Learnable Residual Local Binary Patterns: A Pretraining-Preserving Architecture for Cotton Percentage Estimation in RGB Fabric Images

Automated cotton-percentage identification underpins sustainable textile recycling, but established near-infrared and ATR-FTIR spectroscopy systems cost USD 10,000–25,000 per unit and remain inaccessible to small recyclers. We address this on the CottonFabricImageBD dataset (1300 RGB originals, 13 ordinal cotton classes from 30% to 99%) and report three contributions. First, the Learnable Residual LBP stem, which retains the pretrained ResNet50 first convolution intact and adds a fully differentiable Local Binary Pattern branch as an additive contribution gated by a single learnable scalar α initialized to zero, ensuring the model is numerically equivalent to the baseline at initialization (verified to a maximum absolute logit difference below 10−4). Second, a controlled six-variant comparison (vanilla baseline, CLBP, LBP-Conv, LBP-Residual, LBP+SVM, LBP+ANN) under identical stratified five-fold cross-validation on the 1300 dataset originals. Third, the isolation of pretraining preservation as the dominant architectural variable: the 7.08 pp top-1 gap between LBP-Conv (43.77%) and LBP-Residual (50.85%), both embedding the identical learnable LBP module, is statistically significant (p=0.004, uncorrected paired t-test, df=4) and consistent across all five folds. This gap mainly reconfirms, in the LBP setting, the established cost of discarding pretrained early-layer filters; by contrast, the improvement of LBP-Residual over the vanilla baseline (1.31 pp top-1) is consistent in direction but not statistically significant at the five-fold level (p=0.229), so LBP-Residual, CLBP (50.23% top-1), and the baseline (49.54% top-1) are statistically tied on aggregate accuracy and the ranking among them is exploratory. Classical LBP+SVM and LBP+ANN baselines reach 31.85% and 34.46% top-1, confirming a genuine but limited cotton-density signal in hand-crafted descriptors. Compared to the concurrent triplet-architecture approach of Wiedemann et al. (2025), which achieves 48.15% top-1 accuracy on the same dataset under identical five-fold cross-validation, LBP-Residual attains 50.85% top-1 using a single lightweight backbone rather than an ensemble of three. These results support the design principle: augment, do not replace.