Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Computer vision has been identified as one of the solutions to bridge communication barriers between speech-impaired populations and those without impairment as most people are unaware of the sign language used by speech-impaired individuals. Numerous studies have been conducted to address this challenge. However, recognizing word signs, which are usually dynamic and involve more than one frame per sign, remains a challenge. This study used Tanzania Sign Language datasets collected using mobile phone selfie cameras to investigate the performance of deep learning algorithms that capture spatial and temporal relationships features of video frames. The study used CNN-LSTM and CNN-GRU architectures, where CNN-GRU with an ELU activation function is proposed to enhance learning efficiency and performance. The findings indicate that the proposed CNN-GRU model with ELU activation achieved an accuracy of 94%, compared to 93% for the standard CNN-GRU model and CNN-LSTM. In addition, the study evaluated performance of the proposed model in a signer-independent setting, where the results varied significantly across individual signers, with the highest accuracy reaching 66%. These results show that more effort is required to improve signer independence performance, including the challenges of hand dominance by optimizing spatial features.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12415044PMC
http://dx.doi.org/10.3389/frai.2025.1630743DOI Listing

Publication Analysis

Top Keywords

sign language
12
elu activation
8
cnn-gru model
8
efficient spatio-temporal
4
spatio-temporal modeling
4
sign
4
modeling sign
4
language recognition
4
recognition cnn
4
cnn rnn
4

Similar Publications

Computer vision has been identified as one of the solutions to bridge communication barriers between speech-impaired populations and those without impairment as most people are unaware of the sign language used by speech-impaired individuals. Numerous studies have been conducted to address this challenge. However, recognizing word signs, which are usually dynamic and involve more than one frame per sign, remains a challenge.

View Article and Find Full Text PDF

Background: Cancer screening nonadherence persists among adults who are deaf, deafblind, and hard of hearing (DDBHH). These barriers span individual, clinician, and health care system levels, contributing to difficulties understanding cancer information, accessing screening services, and following treatment directives. Critical communication barriers include ineffective patient-physician communication, limited access to American Sign Language (ASL) cancer information, misconceptions about medical procedures, insurance navigation difficulties, and intersectional barriers for multiply marginalized individuals.

View Article and Find Full Text PDF

Early Childhood Development is a key national priority in South Africa which has developed the Early Learning Outcome Measure (ELOM 4&5) specifically designed to measure the progress of 4- and 5-year-old children across 5 domains of early childhood development. This age-validated, population-standardised instrument has been shown to have measurement equivalence and lack of bias across South Africa's 11 official spoken languages. In 2023, South African Sign Language was formally recognised as 12th official language of South Africa, but no ELOM (4&5) exists in SASL despite over 6,000 deaf children being born annually.

View Article and Find Full Text PDF

Objectives: There are more than 10 million deaf or hard of hearing people in the UK. While the deaf and hard of hearing population is heterogeneous, many of those with profound hearing loss are part of deaf communities (UK estimate around 120 000) which are defined minority communities. Many members of deaf communities are sign language users.

View Article and Find Full Text PDF