# Signature Verification on GPDS Signature Corpus 300 Source: [Signature Verification on GPDS Signature Corpus 300]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:17.908Z Evaluation of signature verification performance on the GPDS Signature Corpus 300 dataset, typically measured using Accuracy, False Acceptance Rate (FAR), and False Rejection Rate (FRR). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Signature Verification | | Dataset (including any stated split) | GPDS Signature Corpus 300 | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [FAR](): Lower is better; unit: PERCENT. - [FRR](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Dutta et al. | 88.79 | Not recorded | 68fa63b91e209131cea005d4 | | Vargas et al. | 87.67 | Not recorded | 68fa63b91e209131cea005d4 | | Ferrer et al. | 86.65 | Not recorded | 68fa63b91e209131cea005d4 | | Kumar et al. | 86.24 | Not recorded | 68fa63b91e209131cea005d4 | | Solar et al. | 84.7 | Not recorded | 68fa63b91e209131cea005d4 | | SigNet | 76.83 | Not recorded | 68fa63b91e209131cea005d4 | | SigNet | 65.36 | Not recorded | 68fa63b91e209131cea005d4 | ### Dutta et al. Accuracy: 88.79. Result ID: 698c1579f729bc7f68e8306f. [Reporting paper]() Recorded evaluation configuration: {"#Signers":"300"}. This record does not assert independent reproduction. ### Vargas et al. Accuracy: 87.67. Result ID: 698c1579f729bc7f68e8306c. [Reporting paper]() Recorded evaluation configuration: {"#Signers":"160"}. This record does not assert independent reproduction. ### Ferrer et al. Accuracy: 86.65. Result ID: 698c1579f729bc7f68e8306b. [Reporting paper]() Recorded evaluation configuration: {"#Signers":"160"}. This record does not assert independent reproduction. ### Kumar et al. Accuracy: 86.24. Result ID: 698c1579f729bc7f68e8306e. [Reporting paper]() Recorded evaluation configuration: {"#Signers":"300"}. This record does not assert independent reproduction. ### Solar et al. Accuracy: 84.7. Result ID: 698c1579f729bc7f68e8306d. [Reporting paper]() Recorded evaluation configuration: {"#Signers":"160"}. This record does not assert independent reproduction. ### SigNet Accuracy: 76.83. Result ID: 698c1579f729bc7f68e83070. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Signers":"300","Forgery Type":"Skilled"}. This record does not assert independent reproduction. ### SigNet Accuracy: 65.36. Result ID: 698c1579f729bc7f68e83071. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Signers":"300","Forgery Type":"Unskilled"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.