Mango Grading System Based on Optimized Convolutional Neural Network

Abstract

In order to achieve the accuracy of mango grading, a mango grading system was designed by using the deep learning method. The system mainly includes CCD camera image acquisition, image preprocessing, model training, and model evaluation. Aiming at the traditional deep learning, neural network training needs a large number of sample data sets; a convolutional neural network is proposed to realize the efficient grading of mangoes through the continuous adjustment and optimization of super-parameters and batch size. The ultra-lightweight SqueezeNet related algorithm is introduced. Compared with AlexNet and other related algorithms with the same accuracy level, it has the advantages of small model scale and fast operation speed. The experimental results show that the convolutional neural network model after super-parameters optimization and adjustment has excellent effect on deep learning image processing of small sample data set. Two hundred thirty-four Jinhuang mangoes of Panzhihua were picked in the natural environment and tested. The analysis results can meet the requirements of the agricultural industry standard of the People’s Republic of China—mango and mango grade specification. At the same time, the average accuracy rate was 97.37%, the average error rate was 2.63%, and the average loss value of the model was 0.44. The processing time of an original image with a resolution of 500 × 374 was only 2.57 milliseconds. This method has important theoretical and application value and can provide a powerful means for mango automatic grading.

Điều khiển hai biến nhiệt độ và độ ẩm đồng bộ sử dụng bộ điều khiển mờ trong nhà màng trồng ớt chuông

“…Hệ thống tưới nước có thể được kết hợp với phân bón hoặc chất dinh dưỡng để cung cấp các chất cần thiết cho cây trồng. Với sự phát triển của khoa học và công nghệ tại Việt Nam, nhiều hệ thống tự động được ứng dụng cho nhiều lĩnh vực khác nhau đặc biệt là trong nông nghiệp [3,4]. Để có thể xuất khẩu và nâng cao chất lượng sản phẩm nông sản các công nghệ cần được ứng dụng vào các hệ thống canh tác nông nghiệp, đây được xem là thách thức đối với ngành nông nghiệp hiện này [5].…”

A Review on Automated Detection and Assessment of Fruit Damage Using Machine Learning

“…Machine learning is a preferred and efficient technique to perform various tasks such as segmentation and classification [94]. However, deep learning state-of-art techniques have also been recently used [84], [128] due to their ability to extract features directly from datasets [22].…”

Maturity grading of jujube for industrial applications harnessing deep learning

“…Furthermore, a fuzzy incremental training algorithm with a precision of around 87% was used for grading. Article (Zheng and Huang, 2021), also presents the grading system for mango using the deep learning concept. An ultra-lightweight model based on SqueezeNet architecture was introduced which achieves an average accuracy of 97.37% over the training samples of 234 mango images belonging to 4 grades.…”