@article{CHEN2026, 
author = {Qi CHEN and Bing LI and Lei ZHANG and Xu HUANG},
title = {Research on Recognition of Stamp Impression Types Based on Small Sample Quantity},
year = {2026},
journal = {Chinese Journal of Forensic Sciences},
volume = {2026},
number = {3},
pages = {55-64},
keywords = {document examination, examination of stamp impression, type recognition, convolutional neural network, visual Transformer},
url = {https://www.sciopen.com/article/10.3969/j.issn.1671-2072.2026.03.006},
doi = {10.3969/j.issn.1671-2072.2026.03.006},
abstract = {ObjectiveTo investigate the feasibility of classical computer vision models in recognizing stamp impression types with small sample quantity, as well as the impact of different stamping conditions.MethodsThree network models, VGG16, ResNet50, and visual Transformer, were utilized to identify the kinds of stamp impressions imprinted by six common types of stamps, including photosensitive stamp, laser-engraved penetration stamp, self-inking stamp, copper stamp, wooden stamp, and rubber stamp.ResultsIn the experiment, the three network models performed well in recognizing all six types of stamp impressions. The recognition accuracy for photosensitive stamp, self-inking stamp, wooden stamp and rubber stamp all basically reached 100%, while only a slight decrease was observed in the recognition accuracy for laser-engraved penetration stamp and copper stamp. In the following blind test, the recognition accuracy of the three models for the six types of stamp impressions generally dropped by 3 to 35 percentage points, confirming the limitations of the network models in real complex scenarios.ConclusionClassical models in the field of computer vision can assist in recognizing the types of stamp impressions, but their recognition accuracy needs to be improved.}
}