Card: naming results use an idealised legend
Browse files
README.md
CHANGED
|
@@ -71,6 +71,11 @@ The ranker and the propagation model were trained without this region.
|
|
| 71 |
| names from text only | 65.9 % | 94.1 % | 62.0 % |
|
| 72 |
| **+ colour propagation** | **74.7 %** | **93.7 %** | **69.9 %** |
|
| 73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |

|
| 75 |
|
| 76 |
## How it works
|
|
|
|
| 71 |
| names from text only | 65.9 % | 94.1 % | 62.0 % |
|
| 72 |
| **+ colour propagation** | **74.7 %** | **93.7 %** | **69.9 %** |
|
| 73 |
|
| 74 |
+
> **Idealised legend.** These naming results use legend colours measured on the scan itself (close to a perfect
|
| 75 |
+
> legend). With the printed legend read automatically, about 19 % of the area is correctly named from text and
|
| 76 |
+
> legend (91–94 % precision, cross-sheet, before propagation). Matching printed swatches by colour alone is the
|
| 77 |
+
> current bottleneck.
|
| 78 |
+
|
| 79 |

|
| 80 |
|
| 81 |
## How it works
|