Development of fully automatic fruit grader and sorter using image processing

Pakistan is an agricultural country as 70% of the population directly rely on agriculture as a source of living. Agriculture plays a vital role in the economic progression of Pakistan. Despite being an agrarian country, Pakistan lags in innovation and efficiency. This is because of old methods being

Project Title

Development of fully automatic fruit grader and sorter using image processing

Project Area of Specialization

Electrical/Electronic Engineering

Project Summary

Pakistan is an agricultural country as 70% of the population directly rely on agriculture as a source of living. Agriculture plays a vital role in the economic progression of Pakistan. Despite being an agrarian country, Pakistan lags in innovation and efficiency. This is because of old methods being used for centuries to get work done which act as a bottleneck for productivity. For instance, fruit production and export require vigilant inspection throughout the process to ensure standard and uniform quality. Usage of human labour or manual grading to inspect, sort and classify the fruits leads to lower productivity and inconsistent results

Manual grading of agricultural products is not only difficult but due to shortage of labour in peak season it is more costly and it is more time consuming. It is inconsistent and less efficient. Farmers are looking forward to having an appropriate automated machine to reduce the labour. The proposed project is a grading machine which will be based on the concept of automation that will help famers save time and will be able to improve graded product’s quality.

The aim of this project is to design and develop a non-destructive fruit grader and sorter which will be fully automated, and which will classify fruits in different categories. The fruit on a conveyer system will pass through an optical sensor which captures the image of the product.  By applying image processing techniques on images, the characteristics features of the products such as shape, size, color, and texture will be extracted. The product will be classified into different categories based on the extracted features. The data from the fruit graders after grading will be stored in cloud-based database which can be assessed through mobile application.

Project Objectives

The main objectives of this project are:

• Development of a system capable of identifying fruits based on color, shape and size
• Implementation of digital image processing for pre-processing and extracting features from the images
• Implementation of a classifier based on machine learning to classify fruits based on extracted features from the images into different categories
• Development of a database which will store records of graded fruits for improving the quality of fruits in the agriculture sector
• Development of a mobile application to access graded fruits records in the database

Project Implementation Method

A container having agricultural products is placed allowing the products to be placed one by one on the conveyor belt for its processing. An optical sensor mounted will capture the image of the fruit.

After capturing the image of the fruit, various pre-processing techniques are applied to the image. The unwanted objects are removed from the captured images which is also known as background subtraction. The noise which can occur due to lighting issues or while capturing image of a moving object is also removed using gaussian and median filters.

The ripeness of the fruit can be detected by the color and size of the fruit. Therefore, we are extracting color and size feature of the fruit. After pre-processing, Color features are extracted from the image using various color spaces such as HSV, LAB and RGB. The area of the image is the total number of pixels in the image. It is calculated by transforming the original image into binary image. The calculated area is used as the size feature and is stored in the data frame along with the color features. The extracted features are fed to the classifier. We have implemented random forest classifier and support vector machine for classification of data extracted from the images.

After classification, the fruits are sorted in different categories  based on the results obtained from classification using pushers which are operated using microcontroller. The results obtained after classification are stored in the database. A mobile application has been developed to access the records of graded fruit present in the database.

The block diagram of the system is as follow: 

https://www.dropbox.com/s/92thuzqww8jrfaf/Block-diagram-of-the-system.png?dl=0

The diagram for the visualization of working of application is given below: 

https://www.dropbox.com/s/3cpr7b2gpdcxji0/Visualization-of-working-of-application.png?dl=0

Benefits of the Project

Manual labour is tedious and costly. It is time consuming and can result in improper grading due to human operation. This project tends to be cost effective and can sort agricultural products effectively to improve the efficiency and accuracy of fruit grading without minimum human input in the markets and industries. The benefits of this project are given below:

• Human error will be minimized, and spoiled products will be separated leading to both more revenue and health benefits
• Farmers will be able to sort fruits using this sorter and thus eliminating the need of extra labour
• Furthermore, more revenue will be generated by farmer and products will become cost-effective for the customers
• A consistency in quality will help to increase demands for Pakistani fruits and vegetables in foreign markets
• Agriculture sector of Pakistan will receive an innovative solution and it will also pave way for further innovation

Technical Details of Final Deliverable

Intended project is all about delivering best quality fruits. This ultimately leads to better health and more revenue for the farmers. A sophisticated approach involving well organized and coordinated array of varied components has been designed. The core of the project is optical sensor. A Camera is used for its high frame rate and pixel density. Optical sensor captures the image of product which is then processed for identification and feature extraction. Along with optical sensor, importance of conveyor belt cannot be ignored. Its speed is synchronised with frequency of optical sensor and also the time required for complete identification of the product. Using image processing, color and size of the fruit can be extracted from the image captured using the optical sensor. Microcontroller uses all of the data coming from sensors to make a decision about its quality using machine learning. After successful classification, microcontroller signals the flapper to place the product in desired box according to its quality and upload the data obtained after classification to the database. A mobile application will be used as gateway to the data stored in the database.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Food

Other Industries

IT , Agriculture , Telecommunication

Core Technology

Internet of Things (IoT)

Other Technologies

Artificial Intelligence(AI), Cloud Infrastructure, Shared Economy, Others

Sustainable Development Goals

No Poverty, Zero Hunger, Good Health and Well-Being for People, Decent Work and Economic Growth, Industry, Innovation and Infrastructure, Responsible Consumption and Production

Required Resources

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