BDSL 49: A Comprehensive Dataset of Bangla Sign Language

Hasib, Ayman; Khan, Saqib Sizan; Eva, Jannatul Ferdous; Nipa, Khatun, Mst.; Haque, Ashraful; Nishat, Shahrin,; Rahman, Rashik; Murad, Hasan Sohaib; Islam, Md. Rajibul; Hussein, Molla Rashied

doi:10.48550/arxiv.2208.06827

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A dataset is highly useful for an automated system to recognize the hand signs of Bengali Sign Language. For this research purpose, a dataset named BdSL 49 [16] is utilized with 49 classes. Each class represents a Bengali alphabet, numeric character, or special character (space, Hasantha).…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…The QMX recognition model is only 3.3MB in size and contains just 3,317,201 trainable parameters, making it an extremely lightweight model for embedded system implementation. To train and evaluate the model, an open-source benchmark dataset named BDSL 49 [16] that contains 14,700 images divided into 49 classes is utilized. The QMX model achieved an overall F1 accuracy of 98%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

QMX-BdSL49: An Efficient Recognition Approach for Bengali Sign Language with Quantize Modified Xception

Begum¹,

Khan²,

Rahman³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Sign language is developed to bridge the communication gap between individuals with and without hearing impairment or speech difficulties. Individuals with hearing and speech impairment typically rely on hand signs as a means of expressing themselves. However, people, in general, may not have sufficient knowledge of sign language, thus a sign language recognition system on an embedded device is most needed. Literature related to such systems on embedded devices is scarce as these recognition tasks are very complex and computationally expensive. The limited resources of embedded devices cannot execute complex algorithms like Convolutional Neural Network (CNN) properly. Therefore, in this paper, we propose a novel deep learning architecture based on default Xception architecture, named Quantized Modified Xception (QMX) to reduce the model's size and enhance the computational speed without compromising model accuracy. Moreover, the proposed QMX model is highly optimized due to the weight compression of model quantization. As a result, the footprint of the proposed QMX model is 11 times smaller than the Modified Xception (MX) model. To train the model, BDSL 49 dataset is utilized which includes approximately 14,700 images divided into 49 classes. The proposed QMX model achieves an overall F1 accuracy of 98%. In addition, a comprehensive analysis among QMX, Modified Xception Tiny (MXT), MX, and the default Xception model is provided in this research. Finally, the model has been implemented on Raspberry Pi 4 and a detailed evaluation of its performance has been conducted, including a comparison with existing state-of-the-art approaches in this domain. The results demonstrate that the proposed QMX model outperforms the prior work in terms of performance.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%