Plant disease detection

This project covered the zone of image processing and deep learning components of software engineering. It is a deep learning application to approach to detect disease Pests like viruses, fungus, and bacteria in plants. Deep learning  (DL) has emerged as a versatile tool to assimilate larg

Project Title

Plant disease detection

Project Area of Specialization

Artificial Intelligence

Project Summary

This project covered the zone of image processing and deep learning components of software engineering. It is a deep learning application to approach to detect disease Pests like viruses, fungus, and bacteria in plants. Deep learning  (DL) has emerged as a versatile tool to assimilate large amounts of heterogeneous data and provide reliable predictions of complex and uncertain phenomena. These tools are increasingly being used by plant science. Image processing provides more efficient ways to detect diseases caused by fungus, bacteria or viruses on plants. Observations by eyes to detect diseases are not accurate. To classify diseases in agricultural applications image processing techniques is used to detect the diseases

Image processing and image acknowledgment of plant and harvests can empower us to screen they're well being, identify illnesses and build up an application that would keep farmers informed about the health of the crops. The extensive number of crops experience the ill effects of infections because of different reasons which can, therefore, influence the ones who eat them.

 farmers have no other explanation crops to examine the harvests themselves or counsel their senior/experienced farmers about the illness obviously their suggestions can't be right or exact constantly. Along these lines,, it will be viable and plausible if farmers have an application that can educate about the strength of the plant by simply floating the portable smartphone over it.

Identification of the plant diseases is important to our agriculture areas which are preventing the losses in the yield and quantity of the agricultural product. Studies of the plant diseases mean the studies of visually observable patterns seen on the plant. Health monitoring and disease detection on the plant is very critical for sustainable agriculture. It is very difficult to monitor plant diseases manually. It requires a tremendous amount of work, expertise in the plant diseases, and also requires excessive processing time. 

Project Objectives

Plant infections cause production and financial misfortunes in the agricultural industry. Plant disease management is a difficult undertaking. We engineers and researchers have taken upon ourselves the task to introduce ease in the detection of Plant disease with the help of Image processing, as it provides the best results and reduces human efforts and will also shorten the time to react to the damage thus preventing damage crop and financial losses. My aim in this task is to make an application that will recognize the disease in different vegetables or fruits to provide feasibility and production boost to the agriculture sector. Plant infections cause production and financial misfortunes in the agricultural industry. Plant disease management is a difficult undertaking. We engineers and researchers have taken upon ourselves the task to introduce ease in the detection of Plant disease with the help of Image processing, as it provides the best results and reduces human efforts and will also shorten the time to react to the damage thus preventing damage crop and financial losses. My aim in this task is to make an application which will recognize the disease in different vegetables or fruits to provide feasibility and production boost to the agriculture sector

Project Implementation Method

The entire procedure of developing the model for plant disease recognition using deep CNN is described further in detail. The complete process is divided into several necessary stages into subsections below, starting with gathering images for the classification process using deep neural networks. Dataset. are required at all stages of object recognition research, starting from the training phase to evaluating the performance of recognition algorithms. Images in the dataset were grouped into different classes.  classes represented plant diseases that could be visually determined from leaves. To distinguish healthy leaves from diseased ones, one more class was added in the dataset. It contains only images of healthy leaves. An extra class in the dataset with background images was beneficial to get a more accurate classification. Thus, a deep neural network could be trained to differentiate the leaves from the surrounding. Image Preprocessing and Labelling. were in various formats along with different resolutions and quality. To get better feature extraction, final images intended to be used as the dataset for deep neural network classifiers were preprocessed. The main purpose of applying augmentation is to increase the dataset and introduce slight distortion to the images which help in reducing overfitting during the training stage Neural Network Training. Training the deep convolutional neural network for making an image classification model from a dataset. Besides, there is Caffe, an open-source deep learning framework developed by the BVLC. Caffe framework is suitable for both research experiments and industry deployment. CNN which has multiple layers that progressively compute features from input images. This neural network module is interconnected to the karas algorithm which is run and request to the server through an app and diagnosed the disease. Development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks... The developed model can recognize different types of plant diseases out of healthy leaves, with the ability to distinguish plant leaves from their surrounding deep learning (DL) has emerged as a versatile tool to assimilate large amounts of heterogeneous data and provide reliable predictions of complex and uncertain phenomena. These tools are increasingly being used by plant science. Image processing provides more efficient ways to detect diseases caused by fungus, bacteria or virus on plants., image processing is used for the detection of plant diseases. Disease detection involves steps like image acquisition, image pre-processing, image segmentation, feature extraction, and classification. But we discussed the methods used for the detection of plant diseases using their leaves images. some segmentation and feature extraction algorithm used in the plant disease detection.

Benefits of the Project

Diseases full plants are destroyed day by day and farmers are not recognized which types of diseases have infected the plants so our plant disease detection application is very helpful for farmers which do not know about the disease.

To minimize the disease-induced damage in crops during growth, harvest and postharvest processing, as well as to maximize productivity and ensure agricultural sustainability, advanced disease detection, and prevention in crops are highly important.

The purpose of this project is to obtain an image from the farmer of the diseased crop preferably the stem or the leaves through the Android Application installed on the farm owner's phone. The image is then processed using the image-processing technique and the disease type is detected. The diseases affected the crop and the amount of fertilizer or the pesticide/insecticide to be used is updated to the Android Application that was previously used by the farmer to upload the image.

One of the major problems which are faced by farmers is the “Biological Problem” (problem present in leaves). They also do not get the result as they are expecting for which is the main reason that most people do not want to do farming.

It helps farm owners by identifying the disease present in their plants' leaves and to provide the best possible solution for that disease. To enhance the productivity of farming and to develop an interest in farming. To reduce the effort of farmer in terms of time and money

Technical Details of Final Deliverable

we develop both mobile and web both applications are available so recently used a local server if anyone uses our web application so all of the people connect to the same IP address because we used a local server. Our project is based on two applications, one is a web application in which we upload pictures of a plant and it will inform us about the disease of our plant and features of the picture. Another application is a mobile application, in which we also upload a picture in the application and it will inform about the disease of plants and precautions of plants.
This all process will be done on a local server, in which whole data will be saved in the user device but if we transfer it into a cloud server it will be also saved in it and we can easily recover our data if we lost it.

Final Deliverable of the Project

Software System

Core Industry

Agriculture

Other Industries

Manufacturing

Core Technology

Artificial Intelligence(AI)

Other Technologies

Others

Sustainable Development Goals

No Poverty, Good Health and Well-Being for People, Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com