Research on ink color matching method based on CNN-Transformer model

This paper proposes a CNN-Transformer hybrid model for ink formulation prediction, named CTNet. The model leverages Convolutional Neural Networks (CNN) to extract local features from the spectral reflectance of sample surfaces and incorporates the self-attention mechanism of the Transformer to achieve efficient mapping between color and formulation. In addition, Bayesian optimization is introduced for hyperparameter tuning, further enhancing model performance. Experimental results demonstrate that CTNet outperforms CNN, RNN, LSTM, and the standard Transformer model in terms of Mean Absolute Error (MAE), achieving higher prediction accuracy. This provides an effective solution for high-precision and automated ink color matching, showing promising potential for industrial applications.