Identifying forged seal imprints using positive and unlabeled learning

Yan, Lianshan; Chen, Kai; Tong, Shikun; Wang, Jinwei; Chen, Zhe

doi:10.1007/s11042-020-10171-6

Cited by 5 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the seal impression has a blank graphic background with the seal text in red, as shown in Figure 1a. The seal impressions are extracted to conform with the RGB color scheme if the RGB pixel value satisfies Equation (1). It should be noted that, in Asian countries, almost all seals are red circular seals, so Equation ( 1) is very suitable to the experiments in this paper.…”

Section: Color Segmentationmentioning

confidence: 99%

“…Thus, it is difficult for researchers to satisfactorily train machine learning models. Additionally, the limited proportion of negative samples leads to an imbalanced distribution between positive and negative samples, which can result in machine learning classifiers learning a biased decision boundary, effectively classifying all samples as positive [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Representation Learning Method for Circular Seal Based on Modified MLP-Mixer

Cao,

Zhou,

Zhang

et al. 2023

Entropy

View full text Add to dashboard Cite

This study proposes Stamp-MLP, an enhanced seal impression representation learning technique based on MLP-Mixer. Instead of using the patch linear mapping preprocessing method, this technique uses circular seal remapping, which reserves the seals’ underlying pixel-level information. In the proposed Stamp-MLP, the average pooling is replaced by a global pooling of attention to extract the information more comprehensively. There were three classification tasks in our proposed method: categorizing the seal surface, identifying the product type, and distinguishing individual seals. The three tasks shared an identical dataset comprising 81 seals, encompassing 16 distinct seal surfaces, with each surface featuring six diverse product types. The experiment results showed that, in comparison to MLP-Mixer, VGG16, and ResNet50, the proposed Stamp-MLP achieved the highest classification accuracy (89.61%) in seal surface classification tasks with fewer training samples. Meanwhile, Stamp-MLP outperformed the others with accuracy rates of 90.68% and 91.96% in the product type and seal impression classification tasks, respectively. Moreover, Stamp-MLP had the fewest model parameters (2.67 M).

show abstract

Section: Color Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%