Transfer Learning-Based Flower Image Classification: Leveraging The Pre-Trained Alexnet Model

Image classification performs an influential role in the field of computer vision, while deep learning has brought remarkable progress for image classification. Targeting the flower image classification task, this paper proposes a transfer learning-based method to achieve effective flower classification using a pre-trained AlexNet model. This method chooses AlexNet as the base pre-trained model and adapts it to optimize flower classification. To enhance the generalization capability of the model, the training images were resized and data augmented, and appropriate training options were defined to evaluate the model’s classification accuracy through training. Through the analysis of experimental results, this method validates the effectiveness of the proposed method and results in a good performance on the flower image classification, which offers important implications for classification applications and provides strong support for botanical research, flower appreciation, and horticulture, among others.