Rep-MobileViT: Texture and Color Classification of Solid Wood Floors Based on a Re-Parameterized CNN-Transformer Hybrid Model

Abstract

In the context of intelligent manufacturing for furniture, the classification of solid wood floors is critical for automating quality control and enhancing production efficiency. The final aesthetic of installed solid wood floors largely depends on the uniformity of color and texture. However, most current research does not address the simultaneous classification of both texture and color in solid wood floors, and there is a notable gap in studies focusing on the classification of color-difference wood floors and white-edge wood floors. This paper proposes a re-parameterized CNN-Transformer hybrid architecture based on the MobileViT model, named Rep-MobileViT. Specifically, the RepAIRB module is introduced, incorporating an asymmetric convolutional block (ACB) and a re-parameterized structure within the inverted residual block (IRB) module to enhance the network’s receptive field without increasing computational costs. Additionally, the RepMFF-MobileViT modu le is designed, utilizing a multi-feature fusion strategy and the RepTransformer structure to reduce the number of parameters while improving the network’s expressiveness and stability. In the preprocessing stage, a contrast-limited adaptive histogram equalization and brightness blending (CLAHE-LB) technique is employed to enhance image clarity, highlighting texture details while preserving original color information. Experimental results indicate that the proposed method achieves an overall classification accuracy of 94.98%, with a processing time of only 20.94 ms. Comparative analyses demonstrate that this approach outperforms existing machine learning methods by over 12% in classification accuracy.