mirrors
/
mmocr
mirror of https://github.com/open-mmlab/mmocr.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[Feature] add a new argument font_properties to set a specific font file in order to draw Chinese characters properly (#1709) 

* [Feature] add new argument font_properties to set specific font file  in order to draw Chinese characters properly

* update the minimum mmengine version

* add docstr
pull/1752/head
Kevin Wang 2023-02-27 14:25:49 +08:00 committed by GitHub
parent 0894178343
commit 62d440fe8e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 72 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/en/get_started/install.md
View File

@ -193,6 +193,6 @@ MMOCR has different version requirements on MMEngine, MMCV and MMDetection at ea
| MMOCR | MMEngine | MMCV | MMDetection |
| -------------- | --------------------------- | -------------------------- | --------------------------- |
| dev-1.x | 0.5.0 \<= mmengine \< 1.0.0 | 2.0.0rc4 \<= mmcv \< 2.1.0 | 3.0.0rc5 \<= mmdet \< 3.1.0 |
| dev-1.x | 0.6.0 \<= mmengine \< 1.0.0 | 2.0.0rc4 \<= mmcv \< 2.1.0 | 3.0.0rc5 \<= mmdet \< 3.1.0 |
| 1.0.0rc\[4-5\] | 0.1.0 \<= mmengine \< 1.0.0 | 2.0.0rc1 \<= mmcv \< 2.1.0 | 3.0.0rc0 \<= mmdet \< 3.1.0 |
| 1.0.0rc\[0-3\] | 0.0.0 \<= mmengine \< 0.2.0 | 2.0.0rc1 \<= mmcv \< 2.1.0 | 3.0.0rc0 \<= mmdet \< 3.1.0 |

2
docs/zh_cn/get_started/install.md
View File

@ -194,6 +194,6 @@ docker run --gpus all --shm-size=8g -it -v {实际数据目录}:/mmocr/data mmoc
| MMOCR | MMEngine | MMCV | MMDetection |
| -------------- | --------------------------- | -------------------------- | --------------------------- |
| dev-1.x | 0.5.0 \<= mmengine \< 1.0.0 | 2.0.0rc4 \<= mmcv \< 2.1.0 | 3.0.0rc5 \<= mmdet \< 3.1.0 |
| dev-1.x | 0.6.0 \<= mmengine \< 1.0.0 | 2.0.0rc4 \<= mmcv \< 2.1.0 | 3.0.0rc5 \<= mmdet \< 3.1.0 |
| 1.0.0rc\[4-5\] | 0.1.0 \<= mmengine \< 1.0.0 | 2.0.0rc1 \<= mmcv \< 2.1.0 | 3.0.0rc0 \<= mmdet \< 3.1.0 |
| 1.0.0rc\[0-3\] | 0.0.0 \<= mmengine \< 0.2.0 | 2.0.0rc1 \<= mmcv \< 2.1.0 | 3.0.0rc0 \<= mmdet \< 3.1.0 |

2
mmocr/__init__.py
View File

@ -16,7 +16,7 @@ mmcv_minimum_version = '2.0.0rc4'
mmcv_maximum_version = '2.1.0'
mmcv_version = digit_version(mmcv.__version__)
if mmengine is not None:
mmengine_minimum_version = '0.5.0'
mmengine_minimum_version = '0.6.0'
mmengine_maximum_version = '1.0.0'
mmengine_version = digit_version(mmengine.__version__)

64
mmocr/visualization/base_visualizer.py
View File

@ -1,9 +1,10 @@
# Copyright (c) OpenMMLab. All rights reserved.
import math
from typing import List, Sequence, Union
from typing import List, Optional, Sequence, Union
import numpy as np
import torch
from matplotlib.font_manager import FontProperties
from mmengine.visualization import Visualizer
from mmocr.registry import VISUALIZERS
@ -27,6 +28,18 @@ class BaseLocalVisualizer(Visualizer):
Defaults to empty dict.
is_openset (bool, optional): Whether the visualizer is used in
OpenSet. Defaults to False.
font_families (Union[str, List[str]]): The font families of labels.
Defaults to 'sans-serif'.
font_properties (Union[str, FontProperties], optional):
The font properties of texts. The format should be a path str
to font file or a `font_manager.FontProperties()` object.
If you want to draw Chinese texts, you need to prepare
a font file that can show Chinese characters properly.
For example: `simhei.ttf`,`simsun.ttc`,`simkai.ttf` and so on.
Then set font_properties=matplotlib.font_manager.FontProperties
(fname='path/to/font_file') or font_properties='path/to/font_file'
This function need mmengine version >=0.6.0.
Defaults to None.
"""
PALETTE = [(220, 20, 60), (119, 11, 32), (0, 0, 142), (0, 0, 230),
(106, 0, 228), (0, 60, 100), (0, 80, 100), (0, 0, 70),
@ -53,19 +66,36 @@ class BaseLocalVisualizer(Visualizer):
def __init__(self,
name: str = 'visualizer',
font_families: Union[str, List[str]] = 'sans-serif',
font_properties: Optional[Union[str, FontProperties]] = None,
**kwargs) -> None:
super().__init__(name=name, **kwargs)
self.font_families = font_families
self.font_properties = self._set_font_properties(font_properties)
def get_labels_image(self,
image: np.ndarray,
labels: Union[np.ndarray, torch.Tensor],
bboxes: Union[np.ndarray, torch.Tensor],
colors: Union[str, Sequence[str]] = 'k',
font_size: Union[int, float] = 10,
auto_font_size: bool = False,
font_families: Union[str, List[str]] = 'sans-serif'
) -> np.ndarray:
def _set_font_properties(self,
fp: Optional[Union[str, FontProperties]] = None):
if fp is None:
return None
elif isinstance(fp, str):
return FontProperties(fname=fp)
elif isinstance(fp, FontProperties):
return fp
else:
raise ValueError(
'font_properties argument type should be'
' `str` or `matplotlib.font_manager.FontProperties`')
def get_labels_image(
self,
image: np.ndarray,
labels: Union[np.ndarray, torch.Tensor],
bboxes: Union[np.ndarray, torch.Tensor],
colors: Union[str, Sequence[str]] = 'k',
font_size: Union[int, float] = 10,
auto_font_size: bool = False,
font_families: Union[str, List[str]] = 'sans-serif',
font_properties: Optional[Union[str, FontProperties]] = None
) -> np.ndarray:
"""Draw labels on image.
Args:
@ -84,6 +114,17 @@ class BaseLocalVisualizer(Visualizer):
Defaults to False.
font_families (Union[str, List[str]]): The font families of labels.
Defaults to 'sans-serif'.
font_properties (Union[str, FontProperties], optional):
The font properties of texts. The format should be a path str
to font file or a `font_manager.FontProperties()` object.
If you want to draw Chinese texts, you need to prepare
a font file that can show Chinese characters properly.
For example: `simhei.ttf`,`simsun.ttc`,`simkai.ttf` and so on.
Then set font_properties=matplotlib.font_manager.FontProperties
(fname='path/to/font_file') or
font_properties='path/to/font_file'.
This function need mmengine version >=0.6.0.
Defaults to None.
"""
if not labels and not bboxes:
return image
@ -102,7 +143,8 @@ class BaseLocalVisualizer(Visualizer):
horizontal_alignments='center',
colors='k',
font_sizes=font_size,
font_families=font_families)
font_families=font_families,
font_properties=font_properties)
return self.get_image()
def get_polygons_image(self,

15
mmocr/visualization/kie_visualizer.py
View File

@ -90,14 +90,16 @@ class KIELocalVisualizer(BaseLocalVisualizer):
colors='k',
horizontal_alignments='center',
vertical_alignments='center',
font_families=self.font_families)
font_families=self.font_families,
font_properties=self.font_properties)
if val_texts:
self.draw_texts(
val_texts, (bboxes[val_index, :2] + bboxes[val_index, 2:]) / 2,
colors='k',
horizontal_alignments='center',
vertical_alignments='center',
font_families=self.font_families)
font_families=self.font_families,
font_properties=self.font_properties)
self.draw_arrows(
x_data,
y_data,
@ -153,7 +155,11 @@ class KIELocalVisualizer(BaseLocalVisualizer):
text_image = np.full(empty_shape, 255, dtype=np.uint8)
text_image = self.get_labels_image(
text_image, texts, bboxes, font_families=self.font_families)
text_image,
texts,
bboxes,
font_families=self.font_families,
font_properties=self.font_properties)
classes_image = np.full(empty_shape, 255, dtype=np.uint8)
bbox_classes = [class_names[int(i)]['name'] for i in bbox_labels]
@ -161,7 +167,8 @@ class KIELocalVisualizer(BaseLocalVisualizer):
classes_image,
bbox_classes,
bboxes,
font_families=self.font_families)
font_families=self.font_families,
font_properties=self.font_properties)
if polygons:
polygons = [polygon.reshape(-1, 2) for polygon in polygons]
image = self.get_polygons_image(

3
mmocr/visualization/textrecog_visualizer.py
View File

@ -68,7 +68,8 @@ class TextRecogLocalVisualizer(BaseLocalVisualizer):
font_sizes=font_size,
vertical_alignments='center',
horizontal_alignments='center',
font_families=self.font_families)
font_families=self.font_families,
font_properties=self.font_properties)
text_image = self.get_image()
return text_image

3
mmocr/visualization/textspotting_visualizer.py
View File

@ -49,7 +49,8 @@ class TextSpottingLocalVisualizer(BaseLocalVisualizer):
text_image,
labels=texts,
bboxes=bboxes,
font_families=self.font_families)
font_families=self.font_families,
font_properties=self.font_properties)
if polygons:
polygons = [polygon.reshape(-1, 2) for polygon in polygons]
image = self.get_polygons_image(

2
requirements/mminstall.txt
View File

@ -1,3 +1,3 @@
mmcv>==2.0.0rc4,<2.1.0
mmdet>=3.0.0rc5,<3.1.0
mmengine>= 0.5.0, <1.0.0
mmengine>= 0.6.0, <1.0.0