Agricultural Research Management Information System

Home
Research Summary
Search
About Us
- ARMIS
- Brochure
Contact Us
Report
User Request
Data Input
Help
- Operation Manual
  - PDF
  - Video
- Program Area & Commodity
We have reached 37600 number of research entries at this moment.

- Logout

Research Detail

Home
Research
Detail

Machine Vision Based Papaya Disease Recognition

Md. Tarek Habib
Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh

Anup Majumder
Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh

Abstract/ Executive Summary:

Over the years little research has been performed for vision-based papaya disease recognition system inorder to help distant farmers, most of whom require proper support for cultivation. Due to advancementof vision-based technology we find a good solution to this problem. Papaya disease recognition mainlyinvolves two challenging problems: one is disease detection and another is disease classification.Considering this scenario, here we present an online machine vision-based agro-medical expert system that processes an image captured through mobile or handheld device and determines the diseases inorder to help distant farmers to address the problem. Some experiments are performed to show theutility of the proposed expert system. First, we propose a set of features from the view point of distin-guishing attributes. K-means clustering algorithm is used in order to segment out the disease-damaged region from the captured image and then required features are extracted to classify the diseases with the help of support vector machine. More than 90% classification accuracy has been achieved, which appears to be good as well as promising by comparing performances obtained with recently reported relevant works

Keywords: Papaya disease, Agro-medical expert system, Machine visionk-means clustering, Support vector machine

Location:

Start Date:

End Date:

Program Area: Pest Management

Commodity: Papaya

Objectives:

In this paper, we perform an in-depth exploratory research onpapaya disease recognition following machine vision based approach. We propose an agro-medical expert system that can pro-cess papaya image and recognize the contamination of any disease in it. A feature set has been proposed for recognizing the diseases.Image processing techniques are used to extract the features from images. Then support vector machine (SVM) is used for successful classification of the diseases. The system is supposed to work almost in real time.

Methodology:

The architecture of online machine vision-based agro-medicalexpert system for recognizing the papaya disease. It originates with the hypothesis that someone, i.e. a farmeror a user captures an image of a disease affected papaya using amobile phone or handheld device, where the proposed mobileapp is already installed. Then he/she will send the image to our proposed expert system by using the app. After receiving the image through Internet at front-end software, it is sent to the back-endserver, where our agro-medical expert system installed. The sys-tem will give its feedback based on the input image. The feedback will be dispatched as an SMS to the user’s handheld device through the front-end software. 4. Research methodology- a solution frame work to the problem of machine vision-based papaya disease recognition. It commences with acolor image of faulty papaya. The image data are collected locallyas well as from Internet. First, the image is converted into afixed-sized image by using bicubic interpolation (Bicubicinterpolation, xxxx). Suppose the intensity valuesIand the deriva-tivespx;pyandpxyare known at the four corners (0, 0), (0, 1), (1, 0)and (1, 1) of the unit square.

Source of Information: Computer and Information Sciences 32 (2020) 300–309

Article Link (Online Journal):

Funding Source:

1.

Budget:

Total Budget (Tk.) :

Achievement/Findings:

In this paper, we have presented a machine vision-based agro-medical expert system. Here, we have presented a two-feature setconsisting of ten features in total to solve papaya disease recogni-tion. Image processing techniques have been employed to extractthe features. The classification of the papaya diseases has been accomplished with SVM and the relative merits of our work have been assessed by analyzing results of similar works thereafter. We achieved an accuracy of 90.15%, which is good as well aspromising. There remains a potential future work with a very large data set of images to cover a wider range of papaya diseases.

Knowledge Management: Journal