Traditional deep learning methods employing 2D images can only classify healthy and unhealthy seedlings; consequently, this study proposes a method by which to further classify healthy seedlings into primary seedlings and secondary seedlings and finally to differentiate three classes of seedling through a 3D point cloud for the detection of useful eggplant seedling transplants. Initially, RGB images of three types of substrate-cultivated eggplant seedlings (primary, secondary, and unhealthy) were collected, and healthy and unhealthy seedlings were classified using ResNet50, VGG16, and MobilNetV2. Subsequently, a 3D point cloud was generated for the three seedling types, and a series of filtering processes (fast Euclidean clustering, point cloud filtering, and voxel filtering) were employed to remove noise. Parameters (number of leaves, plant height, and stem diameter) extracted from the point cloud were found to be highly correlated with the manually measured values. The box plot shows that the primary and secondary seedlings were clearly differentiated for the extracted parameters. The point clouds of the three seedling types were ultimately classified directly using the 3D classification models PointNet++, dynamic graph convolutional neural network (DGCNN), and PointConv, in addition to the point cloud complementary operation for plants with missing leaves. The PointConv model demonstrated the best performance, with an average accuracy, precision, and recall of 95.83, 95.83, and 95.88%, respectively, and a model loss of 0.01. This method employs spatial feature information to analyse different seedling categories more effectively than two-dimensional (2D) image classification and three-dimensional (3D) feature extraction methods. However, there is a paucity of studies applying 3D classification methods to predict useful eggplant seedling transplants. Consequently, this method has the potential to identify different eggplant seedling types with high accuracy. Furthermore, it enables the quality inspection of seedlings during agricultural production.

Traditional seed supply chains face several hidden risks. Certain regulatory departments tend to focus primarily on entity circulation while neglecting the origin and accuracy of data in seed quality supervision, resulting in limited precision and low credibility of traceability information related to quality and safety. Blockchain technology offers a systematic solution to key issues such as data source distortion and insufficient regulatory penetration in the seed supply chain by enabling data rights confirmation, tamper-proof traceability, smart contract execution, and multi-node consensus mechanisms. In this study, we developed a system that integrates blockchain and neural networks to provide seed traceability services. When uploading seed traceability information, the neural network models are employed to verify the authenticity of information provided by humans and save the tags on the blockchain. Various neural network architectures, such as Multilayer Perceptron, Recurrent Neural Network, Fully Convolutional Neural Network, and Long Short-term Memory model architectures, have been tested to determine the authenticity of seed traceability information. Among these, the Long Short-term Memory model architecture demonstrated the highest accuracy, with an accuracy rate of 90.65%. The results demonstrated that neural networks have significant research value and potential to assess the authenticity of information in a blockchain. In the application scenario of seed quality traceability, using blockchain and neural networks to determine the authenticity of seed traceability information provides a new solution for seed traceability. This system empowers farmers by providing trustworthy seed quality information, enabling better purchasing decisions and reducing risks from counterfeit or substandard seeds. Furthermore, this mechanism fosters market circulation of certified high-quality seeds, elevates crop yields, and contributes to the sustainable growth of agricultural systems.