A Model for Qur’anic Sign Language Recognition Based on Deep Learning Algorithms

Table 6

QSLRS-CNN accuracy on the test original data before applying sampling for 200 epochs.

Class name	Number of samples in the test data	Number of samples correctly classified	Accuracy
Alif	327	323	98.78%
Ha	312	307	98.40%
Ra	352	352	100.00%
Sin	323	315	97.52%
Sad	364	353	96.98%
Tah	379	370	97.63%
Ayn	427	420	98.36%
Qaf	348	331	95.11%
Kaf	341	320	93.84%
Lam	366	355	96.99%
Mim	368	353	95.92%
Nun	369	357	96.75%
Haa	304	295	97.04%
Ya	326	323	99.08%