PSL-mCFRT: A Multi-View Video Dataset for Continuous Finger-Spelling Recognition and Translation in Pakistan Sign Language

a multi-angle comprehensive data set of continuous finger spelling of Pakistan Sign Language (PSL). This dataset is created with the support of domain experts. At first, 70 most commonly terms finger spelled by deaf community were identified and documented. Subsequently, 05 signers including two males and three females finger spelled all these terms individually. This dataset is created using three came views: front, +45o (left) and -45o (right) from the center of signers’ face. In this dataset, there are total 350 videos. All these videos contain continuous signing of identified terms.