Evaluating the Efficiency of CBAM-Resnet Using Malaysian Sign Language
Source abstract
Abstract
The deaf-mutes population is constantly feeling helpless when others do not understand them and vice versa. To fill this gap, this study implements a CNN-based neural network, Convolutional Based Attention Module (CBAM), to recognise Malaysian Sign Language (MSL) in videos recognition. This study has created 2071 videos for 19 dynamic signs. Two different experiments were conducted for dynamic signs, using CBAM-3DResNet implementing ‘Within Blocks’ and ‘Before Classifier’ methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time were recorded to evaluate the models’ efficiency. Results showed that CBAM-ResNet models had good performances in videos recognition tasks, with recognition rates of over 90% with little variations. CBAM-ResNet ‘Before Classifier’ is more efficient than ‘Within Blocks’ models of CBAM-ResNet. All experiment results indicated the CBAM-ResNet ‘Before Classifier’ efficiency in recognising Malaysian Sign Language and its worth of future research.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Hand Gesture Recognition Systems · Hearing Impairment and Communication · Wireless Signal Modulation Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (33)
Show source-provided references
1. Recognition of Malaysian sign language using skeleton data with neural network
2. Malaysian sign language translator
3. Mental health of deaf and hard-of-hearing adolescents: What the students say10.1093/deafed/enu031 ↗
4. Psychiatric assessment of deaf and mute patients–a case series10.1016/j.ajp.2016.10.007 ↗
5. Workplace discrimination against Malaysians with disabilities: Living with it or fighting against it?10.18061/dsq.v33i3.3399 ↗
6. Cbam: Convolutional block attention module
7. Sign language recognition based on cbam-resnet
8. Zurada · Introduction to Artificial Neural Systems · 1992 · 8 · 15
9. American sign language recognition by using 3d geometric invariant feature and ann classification
10. Thai sign language recognition by using geometric invariant feature and ann classification
11. Glove-based sign language recognition solution to assist communication for deaf users
12. Sign language recognition using sensor gloves
13. American Sign Language Finger Spelling Recognition System
14. Convolutional networks for images, speech, and time series
15. American sign language posture understanding with deep neural networks
16. Imagenet classification with deep convolutional neural networks
17. Hand gesture recognition system using convolutional neural networks
18. Deep learning using rectified linear units (relu)
19. Supervised sequence labelling10.1007/978-3-642-24797-2_2 ↗
20. Sign language recognition with long short-term memory
21. Sign language system for bahasa Indonesia (known as sibi) recogniser using tensorflow and long short-term memory
22. Real-time Malaysian sign language translation using colour segmentation and neural network
23. Malay sign language gesture recognition system
24. Gesture recognition system for kod tangan bahasa melayu (ktbm) using neural network
25. Malaysian sign language database for research
26. A model for real-time recognition and textual representation of Malaysian sign language through image processing
27. Malaysian sign language dataset for automatic sign language recognition system10.4314/jfas.v9i4S.26 ↗
28. The Malaysian sign language and deaf studies association (mybim)
29. The American sign language lexicon video dataset
30. Video-based sign language recognition without temporal segmentation
31. A dataset of 101 human action classes from videos in the wild
32. Mict: Mixed 3d/2d convolutional tube for human action recognition
33. Would mega-scale datasets further enhance spatiotemporal 3d cnns?