Authors: P. Sangeetha, P. Sathwik, P. Surjid Banu, P. Shalini, K. Gopala Krishna, Dr. Thayyaba Khatoon
Certificate: View Certificate
Agriculture is the most important sector among all, as it supplies food to people. As the food demand is increasing in our daily life and the population is increasing there is need of increasing in the food production also. The main issue nowadays is that diseases that are causing the food production to reduce. So our main aim is identification of the disease of the plants in early stage so that we can do the early diagnosis and protect crops from the harmful diseases. By doing this we can avoid the damage of crops and also can reduce the loses that farmers suffer from damage of crops. Here we are using image processing technique to identify the disease of the crops so that we can cure the diseases of the crops in early stage. Here we are using Deep learning algorithms like Convolutional neural networks (CNN) for our project that is leaf disease detection. CNN is the best algorithm for image processing as it greatly increases the performance of our model. Nowadays deep learning is the current trend as it solves the most complicated problems easily and can get the highest accuracy.
A. Problem Definition
Agriculture, being a important contributor to the world’s economy, it is the main source of food, income, and employment. In India, as in other low- and middle-income countries, where an enormous number of farmers exist, agriculture contributes 18% of the nation’s income and boosts the employment rate to 53%. In the past years agriculture sector provides the highest growth of economy. It not only helps in economic growth but also provides food which is an important factor. It is our duty to protect the crops from the harmful diseases that are being spread. So our project’s main theme is to detect the diseases that are causing damage to the crops by doing this we can do the early diagnosis and can protect the plants. Here we are using one of the methods called image processing for the detection of plant disease because it is one of the most effective method of deep learning techniques where we can detect the disease using images of the leaves of the plant. Nowadays there are many diseases that farmers also don’t know what are the causes of that disease in this case our model is most reliable to detect the disease and to prevent it from damaging the crops. We are using one of the deep learning algorithms for our model i.e. Convolutional neural networks (CNN) this is one of the effective algorithms for image processing many of the researches used this convolutional neural network algorithm for their models so that they can get the better performance and high accuracy. Convolutional neural network is one of the of deep learning methods which has become dominant in various tasks and is attracting interest across a variety of domains, including radiology.
B. Objective of the Project
Our main objective of the project is detection of diseases in plants as they are the vital source of energy we need to protect them. Early diagnosis of plant diseases using automatic detection techniques can improve the quality of food production and minimize economic losses. In recent years, there are many areas where we used deep learning techniques for problem solving.
There are many diseases that are spreading among the plants which are destroying the crops, so to detect them and to and preventing them is our main objective of this model. Moreover it is our goal to create an automatic detection system for detection of diseases in the plants using image processing by implementing convolutional neural networks.
II. LITERATURE SURVEY
There are many researches that are done on different plant leaves they are as follows.
III. PROPOSED SYSTEM
A. Existing System
The current approach for detecting plant disease is simple naked eye observation by plant experts, which can be used to detect and identify plant diseases. In these circumstances ,the suggested technique is useful for tracking vast fields of crops. Furthermore, in some nations, farmers lack adequate facilities or are unware that they can contact experts.AS a result, consulting experts is not only more expensive but also more time consuming. In those circumstances, the suggested technique for tracking a large number of plants would be useful.
Disadvantages of Existing System
B. Proposed System
This study is focused on the identification of plant diseases. The plants which are mostly consumed are taken into consideration. It aims for providing a solution at early stage and hence observation from leaves for the identification of diseases is crucial. For any plant disease it is known that leaves are major regions where initial symptoms were found.
Hence considering the images of leaves , the methodology used Convolutional Neural Network to train with infected and healthy plant images.
The train dataset is used to train the model (CNN) so that it can identify the test image and the disease it has CNN has different types that are Dense, Dropout, Activation, Flatten, Convolution2D and Maxpooling2D.
After training the model successfully, the software can identify the disease detection contained in the dataset.After successful training and preprocessing , comparision of the test image and trained model takes place to detect the disease detection.
A convolution neural network is made up of input layers, hidden layers and an output layer. In a feed forward neural network, these middle layers are being addressed as hidden layers because the inputs being fed to hidden layers and output generated from them are masked by activation function and final covolutional. In CNN ,the hidden layers are most essential as they perform convolutions. This Convolution layer does most heavy lifting. The output from these layer is termed as Feature map which gives us the important information of the image.
Following these CNN consists of layers like Pooling layers, fully connected layers and normalization layers which will help to process the image and provide results more accurately. The primary application of pooling layer is to reduce the computational cost by decreasing the size of convolved feature map. The fully connected layer comes before the output layer which consists of weights and biases and all the main mathematical computation takes place in this layer. In these layer, the main function that is classification takes place. These layers along with additional features like dropout and Activation function makes the model more efficient.
D. Method and Algorithm Convolution Neural Network
The input image captured is preprocessed by following steps. After reading the image the next step is to resize the image. The resizing of the image is vital because the images obtained from the dataset will be of different sizes which in turn would be difficult to process through the model .Therefore, we must make sure that a base size is set for all images and then fed in to our algorithms. Then we try to remove the blur by reducing the noise. In the next step , we are going to segment the image, separating the background from foreground objects and we are going to further improve our segmentation with more noise removal. The preprocessing step helps to reduce the unwanted section and focuses on the main object in the image.
F. Feature Extraction
Features are patterns of an object in an image which will help to identify the desired result. Features include different types of properties such as corners, edges, regions of interest points, ridges, etc. This method will be most useful when the dataset is large and because of this technique it is possible to reduce the number of features without losing any important or relevant information. So, by this processing gets easier. It will be able to extract complex features compared to traditional feature extractors where CNN are able to express the image in much more detail and more efficient. These large datasets have multiple different variables. These variables require high computing resources in order to process them. So, Feature extraction identifies the best feature from those big datasets, thus effectively reducing the amount of data. Ideally, these features are relatively easy to process, but still are able to describe the actual dataset with accuracy. The CNN layers helps us to extract features from an image. The amount of redundant data will be significantly eliminated with the help of feature extraction.
Our main aim of this model is welfare of the agriculture sector so that we can prevent the plants by getting infected from various types of diseases using the convolutional neural networks using image processing technique. By proper knowledge of the disease we can cure the maximum number of disease that plants suffer. This paper presents a basic overview of the concept of Convolutional neural networks and to build a automatic detection system for detection of leaf diseases. our main aim is to get the high accuracy and a model at low cost thereby building a model which is robust and reliable. Here we used deep learning technique which is used to solve the complex problems and by doing this we want to increase the production of agriculture sector. By using this model we achieve the following. 1) Detection of leaf disease with highest accuracy. 2) With low cost.
 Diseased plant leaves using Neural Network Algorithms K. Muthukannan1, P. Latha2, R. Pon Selvi1 and P. Nisha1 1Department of ECE, Einstein College of Engineering, Anna University, Tirunelveli, India 2Department of CSE, Government College of Engineering, Anna University, Tirunelveli, India ARPN Journal of Engineering and Applied Sciences, VOL. 10, NO. 4, MARCH 2015, ISSN 1819-6608.  Ranjan, Malvika, and others ”Detection and classification of leaf disease using artificial neural network.” International Journal of TechnicalResearch and Applications 3.3 (2015): 331-333.  Cortes, Emanuel. ”Plant disease classification using convolutional networks and generative adversarial networks.” (2017).  Ramcharan, Amanda, et al. ”Deep learning for image-based cassava disease detection.” Frontiers in plant science 8 (2017): 1852.  Arivazhagan, S. and Ligi, S. V.: Mango Leaf Diseases Identification Using Convolutional Neural Network. Int. J. Pure Appl. Math., 120(2018) 11067–11079  Oppenheim, D. and Shani, G.: Potato Disease Classification Using Convolution Neural Networks. Adv. Anim. Biosci., 8 (2017), 244–249  Barbedo, J. G. A.: Factors influencing the use of deep learning for plant disease recognition. Biosyst. Eng., 172 (2018) 84–91  S. D. Khirade and A. B. Patil, “Plant Disease Detection Using ImageProcessing,” 2015 International Conference on Computing CommunicationControl and Automation, 2015, pp. 768-771, DOI: 10.1109/ICCUBEA.2015.153  P. Moghadam, D. Ward, E. Goan, S. Jayawardena, P. Sikka andE. Hernandez, ”Plant Disease Detection Using Hyperspectral Imaging,”2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2017, pp. 1-8, doi:10.1109/DICTA.2017.8227476  Sharath, D. M., et al. ”Image-based plant disease detection in pomegranate plant for bacterial blight.” 2019 international conference on communication and signal processing.  U?uz, S. and Uysal, N.: Classification of olive leaf diseases using deep convolutional neural networks. Neural Comput. Appl., 5 (2020)  Agarwal, M., Gupta, S. K., and Biswas, K. K.: Development of Efficient CNN model for Tomato crop disease identification. Sustain. Comput. Informatics Syst., 28 (2020) 100407  Wang, J., Chen, L., Zhang, J., Yuan, Y., Li, M., and Zeng, W. H.: CNN transfer learning for automatic image-based classification of crop disease. Springer Singapore 875 (2018)  Toda, Y., and Okura, F.: How Convolutional Neural Networks Diagnose Plant Disease. Plant Phenomics, 2019 (2019) 1–14  Tran, T. T., Choi, J. W., Le, T. T. H. and Kim, J. W.: A comparative study of deep CNN in forecasting and classifying the macro-nutrient deficiencies on development of tomato plant. Appl. Sci.,9(2019).
Copyright © 2023 P. Sangeetha, P. Sathwik, P. Surjid Banu, P. Shalini, K. Gopala Krishna, Dr. Thayyaba Khatoon. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.