Reliability-Aware Active Crowdsourcing and Ontology-Constrained Multi-Evidence Clustering for Agricultural Multimedia Knowledge-Base Construction

Constructing agricultural multimedia knowledge bases is complicated by heterogeneous evidence, noisy crowdsourced annotations, variations in sample difficulty, and inadequate integration of multisource information. Using tomato disease and pest data, this study proposes a unified framework comprising Multi-evidence Reliability-Aware Active Crowdsourcing (MRAC) and Ontology-Constrained Multi-Evidence Clustering and Refinement (OMCR). MRAC jointly models annotator reliability, sample difficulty, content-evidence quality, and evidence availability. It selects sample-annotator pairs according to the expected information gain per unit cost and produces calibrated soft-label posteriors. OMCR integrates frozen visual features, crowdsourcing posteriors, and agricultural ontology constraints, and uses class prototypes, pairwise constraints, and risk scores for sample clustering, mislabeled-instance detection, and label refinement. Under 30% synthetic annotation noise, MRAC achieved an Accuracy of 0.9732 and a Macro-F1 of 0.9676. MRAC-EIG achieved the highest mean Macro-F1 (0.9631) and the lowest mean relative annotation cost (1.0080) among the evaluated policies. The complete OMCR model achieved ACC, NMI, and ARI values of 0.9708, 0.9293, and 0.9500, respectively. The unified framework achieved Precision@5, Precision@10, and nDCG@10 values of 0.9251, 0.9223, and 0.9233, respectively, with a 14.97% relative improvement in nDCG@10 over visual-only retrieval. These results show that the proposed framework improves noisy-label aggregation, multi-evidence knowledge organization, and retrieval ranking while controlling annotation costs, offering a practical route to reliable agricultural multimedia knowledge-base construction.