Convolutional Neural Networks for Rotten Fruit Detection Using MATLAB

Chai, Cheng Foong (2021) Convolutional Neural Networks for Rotten Fruit Detection Using MATLAB. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

Text Chai Cheng Foong.pdf Restricted to Registered users only Download (2MB)

Abstract

Human beings need food which provides nutrients to stay alive. Out of so many type of food, fruit is one of the food that can provide essential nutrients. However, fruit will get rotten due to the spread of bacteria. Therefore, it is important for food industry to perform inspection on fruits before selling to the consumers. The problem in this case is the human inspection has lower consistency and accuracy as human will get tired after a long period of time. To solve this problem, an algorithm to detect rotten fruits is designed and developed in this project. The proposed method consists of deep learning technique which is Convolutional Neural Networks (CNNs) for feature extraction and classification of rotten fruits. This proposed method is designed and developed in MATLAB as the deep learning platform. The types of fruits that will be detected and classified in this project are banana, apple and orange. The validation accuracy obtained in this project is 99%. The total duration of training stage is 212.13 minutes. The required time to classify single fruit image is approximately 0.2 second.