Interpretable Prototype-Based Classification of Charcoal-Canker and Bleeding-Canker Bark Symptoms in Cork Oak (Quercus suber L.)

Cork oak (Quercus suber L.) woodlands are ecologically and economically important and are threatened by a decline syndrome in which the endophytic ascomycete Biscogniauxia mediterranea (De Not.) Kuntze (charcoal canker) and the soil-borne oomycete Phytophthora cinnamomi Rands (root rot and bleeding cankers) play prominent roles. This study investigates whether a small set of real, representative bark images can provide an interpretable, field-oriented aid for classifying bark symptoms. We assembled 1,195 publicly available images labelled from their source captions as asymptomatic, charcoal-canker symptoms, or bleeding-canker symptoms; the labels describe visible symptoms and were not confirmed by laboratory diagnosis. Features were extracted with a frozen MobileNetV3-Small network, and per-class k-means or k-medoids clustering was used to select real images closest to cluster centres (“pseudo-centroids”), which were then used as references for k-nearest-neighbour (KNN) classification. On a held-out set of 239 images, the practical configuration with four reference images per class reached 72.8% accuracy (95% CI 66.8–78.1%) and the best configuration (10 per class) 79.1% (73.5–83.8%). Exact McNemar tests and 30 repeated, leakage-free splits showed no reliable differences among the three KNN variants, and geometric or AutoAugment-type augmentation of the minority class did not change accuracy. Swapping the labels of two reference images reduced accuracy by 9.8 ± 3.8 percentage points with four references per class and by 4.8 ± 2.1 points with ten. Bleeding-canker symptoms were the most difficult class, reflecting their high visual heterogeneity, overlap with the other classes and small sample size. Using all training images as references raised accuracy to 91.1%, quantifying the cost of a compact card set. The reference cards are therefore best viewed as a visual screening and training aid that complements, rather than replaces, established field keys and laboratory confirmation.