “ Agriculture and Agricultural Science Procedia, 6, pp.73-79, 2015.
[14] Khosla, R.,. “Precision agriculture: challenges and opportunities in a flat world.” In 19th World Congress of Soil Science, Soil Solutions for a Changing World, Brisbane (pp. 1-6), 2010.
[15] Sammouda, R., Adgaba, N., Touir, A. and Al-Ghamdi, A.,. “Agriculture satellite image segmentation using a modified artificial Hopfield neural network.” Computers in Human Behavior, 30, pp.436-441, 2014.
[16] Farooque, A.A., Quang, T., Zaman, Q.U., Groulx, D., Schumann, A.W. and Chang, Y.K.,. “Development of a predictive model for wild blueberry fruit losses during harvesting using artificial neural network.” Applied Engineering in Agriculture, 32(6), 725-738. doi:10.13031/aea.32.10872, 2016.
[17]Jones, A., Ali, U. and Egerstedt, M., “ April.Optimal Pesticide Scheduling in Precision Agriculture.” In ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS) (pp. 1-8).IEEE., 2016.
[18] Peters, R.,. “Nine billion and beyond: from farm to fork [Agriculture Big Data]. “ Engineering & Technology, 11(4), pp.74-74, 2016.
[19] Nguyen, T., Hefenbrock, D., Oberg, J., Kastner, R. and Baden, S.,. “A software-based dynamic-warp scheduling approach for load-balancing the Viola–Jones face detection algorithm on GPUs.” Journal of Parallel and Distributed Computing, 73(5), pp.677-685, 2013.
[20] Feng, K.P. and Yuan, F.,” December. Static hand gesture recognition based on HOG characters and support vector machines. “In Instrumentation and Measurement, Sensor Network and Automation (IMSNA), 2nd In1ernational Symposium on (pp. 936-938). IEEE, 2013.
[21] Dubey, S.R. and Jalal, A.S., “November. Detection and classification of apple fruit diseases using complete local binary patterns.” In Computer and Communication Technology (ICCCT), Third International Conference on (pp. 346-351). IEEE., 2012.
[22] Harini, D.N.D. and Bhaskari, D.L., 2011. “Identification of leaf diseases in tomato plant based on wavelets and PCA.” In 2011 World Congress on Information and Communication Technologies (pp. 978-1), 2011.
[23]Liu, C., Yuen, J. and Torralba, A “SIFT Flow: Dense Correspondence Across Scenes and Its Applications.” In Dense Image Correspondences for Computer Vision, Springer International Publishing,., (pp. 15-49), 2016.
[24] Yao, S., Pan, S., Wang, T., Zheng, C., Shen, W. and Chong, Y., “A new pedestrian detection method based on combined HOG and LSS features.” Neurocomputing, 151, pp.1006-1014, 2015.
[25] Li, J. and Zhang, Y., “Learning surf cascade for fast and accurate object detection.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3468-3475), 2013.
[26] Xiao, Xue-Yang, et al. "HOG-based approach for leaf classification." Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. Springer Berlin Heidelberg,. 149-155, 2010.
[27] Arafat, S.Y., Saghir, M.I., Ishtiaq, M. and Bashir, U., July. “Comparison of techniques for leaf classification.” In Digital Information and Communication Technology and its Applications (DICTAP), 2016 Sixth International Conference on (pp. 136-141). IEEE, 2016.