Innovative hand pose based sign language recognition using hybrid metaheuristic optimization algorithms with deep learning model for hearing impaired persons.
Journal:
Scientific reports
PMID:
40102499
Abstract
Sign language (SL) is an effective mode of communication, which uses visual-physical methods like hand signals, expressions, and body actions to communicate between the difficulty of hearing and the deaf community, produce opinions, and carry significant conversations. SL recognition (SLR), the procedure of automatically identifying and construing gestures of SL, has gotten considerable attention recently owing to its latent link to the lack of communication between the deaf and the hearing world. Hand gesture detection is its domain, in which computer vision (CV) and artificial intelligence (AI) help deliver non-verbal communication between computers and humans by classifying the significant movements of the human hands. The emergence and constant growth of DL approaches have delivered motivation and momentum for evolving SLR. Therefore, this manuscript presents an Innovative Sign Language Recognition using Hand Pose with Hybrid Metaheuristic Optimization Algorithms in Deep Learning (ISLRHP-HMOADL) technique for Hearing-Impaired Persons. The main objective of the ISLRHP-HMOADL technique focused on hand pose recognition to improve the efficiency and accuracy of sign interpretation for hearing-impaired persons. Initially, the ISLRHP-HMOADL model performs image pre-processing using a wiener filter (WF) to enhance image quality by reducing noise. Furthermore, the fusion of three models, ResNeXt101, VGG19, and vision transformer (ViT), is employed for feature extraction to capture diverse and intricate spatial and contextual details from the images. The bidirectional gated recurrent unit (BiGRU) classifier is implemented for hand pose recognition. To further optimize the performance of the model, the ISLRHP-HMOADL model implements the hybrid crow search-improved grey wolf optimization (CS-IGWO) model for parameter tuning, achieving a finely-tuned configuration that enhances classification accuracy and robustness. A comprehensive experimental study is accomplished under the ASL alphabet dataset to exhibit the improved performance of the ISLRHP-HMOADL model. The comparative results of the ISLRHP-HMOADL model illustrated a superior accuracy value of 99.57% over existing techniques.