Open AccessLeaf Disease Detection using Labview Imaq Vision
Author(s) -
Anusha Nellutla,
Gnana Sai Ganesh Chittajallu,
Feroz Shaik
Publication year - 2020
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.c4574.099320
Subject(s) - artificial intelligence , computer science , computer vision , machine vision , image processing , rgb color model , process (computing) , image (mathematics) , operating system
The intension of our project is to design a system which can identify the good leaves from the diseased ones. Image processing is a powerful tool capable of many applications. Image processing combined with Machine Vision can simulate and execute real time projects. In this project we have used LabVIEW along with IMAQ Vision to acquire real time images and process them. LabVIEW IMAQ Vision is potentially useful for agricultural products since it combines the merits of both LabVIEW and IMAQ Vision, which have graphical programming environment and rich image processing functions. The project aims to provide a brief introduction into the IMAQ vision components like Image Acquisition, Calibration, Defect detection. Major leaf diseases’ symptoms include spots or discolouration of leaves. The presence or absence of macro and micro nutrients, bug infestation and other diseases can be identified through leaves. In this project we have obtained the images through LabVIEW IMAQ vision pallet. Further on two procedures were followed – one based on colour of the leaves and other is based on spots and patterns present on the leaves. For the discolouration we first split the image into its constituent planes- RGB and CMYK, here we used Green, Cyan and Yellow planes. Then on we decided a threshold based on sample data using Linear Regression based prediction model of Machine Learning to classify the data into three states – safe, risk and high risk.The second method was detecting spots. First, we split the images into its constituent planes to convert the RGB image to Greyscale and increase the contrast using the Colour Plane Extraction tool then use the Look up table tool to further enhance the contrast. Then on locate the bright objects and then using dilation from the Morphology tool box we increase the size of the spots to increase detection rate. Using Advanced Morphology tool box we removed the boundary objects to isolate the spots. Then using the shape detection or circle detection algorithm we can detect the spots. Several samples were obtained and are successfully classified. Finally, current limitations and likely future development trends are discussed. Combining LabVIEW along with different programming algorithms can help in raising the accuracy of the system.