Advanced Apple Sorting and Quality Grading Application Using Graph Neural Networks, Vision Transformers, and Convolutional Neural Networks

In the agriculture sector, assessing apples for quality is crucial for both market sales and international commerce. Traditional procedures, including human grading, need experienced employees and take a long time. Grading in a lab is also very costly. Farmers on a limited budget require a quick and precise means to pick along with grade apples, and there is a need for them. Our work addresses these limitations by building a smart and automated approach for quality grading of the Advanced Apple Sorting Application. The primary goal is to integrate 3 types of models, Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Graph Neural Networks (GNNs) to create a smart, automated software for grading apples. We are using a CNN model to extract important features such as surface texture coloration patterns and defects which are critical for our quality evaluation. The CNNs are primarily interested in localized features and find it difficult to observe the entire context of an image. But CNNs individually concentrate on local features but lack global structural relationships. For this we are utilizing ViTs self-attention mechanisms to examine the whole apple image simultaneously, enabling them to pick up on slight differences in shape size and color. While ViTs take a global view they might miss finer details. Finally, we use GNNs to improve classification accuracy by detecting important attributes such as weight diameter and ripeness. This guarantees a more consistent grading process that is not limited to simple pixel based analysis. GNNs bridge this gap by learning physical relationships and enhancing classification stability. By integrating these three modules, the system can extract fine-grained features and comprehend the global structure of the image. This results in a more accurate grading process. We have also developed an easy to use web and Android Application that farmers can grade apples promptly and efficiently. Our model has been tested and trained using various kinds of Apple datasets.