Machine Learning Based Nutrient Deficiency Detection in Crops
Amirtha T1, Gokulalakshmi T2, Umamaheswari P3, T Rajasekar M.Tech4
1Amirtha T, Department of Electronics and Communication Engineering ,Agni college of Technology, OMR, Thalambur, Chennai.
2Gokulalakshmi T, Department of Electronics and Communication Engineering,Agni college of Technology, OMR, Thalambur, Chennai.
3Umamaheswari P, Department of Electronics and Communication Engineering,Agni college of Technology, OMR, Thalambur, Chennai.
4T Rajasekar, Department of Electronics and Communication Engineering, Agni college of Technology, OMR, Thalambur, Chennai.
Manuscript received on February 28, 2020. | Revised Manuscript received on March 22, 2020. | Manuscript published on March 30, 2020. | PP: 5330-5333 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9322038620/2020©BEIESP | DOI: 10.35940/ijrte.F9322.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Indian economy is mainly based on Agriculture, involves the process of cultivating certain plants for producing food and many other desired products and raising of domesticated animals. Nutrients play a major role in agriculture and crop production. There are number of reasons for decreasing of crop yield. One such factor involved is nutrient deficiency. The proper detection of nutrient deficiency and appropriate fertilizer for that deficiency are the major problems faced by many farmers. Hence, in order to improve productivity, Automation in agriculture evolved drastically in recent years. This paper aims at designing an automatic robotic vehicle which detects the nutrient deficiency in crops just by simply capturing the image of leaves of the crop plants. The captured image is then processed by using the convolutional neural networks (CNN). This technique uses captured image, processing it by comparing it with the already available dataset. When the input image is matched or partially matched with any one of the existing images in the dataset, it will provide the result of nutrient deficiency in crops, in terms of the percentage. The name of disease associated with nutrient deficiency and appropriate amount of fertilizer will be displayed in the LCD. This will reduce the problems of the labour force and the burden of farmers.
Keywords: Nutrient Deficiency Detection, Automation, CNN, Fertilizer.
Scope of the Article: Machine Learning.