Offline handwritten signature verification under a stream context with partially labeled data

Handwritten signature verification is a biometric authentication task that distinguishes genuine from forged signatures. Traditional offline methods rely on batch learning, which struggles with signature variability and limited labeled data. Recent advances in stream-based approaches have improved adaptability but still depend on fully labeled training data, which is impractical for real-world applications. This paper extends prior work by introducing a framework that integrates partially labeled data with active learning to enhance verification performance in a streaming context. We introduce a novel query strategy based on the k-disagreeing neighbors score, which prioritizes ambiguous samples near decision boundaries. Experimental results demonstrate that the proposed approach adapts to new signature variations while improving performance with minimal labeled data. Random sampling proves surprisingly effective by leveraging the structured dissimilarity space, while the k-disagreeing neighbors strategy provides more stable performance over time. The implementation is available at https://github.com/kdmoura/stream_hsv .