Table 7.
Performance of MolScribe and DECIMER Image-Transformer on four distorted benchmark datasets
MolScribe | DECIMER | |||
---|---|---|---|---|
Pi | T | Pi | T | |
JPO_dist | 56.44% | 0.94 | 40.00% | 0.79 |
CLEF_dist | 73.84% | 0.96 | 58.59% | 0.89 |
UOB_dist | 87.25% | 0.99 | 55.42% | 0.91 |
Ingido_dist | 36.12% | 0.97 | 2.66% | 0.40 |
Average | 63.41% | 0.96 | 39.17% | 0.75 |
The performance is described as the proportion of occurrences of identical predictions Pi and the average Tanimoto similarity T.