11 V May 2023

https://doi.org/10.22214/ijraset.2023.52103
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue V May 2023- Available at www.ijraset.com

Plant Disease Detection and Classification

Using Deep Learning
Krishna Chandan K1, Hruthik B2, Charith K3, Swapana Kamakshi K4.
1, 2, 3, 4
Sreenidhi Institute of Science and Technology, Hyderabad, India

Abstract: Agriculture is the backbone of every country in the world. In India, most of the rural population still depends on
agriculture. The agricultural sector provides major employment in rural areas. Furthermore, it contributes a significant amount
to India’s gross domestic product (GDP). Therefore, protecting and enhancing the agricultural sector helps in the development
of India’s economy. In this work, a real-time decision support system integrated with a camera sensor module was designed and
developed for the identification of plant disease. This research proposes an intelligent method for plant disease classification
using image processing techniques. The proposed method aims to assist farmers and experts in identifying and diagnosing plant
diseases efficiently and accurately. The system first obtains images of the plant leaves from different perspectives and then pre-
processes the images to enhance the quality and remove noise. The preprocessed images are then subjected to feature extraction
using a deep convolutional neural network (CNN) model. The features extracted from the CNN are then fed into a classifier for
the classification of plant diseases. The proposed method is evaluated using a dataset of plant images with three different types
of diseases. The results obtained show that the proposed method achieves high accuracy in the classification of plant diseases,
making it a useful tool for plant disease diagnosis and control. The proposed method can be integrated into a mobile application
or web based platform for use by farmers and botanists.
Keywords: Plant Disease Detection, Deep Learning, Convolution Neural Network, OpenCV

I. INTRODUCTION
In the field of agricultural production, ignoring the early signs of plant diseases may lead to losses in food crops, which could
eventually affect world’s economy [1]. This section presents an in-depth survey of state-of-the-art research in the field of leaf
disease identification. A CNN-based deep learning model was proposed for the accurate classification of plant disease in [2], and the
model was trained using a publicly available dataset with 87,000 RGB images. Initially, pre-processing was undertaken, followed by
segmentation. For classification, a CNN was used. Although this model reached an accuracy of 94%, it failed to classify some
classes, leading to confusion with the classes in subsequent stages. Further, the performance of the model deteriorated due to the
limited availability of data. However, to improve recognition accuracy, proposing a hybrid convolutional neural network to classify
banana plant disease. In their approach, the input image was pre-processed without altering any default information, and the
standard image dimensions were maintained using a median filter. This approach used a fusion SVM along with a CNN. A
multiclass SVM was used in the testing phase to identify the type of infection or disease in infected banana leaves, whereas the
SVM was used in phase 1 to classify whether the potato leaves were healthy or infected. The classified CNN output was fetched as
an input to the support vector machine, attaining a classification accuracy of 99%. The previous work stated that CNN had better
accuracy outcomes than traditional methods but this approach lacked diversity. Crop disease reduces both the quantity and quality
of food produced. Crop diseases not only have an effect on global food security, but they also have a negative impact on small-scale
farmers whose livelihood is dependent on cultivation. The benefit is that crop diseases can be monitored by detecting them as
soon as they appear on the crops. It has been possible to provide an effective solution to this problem thanks to the advent of the
internet and the field of computer vision. A mistaken diagnosis of plant disease results in a significant loss of production, time,
resources, and product quality. Identifying the state of the plant is critical for effective cultivation. Different types of environmental
anomalies, such as fungi, water shortages, insects, and weeds, have an effect on crop. These are issues that require farmers to take
defensive steps to boost productivity. This research aids in concentrating on the visually targeted quality of the crop. Artificial
intelligence advances have made it possible to identify plant diseases automatically from images. Deep learning is a learning system
based on neural networks. One of the benefits of deep learning is that it can extract features from photos. During preparation, the
neural network learns how to extract features. The deep learning model is CNN, which is a multi-layer feed-forward neural network.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 6305
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue V May 2023- Available at www.ijraset.com

Fig.1. Infected plant

II. PROBLEM STATEMENT

The Indian agriculture sector employs nearly half of the country's workforce. India is the largest producer of pulses, rice, wheat,
spices, and spice products in the world. Farmers' economic growth is determined by the quality of the goods they make, which is
dependent on plant growth and yield. As a result, in the field of agriculture, disease identification in plants is important. Plants are
highly prone to diseases that inhibit plant development. The use of an automated disease detection technique is advantageous in
detecting a plant disease at an early stage. Plant diseases manifest themselves in various parts of the plant, such as the leaves. It
takes a long time to manually diagnose plant disease using leaf photographs. As a result, computational methods must be developed
to automate the process of disease detection and classification using leaf images.

III. EXISTING SYSTEM

The current approach for detecting plant disease is simple eye observation by 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 unaware then, As a result, on those circumstances, the suggested technique for tracking a large
number of plants would be useful.

A. Disadvantages of the Existing System

1) The procedure is slow.
2) Consumption of time and space is also very high.
3) Not economically friendly.

IV. PROPOSED SOLUTION

This study is focused on implementing a web application and identification of plant diseases. Segmentation feature extraction and
classification techniques are used to detect plant diseases. Photos of leaves from various plants are taken with a digital camera or
similar unit, and the images are used to classify the affected region in the leaves.
To detect plant disease, we use a Convolution neural network and a deep neural network in the proposed methodology. This paper
proposes a framework that employs low-cost, open-source software to achieve the task of reliably detecting plant disease.

A. It is capable
Advantages to detect images with a cost-effective camera and open cv.
Open CV helps in the efficient analysis of sources such as images and videos.
It does not require any high-resolution images.

V. LIST OF MODULES
Image acquisition Image pre-processing Image enhancement Image segmentation Image analysis Feature extraction Disease
classification

A. Image Acquisition
The first step is to gather data from a publicly accessible repository. The picture is used as the input for further processing. We've
chosen the most common image domains so that we can accept any format as input to our method, including.jpg The camera feeds
the real-time images directly.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 6306
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue V May 2023- Available at www.ijraset.com

Since most leaves’ color differs from red to green for exact segmentation, a white background is provided for further study, proper
visibility, and easy image analysis Images are captured using an image capturing system in this process.

B. Image Pre-processing
The use of computer algorithms to perform image processing on digital images is known as image pre-processing. We can detect the
plant by analyzing the image with a specific algorithm. We use a similar approach for image processing and detection with an
algorithm. The image quality is critical in this process.

C. Image Enhancement
The process of modifying digital images so that the effects are more appropriate for display or further image processing is known
as image enhancement. Any of the following can be used to improve an image:
1) Model optimization
2) Noise removal using filters. Decorrelation etc.
The method of segmenting a digital image into multiple segments is known as image segmentation. Used to make image
identification and analysis simpler by dividing the image into segments and analyzing each segment individually. Color, texture, and
intensity are all features among the various segments.

Fig.2 image segmentation of leaf

D. Image Analysis
In this process, image segmentation is used to locate the region of concern. The technique used in segmentation is region-based
segmentation, which uses the color of the leaf to distinguish between healthy and diseased areas of the leaf.

E. Feature Extraction
Feature extraction is a part of the dimensional reduction method in machine learning, which divides and reduces a large set of raw
data into smaller classes. This step is needed when we have a large amount of data and need to minimize the number of resources
while avoiding errors. As a result, function extraction aids in the extraction of the best feature from data sets by selecting and
combining variables into functions.

F. Disease Classifications
It is the method of using our qualified deep learning model to recognize plant disease. A digital camera or equivalent system should
be used to take an image of the contaminated plant's leaf. Open CV was used to scan the image. Then it determines what category
of plant it is.

VI. CONCLUSIONS
The proposed system tracks the cultivated field on a regular basis. The CNN algorithm is used to identify crop diseases at an early
stage. Machine learning methods are used to train the model, which helps in making appropriate disease decisions. To contain
infected diseases, the farmer is advised to use pesticides as a cure.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 6307
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue V May 2023- Available at www.ijraset.com

In the future, the proposed scheme could be expanded to provide additional facilities such as nearby government markets, pesticide
price lists, and a nearby open market, among others. Some of the organisms on which the proposed algorithm is evaluated include
bananas and jackfruit. To prevent losses, smallholder farmers are dependent on a timely diagnosis. In this study a pre-trained CNN
was fine-tuned and the model was developed online, with very less computational effort the optimum results were obtained which
shows the efficiency of proposed algorithm a merit of using this method is that the plant disease can be identified in a very early
stage. We proposed a CNN based on Deep learning for plant disease classification eliminating possible hazards. Convolution neural
network and Deep neural network algorithms may be used to increase accuracies in the classification process.

REFERENCES
[1] Panigrahi, K.P.; Das, H.; Sahoo, A.K.; Moharana, S.C. Maize leaf disease detection and classification using machine learning algorithms. In Progress in
Computing, Analytics and Networking; Springer: Singapore, 2020.
[2] Mohsin Kabir, M.; Quwsar Ohi, A.; Mridha,M.F. A Multi-plant disease diagnosis method using convolutional neural network. arXiv 2020,
arXiv:2011.05151.
[3] Prodeep, A.R.; Hoque, A.M.; Kabir, M.M.; Rahman, M.S.; Mridha, M.F. Plant Disease Identification from Leaf Images using Deep CNN’s EfficientNet. In
Proceedings of the 2022 International Conference on Decision Aid Sciences and Applications (DASA), Chiangrai, Thailand, 23–25 March 2022; pp. 523–527.
[4] Tan, C.; Sun, F.; Kong, T.; Zhang, W.; Yang, C.; Liu, C. A Survey on Deep Transfer Learning. In Proceedings of the 27th International Conference on
Artificial Neural Networks, Rhodes, Greece, 4–7 October 2018; pp. 270–279.
[5] H. Al-Hiary, S. Bani-Ahmad, M. Reyalat, M. Braik and Z. ALRahamneh “Fast and Accurate Detection and Classification of Plant Diseases”, 2011
[6] André S. Abade, Paulo Afonso Ferreira and Flávio de Barros Vidal “Plant diseases recognition on images using convolutional neural networks: a systematic
review” ,2020
[7] Guo, X., Zhang, M., & Dai, Y.,” Image of Plant Disease Segmentation Model Based on Pulse Coupled Neural Network with Shuffle Frog Leap
Algorithm.”,2018.
[8] Chouhan, S. S., Kaul, A., & Singh, “A deep learning approach for the classification of diseased plant leaf images.”,2019.
[9] Kumar, M., Gupta, P., Madhav, P., & Sachin, “Disease Detection in Coffee Plants Using Convolutional Neural Network”,2020
[10] .

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 6308