Update README.md
Browse files
README.md
CHANGED
|
@@ -64,6 +64,8 @@ This section details the performance comparison between the open-source ThaiTrOC
|
|
| 64 |
| Scene Text | **0.134182** | 0.390583 | 2.408704 |
|
| 65 |
| **Adjusted Mean** | **0.123600** | 0.298474 | 1.269101 |
|
| 66 |
|
|
|
|
|
|
|
| 67 |
# Key Insights
|
| 68 |
|
| 69 |
* Character Error Rate (CER): This metric evaluates the percentage of characters that were incorrectly predicted by the model. A lower CER indicates better performance. As shown in the table, ThaiTrOCR consistently outperforms EasyOCR and Tesseract across all document types, with a significantly lower average CER, making it the most accurate model in the comparison.
|
|
|
|
| 64 |
| Scene Text | **0.134182** | 0.390583 | 2.408704 |
|
| 65 |
| **Adjusted Mean** | **0.123600** | 0.298474 | 1.269101 |
|
| 66 |
|
| 67 |
+
**Disclaimer**: The test dataset at https://huggingface.co/datasets/openthaigpt/thai-ocr-evaluation includes only 100 images, which may limit the generalizability of these results. We are increasing the number of the test dataset.
|
| 68 |
+
|
| 69 |
# Key Insights
|
| 70 |
|
| 71 |
* Character Error Rate (CER): This metric evaluates the percentage of characters that were incorrectly predicted by the model. A lower CER indicates better performance. As shown in the table, ThaiTrOCR consistently outperforms EasyOCR and Tesseract across all document types, with a significantly lower average CER, making it the most accurate model in the comparison.
|