Table 8 Text detection performance comparison with other techniques
From: Detection and recognition of cursive text from video frames
Image type | Study | Language | Data size | Recognition rate (%) |
|---|---|---|---|---|
Document | Ahmed et al. [146] | Urdu | 56 character clusters | 93.40 |
| Â | Akram et al. [147] | Urdu | 224 images | 86.15 |
| Â | Hussain et al. [148] | Urdu | 5249 ligatures | 87.44 |
| Â | Ahmed et al. [149] | Urdu | 15,251 lines | 96.00 |
| Â | Naz et al. [123] | Urdu | 10,000 lines | 98.12 |
| Â | Hassan et al. [150] | Urdu | 10,000 lines | 94.85 |
Videos | Zayene et al. [114] | Arabic | 7843 lines | 96.85 |
| Â | Tayyab et al. [134] | Urdu | 19,824 lines | 93.02 |
| Â | Hayat et al. [133] | Urdu | 290 uniqe ligatures | 99.50 |
| Â | Proposed | Urdu | 40,470 lines | 87.00 |