Sign Language Recognition using Improved Seagull Optimization Algorithm with Deep Learning Model

Sign Language Recognition (SLR) covers the ability to translate Sign Language (SL) signals into written or spoken languages. This technique is useful for hearing-impaired people by offering them an effective method to communicate with persons having trouble in recognizing SLs. It can also be employed for generating automatic captions in real-time for live actions and videos. Various models of SLR include machine and deep learning, and computer vision techniques. A commonly employed technique involves using a camera to capture the body and hand movements of the signer, processing the video data to identify the signs. One of the high tasks of SLR includes the flexibility in SL over numerous individuals and cultures, the complex of definite signs, and the need for real-time process. This manuscript presents a SL Recognition Using an Improved Seagull Optimization Algorithm with Deep Learning (SLR-ISOADL) methodology. The SLR-ISOADL approach aims to exploit a hyperparameter-tuned DL model to recognize and classify the SLs. In the SLR-ISOADL approach, a bilateral filtering (BF) approach can be applied to get rid of the noise. For learning and deriving intrinsic patterns, the SLR-ISOADL approach employs the AlexNet model. Besides, the ISOA can be applied for optimal hyperparameter election of the AlexNet model. Finally, the multilayer perceptron (MLP) technique can be exploited to detect and classify the SLs. The analytical experiment of the SLR-ISOADL technique is conducted on a benchmark dataset. The investigational analysis highlighted that the SLR-ISOADL technique gains enhanced detection outcomes in terms of distinct measures.