Spaces:
Running
Running
breezedeus
commited on
Commit
•
d2ddbc0
1
Parent(s):
694d1a3
Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding: utf-8
|
2 |
+
# Copyright (C) 2022, [Breezedeus](https://github.com/breezedeus).
|
3 |
+
# Licensed to the Apache Software Foundation (ASF) under one
|
4 |
+
# or more contributor license agreements. See the NOTICE file
|
5 |
+
# distributed with this work for additional information
|
6 |
+
# regarding copyright ownership. The ASF licenses this file
|
7 |
+
# to you under the Apache License, Version 2.0 (the
|
8 |
+
# "License"); you may not use this file except in compliance
|
9 |
+
# with the License. You may obtain a copy of the License at
|
10 |
+
#
|
11 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
12 |
+
#
|
13 |
+
# Unless required by applicable law or agreed to in writing,
|
14 |
+
# software distributed under the License is distributed on an
|
15 |
+
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
16 |
+
# KIND, either express or implied. See the License for the
|
17 |
+
# specific language governing permissions and limitations
|
18 |
+
# under the License.
|
19 |
+
|
20 |
+
import os
|
21 |
+
|
22 |
+
from PIL import Image, ImageFilter
|
23 |
+
import streamlit as st
|
24 |
+
|
25 |
+
from cnocr import CnOcr
|
26 |
+
|
27 |
+
from antiocr import AntiOcr, BG_IMAGE_FP, FONT_NAMES, set_logger, download_font
|
28 |
+
|
29 |
+
logger = set_logger()
|
30 |
+
st.set_page_config(layout="wide")
|
31 |
+
FONT_LOCAL_DIR = 'fonts'
|
32 |
+
|
33 |
+
|
34 |
+
@st.cache(allow_output_mutation=True)
|
35 |
+
def get_ocr_model():
|
36 |
+
return CnOcr()
|
37 |
+
|
38 |
+
|
39 |
+
def save_image(img):
|
40 |
+
from io import BytesIO
|
41 |
+
|
42 |
+
buf = BytesIO()
|
43 |
+
img.save(buf, format="JPEG")
|
44 |
+
byte_im = buf.getvalue()
|
45 |
+
st.download_button(
|
46 |
+
label="下载图片",
|
47 |
+
data=byte_im,
|
48 |
+
file_name="antiOCR.jpeg",
|
49 |
+
mime="image/jpeg",
|
50 |
+
)
|
51 |
+
|
52 |
+
|
53 |
+
def main():
|
54 |
+
st.sidebar.header('输出设置')
|
55 |
+
|
56 |
+
with st.spinner('Downloading fonts ...'):
|
57 |
+
for fnt_fp in FONT_NAMES:
|
58 |
+
download_font(os.path.join(FONT_LOCAL_DIR, fnt_fp))
|
59 |
+
|
60 |
+
font_fn = st.sidebar.selectbox('选择字体', FONT_NAMES, index=0)
|
61 |
+
font_fp = os.path.join(FONT_LOCAL_DIR, font_fn)
|
62 |
+
char_reverse_ratio = st.sidebar.slider(
|
63 |
+
'文字倒转概率', min_value=0.0, max_value=1.0, value=0.1
|
64 |
+
)
|
65 |
+
char_to_pinyin_ratio = st.sidebar.slider(
|
66 |
+
'文字转拼音概率', min_value=0.0, max_value=1.0, value=0.1
|
67 |
+
)
|
68 |
+
cols = st.sidebar.columns(2)
|
69 |
+
min_font_size = int(cols[0].number_input('最小文字大小', 2, 80, value=15))
|
70 |
+
max_font_size = int(
|
71 |
+
cols[1].number_input(
|
72 |
+
'最大文字大小', min_font_size + 1, 120, value=max(40, min_font_size + 1)
|
73 |
+
)
|
74 |
+
)
|
75 |
+
text_color = st.sidebar.color_picker('文字颜色', value='#5087DC')
|
76 |
+
|
77 |
+
st.sidebar.markdown('----')
|
78 |
+
use_random_bg = st.sidebar.checkbox('随机生成背景图片')
|
79 |
+
if use_random_bg:
|
80 |
+
bg_text_density = st.sidebar.slider(
|
81 |
+
'背景图片文字密度', min_value=0.0, max_value=3.0, value=1.0
|
82 |
+
)
|
83 |
+
cols = st.sidebar.columns(2)
|
84 |
+
bg_min_size = int(
|
85 |
+
cols[0].number_input('背景图片最小文字', 2, 80, key='bg_min', value=15)
|
86 |
+
)
|
87 |
+
bg_max_size = int(
|
88 |
+
cols[1].number_input(
|
89 |
+
'背景图片最大文字',
|
90 |
+
bg_min_size + 1,
|
91 |
+
120,
|
92 |
+
key='bg_max',
|
93 |
+
value=max(70, bg_min_size + 1),
|
94 |
+
)
|
95 |
+
)
|
96 |
+
bg_text_color = st.sidebar.color_picker('背景图片文字颜色', value='#07BCE0')
|
97 |
+
bg_gen_config = dict(
|
98 |
+
text_density=bg_text_density,
|
99 |
+
text_color=bg_text_color,
|
100 |
+
min_font_size=bg_min_size,
|
101 |
+
max_font_size=bg_max_size,
|
102 |
+
)
|
103 |
+
bg_image = None
|
104 |
+
else:
|
105 |
+
bg_gen_config = None
|
106 |
+
bg_image = Image.open(BG_IMAGE_FP)
|
107 |
+
bg_image = bg_image.filter(ImageFilter.MaxFilter(3))
|
108 |
+
|
109 |
+
title = '让文字自由传播:<a href="https://github.com/breezedeus/antiOCR">antiOCR</a>'
|
110 |
+
st.markdown(f"<h1 style='text-align: center;'>{title}</h1>", unsafe_allow_html=True)
|
111 |
+
subtitle = '作者:<a href="https://github.com/breezedeus">breezedeus</a>; ' \
|
112 |
+
'欢迎加入 <a href="https://cnocr.readthedocs.io/zh/latest/contact/">交流群</a>'
|
113 |
+
st.markdown(f"<div style='text-align: center;'>{subtitle}</div>", unsafe_allow_html=True)
|
114 |
+
st.markdown('')
|
115 |
+
st.markdown('')
|
116 |
+
desc = '<strong>antiOCR</strong> 对指定的文字(来自输入或者图片)进行处理,输出图片,此图片无法通过OCR技术识别出有意义的文字。'
|
117 |
+
st.markdown(f"<div style='text-align: left;'>{desc}</div>", unsafe_allow_html=True)
|
118 |
+
st.markdown('')
|
119 |
+
st.subheader('选择待转换文字图片,或者直接输入待转换文字')
|
120 |
+
default_texts = '真的猛士,敢于直面惨淡的人生,敢于正视淋漓的鲜血。这是怎样的哀痛者和幸福者?然而造化又常常为庸人设计,以时间的流逝,来洗涤旧迹,仅是留下淡红的血色和微漠的悲哀。在这淡红的血色和微漠的悲哀中,又给人暂得偷生,维持着这似人非人的世界。 ——鲁迅'
|
121 |
+
content_file = st.file_uploader('输入待转换的文字图片:', type=["png", "jpg", "jpeg", "webp"])
|
122 |
+
ocr = get_ocr_model()
|
123 |
+
anti = AntiOcr()
|
124 |
+
texts = None
|
125 |
+
if content_file is not None:
|
126 |
+
try:
|
127 |
+
img = Image.open(content_file).convert('RGB')
|
128 |
+
ocr_out = ocr.ocr(img)
|
129 |
+
texts = '\n'.join([out['text'] for out in ocr_out])
|
130 |
+
except Exception as e:
|
131 |
+
st.error(e)
|
132 |
+
|
133 |
+
texts = st.text_area('或者,直接输入待转换的文字:', value=texts or default_texts, height=120)
|
134 |
+
|
135 |
+
if st.button("生成图片"):
|
136 |
+
if texts:
|
137 |
+
with st.spinner('图片生成中…'):
|
138 |
+
out_img = anti(
|
139 |
+
texts,
|
140 |
+
char_reverse_ratio=char_reverse_ratio,
|
141 |
+
char_to_pinyin_ratio=char_to_pinyin_ratio,
|
142 |
+
text_color=text_color,
|
143 |
+
min_font_size=min_font_size,
|
144 |
+
max_font_size=max_font_size,
|
145 |
+
bg_image=bg_image,
|
146 |
+
bg_gen_config=bg_gen_config,
|
147 |
+
font_fp=font_fp,
|
148 |
+
)
|
149 |
+
st.subheader('输出图片')
|
150 |
+
st.image(out_img)
|
151 |
+
save_image(out_img)
|
152 |
+
|
153 |
+
st.markdown('**对输出图片进行OCR,结果如下(如果依旧出现敏感词,尝试重新生成图片):**')
|
154 |
+
ocr_out = ocr.ocr(out_img)
|
155 |
+
new_texts = [out['text'] for out in ocr_out]
|
156 |
+
st.text('\n'.join(new_texts))
|
157 |
+
|
158 |
+
|
159 |
+
if __name__ == '__main__':
|
160 |
+
main()
|