Rule based approach to determine nutrient deficiency in paddy leaf images.

Rice is one of the most consumed grains among the human society especially in Asia, but is easily affected by the deficiency caused due to lack of nutrient elements. Identifying nutrient deficiencies of paddy crop is very essential in overcoming these and thereby enhancing yield. Color of paddy leaves plays important role in identifying major deficiencies such as NPK (Nitrogen, phosphorus and Potassium) when crop is in its middle of its growth. In order to do so a database of healthy, nitrogen defected, phosphorus defected and potassium defected leaves is created. Color features of both healthy and defected paddy leaves are extracted using HSV color model. Similarly color features of test image is extracted and compared against database properties. Comparison results are validated against the rules set to determine the specific deficiency. The rules are framed based on rigorous experiment. The efficiency can be further increased by including leaf pattern analysis.

[1]  Ratih Kartika Dewi,et al.  Feature extraction for identification of sugarcane rust disease , 2014, Proceedings of International Conference on Information, Communication Technology and System (ICTS) 2014.

[2]  Jayamala K. Patil,et al.  Advances in Image Processing for Detection of Plant Disease , 2017 .

[3]  Nitin S. Tijare,et al.  IMAGE RECOGNITION BASED CROP DISEASE IDENTIFICATION SYSTEM: A SURVEY , 2014 .

[4]  Junlong Fang,et al.  Color Analysis of Leaf Images of Deficiencies and Excess Nitrogen Content in Soybean Leaves , 2010, 2010 International Conference on E-Product E-Service and E-Entertainment.

[5]  Hugo Franco,et al.  An image retrieval system for tomato disease assessment , 2014, 2014 XIX Symposium on Image, Signal Processing and Artificial Vision.

[6]  Viswanath Talasila,et al.  Leaf features based approach for automated identification of medicinal plants , 2014, 2014 International Conference on Communication and Signal Processing.

[7]  Jagadeesh D. Pujari,et al.  Identification and classification of fungal disease affected on agriculture/horticulture crops using image processing techniques , 2014, 2014 IEEE International Conference on Computational Intelligence and Computing Research.

[8]  P. K. Mishra,et al.  Understanding Color Models: A Review , 2012 .

[9]  P. Bhandarkar,et al.  Leaf identification using morphology and structural decomposition , 2014, 2014 International Conference on Signal Processing and Integrated Networks (SPIN).

[10]  Debashis Ghosh,et al.  Energy efficient mobile vision system for plant leaf disease identification , 2014, 2014 IEEE Wireless Communications and Networking Conference (WCNC).

[11]  Shanu Sharma,et al.  Leaf disease detection and grading using computer vision technology & fuzzy logic , 2015, 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN).

[12]  R. V. Kshirsagar,et al.  Cotton leaf disease identification using pattern recognition techniques , 2015, 2015 International Conference on Pervasive Computing (ICPC).

[13]  Mahdi Jampour,et al.  A heuristic method for gray images pseudo coloring with histogram and RGB layers , 2011, 2011 IEEE 3rd International Conference on Communication Software and Networks.

[14]  Li-shu Wang.  Soybean leaves nitrogen elements information collected preprocessing based on model identification , 2010, 2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE).

[15]  Su Hang,et al.  A Research of Maize Disease Image Recognition of Corn Based on BP Networks , 2011, 2011 Third International Conference on Measuring Technology and Mechatronics Automation.