Oil Palm Fruit Maturity Classification Algorithm Based on LAB Dual-Branch Feature Fusion

Accurate classification of oil palm fruit maturity is critical for optimizing harvest schedules and maximizing yield. To address the limited discrimination accuracy caused by subtle color variations, this paper proposes an LAB dual-branch feature fusion method for five-class oil palm fruit maturity classification. A classification model named CMF-Net is constructed, in which the luminance (L) and chrominance (ab) components are decoupled into two parallel branches to separately extract structural and color information. An input adaptation module is introduced to perform channel mapping and feature enhancement. During feature fusion, a gated fusion mechanism is employed for adaptive integration of the dual-branch features, followed by a BiFPN module for multi-scale feature interaction. A multi-level attention enhancement module composed of coordinate attention and self-attention is designed to strengthen key-region perception and global contextual modeling. An auxiliary color regression constraint and ordinal supervision are incorporated to improve the model’s sensitivity to subtle chromatic changes and the progressive relationship among maturity stages. The proposed algorithm provides a color-decoupled and order-aware representation framework for gradual fruit maturity classification, offering a useful reference for fine-grained agricultural visual classification tasks involving continuous color transitions. Experimental results on a public dataset show that CMF-Net achieves a validation accuracy of 94.66%, outperforming mainstream models by 1.3–6.1 percentage points, while also yielding superior recall and F1-score.