Published January 1, 2026
| Version v1
Journal article
Open
Comparative Evaluation Of FP32 And INT8 Quantization For Edge Device Real-Time Indian Sign Language Recognition
Authors/Creators
Description
The high memory and computational requirements of standard floating-point architectures make it difficult to deploy Deep Learning models on edge devices with limited resources. The Post-Training Quantization (PTQ) methods used with a MobileNetV2 architecture for real-time Indian Sign Language (ISL) recognition are compared in this paper. We show that the baseline 32-bit floating-point (FP32) model can be converted to an 8-bit integer (INT8) format, which significantly reduces the model footprint and improves inference latency without significantly degrading accuracy. The INT8 quantized model achieves a 72.4% reduction in memory size (from 9.52 MB to 2.63 MB) and a 31.7% increase in inference speed (from 14.40 ms to 9.83 ms per frame), according to experimental results on a 27-class ISL dataset. Importantly, compared to the FP32 baseline, the quantized model maintains a strong validation accuracy of 98.60%, with an accuracy decline of less than 1%. These results confirm that INT8 quantization is effective in enabling offline, high-framerate computer vision applications on low-power edge hardware.
Files
IJSRET_V12_issue2_475.pdf
Additional details
Related works
- Has part
- Journal article: https://www.ijset.in/wp-content/uploads/IJSRET_V12_issue2_475.pdf (URL)
- Is identical to
- Journal article: https://www.ijset.in/comparative-evaluation-of-fp32-and-int8-quantization-for-edge-device-real-time-indian-sign-language-recognition/ (URL)