Identifying forged seal imprints using positive and unlabeled learning

Abstract

Nowadays with the development of photosensitive seal technology, the seal fraud events have gradually increased. Forged seals can bring considerable benefits to counterfeiters, and will also bring huge losses to companies and users. Since it is almost impossible to collect enough forged seal samples, traditional machine learning methods do not work in this situation. In this paper, a method based on PU learning and distance learning is proposed. This method uses a limited number of labeled samples and some unlabeled samples to train multiple kNN classifiers to identify forged seal imprints, and use distance learning to improve the performance of kNN classifiers. The experimental results show that the F1-score of the proposed method can reach 0.97 regardless of the seal imprints with lots of text background noise, which outweighs many traditional models.