Research Article
Intelligent Malaysian Sign Language Translation System Using Convolutional-Based Attention Module with Residual Network
Table 1
Classification report of CBAM-2DResNet “within blocks.”
| | | Precision | Recall | F1-score | Support | | Within blocks | Before classifier | Within blocks | Before classifier | Within blocks | Before classifier | |
| | A | 0.99 | 0.99 | 1.00 | 1.00 | 0.99 | 0.99 | 885 | | B | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 844 | | C | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 932 | | D | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 865 | | E | 1.00 | 1.00 | 0.99 | 0.99 | 0.99 | 0.99 | 893 | | F | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 854 | | H | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 884 | | I | 0.99 | 0.99 | 1.00 | 1.00 | 0.99 | 0.99 | 854 | | K | 0.97 | 0.97 | 0.98 | 0.98 | 0.98 | 0.98 | 865 | | L | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 881 | | M | 1.00 | 1.00 | 0.98 | 0.98 | 0.99 | 0.99 | 886 | | N | 0.99 | 0.99 | 1.00 | 1.00 | 0.99 | 0.99 | 944 | | O | 1.00 | 1.00 | 0.99 | 0.99 | 1.00 | 1.00 | 879 | | P | 0.99 | 0.99 | 1.00 | 1.00 | 1.00 | 1.00 | 883 | | Q | 1.00 | 1.00 | 0.99 | 0.99 | 1.00 | 1.00 | 913 | | R | 1.00 | 1.00 | 0.98 | 0.98 | 0.99 | 0.99 | 917 | | S | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 874 | | U | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 860 | | V | 0.97 | 0.97 | 0.98 | 0.98 | 0.97 | 0.97 | 876 | | W | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 907 | | X | 0.99 | 0.99 | 1.00 | 1.00 | 0.99 | 0.99 | 827 | | Y | 0.99 | 0.99 | 100 | 100 | 1.00 | 1.00 | 846 | | Accuracy | | | | | 0.99 | 0.99 | 19360 | | Macro avg. | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 19360 | | Weighted avg. | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 19360 |
|
|
