Research on multimodal image classification based on hybrid network model
HUANG Xilin
HONG Lan
Abstract：A multimodal image classification study based on a hybrid network model is proposed to address the problems of low completeness in extracting multimodal feature vectors and poor accuracy in image classification in existing image classification methods.Using regularization operations,logarithmic transformation algorithms,top hat operation algorithms,and gamma transformation algorithms to preprocess multimodal images,high-quality,high contrast,and high-definition multimodal images were obtained.A hybrid network model(complex network model and convolutional neural network model)was constructed to extract multimodal image feature vectors using complex network models.The multimodal image classification tasks were performed through the multi-level structure of convolutional neural network models(convolutional layer,pooling layer,and fully connected layer),thereby achieving multimodal image classification objectives.The experimental data shows that under different experimental conditions,the maximum completeness of feature vector extraction for multimodal images after the proposed method is 99.03％,and the maximum accuracy of multimodal image classification is 100％.
Keywords：multimodal imagesimage descriptionimage classificationhybrid network model
Publication Date：2024-11-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：8( 38-45 )