Update app.py
Browse files
app.py
CHANGED
@@ -1,7 +1,8 @@
|
|
1 |
-
import gradio as gr
|
2 |
# from transformers import pipeline
|
3 |
from PIL import Image
|
4 |
import pytesseract
|
|
|
5 |
import cv2
|
6 |
import os
|
7 |
|
@@ -11,17 +12,89 @@ import os
|
|
11 |
# predictions = pipeline(input_img)
|
12 |
# return input_img, {p["label"]: p["score"] for p in predictions}
|
13 |
|
14 |
-
def recognize(input_img):
|
15 |
-
|
16 |
-
|
17 |
|
18 |
-
gradio_app = gr.Interface(
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
|
23 |
-
|
24 |
-
)
|
25 |
|
26 |
-
if __name__ == "__main__":
|
27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# import gradio as gr
|
2 |
# from transformers import pipeline
|
3 |
from PIL import Image
|
4 |
import pytesseract
|
5 |
+
import easyocr
|
6 |
import cv2
|
7 |
import os
|
8 |
|
|
|
12 |
# predictions = pipeline(input_img)
|
13 |
# return input_img, {p["label"]: p["score"] for p in predictions}
|
14 |
|
15 |
+
# def recognize(input_img):
|
16 |
+
# text = pytesseract.image_to_string(Image.open("./data/" + filename))
|
17 |
+
# return input_img, text
|
18 |
|
19 |
+
# gradio_app = gr.Interface(
|
20 |
+
# recognize,
|
21 |
+
# inputs=[gr.Image(label="Upload an Image", type="pil")],
|
22 |
+
# outputs=[gr.Textbox(label="Text in the Image")],
|
23 |
|
24 |
+
# title="Extrate Text From Image",
|
25 |
+
# )
|
26 |
|
27 |
+
# if __name__ == "__main__":
|
28 |
+
# gradio_app.launch(server_port=8756)
|
29 |
+
|
30 |
+
|
31 |
+
import os
|
32 |
+
|
33 |
+
import matplotlib.pyplot as plt
|
34 |
+
import streamlit as st
|
35 |
+
|
36 |
+
import cv2
|
37 |
+
import tensorflow as tf
|
38 |
+
from PIL import Image
|
39 |
+
import pytesseract
|
40 |
+
|
41 |
+
DET_ARCHS = ["pytesseract", "easyocr"]
|
42 |
+
|
43 |
+
def main():
|
44 |
+
|
45 |
+
# Wide mode
|
46 |
+
st.set_page_config(layout="wide")
|
47 |
+
|
48 |
+
# Designing the interface
|
49 |
+
st.title("Image Text Recognition")
|
50 |
+
# For newline
|
51 |
+
st.write('\n')
|
52 |
+
|
53 |
+
# Instructions
|
54 |
+
st.markdown("*Hint: click on the top-right corner of an image to enlarge it!*")
|
55 |
+
# Set the columns
|
56 |
+
cols = st.columns((1, 1, 1, 1))
|
57 |
+
cols[0].subheader("Input image")
|
58 |
+
cols[1].subheader("OCR output")
|
59 |
+
|
60 |
+
# Sidebar
|
61 |
+
# File selection
|
62 |
+
st.sidebar.title("Document selection")
|
63 |
+
# Disabling warning
|
64 |
+
# st.set_option('deprecation.showfileUploaderEncoding', False)
|
65 |
+
# Choose your own image
|
66 |
+
uploaded_file = st.sidebar.file_uploader("Upload files", type=['png', 'jpeg', 'jpg'])
|
67 |
+
if uploaded_file is not None:
|
68 |
+
doc = uploaded_file.read()
|
69 |
+
cols[0].image(doc)
|
70 |
+
|
71 |
+
# Model selection
|
72 |
+
st.sidebar.title("Model selection")
|
73 |
+
det_arch = st.sidebar.selectbox("OCR model", DET_ARCHS)
|
74 |
+
|
75 |
+
# For newline
|
76 |
+
st.sidebar.write('\n')
|
77 |
+
|
78 |
+
if st.sidebar.button("Analyze image"):
|
79 |
+
|
80 |
+
if uploaded_file is None:
|
81 |
+
st.sidebar.write("Please upload a document")
|
82 |
+
|
83 |
+
else:
|
84 |
+
with st.spinner('Loading model...'):
|
85 |
+
if det_arch == 'pytesseract':
|
86 |
+
predictor = pytesseract.image_to_string(Image.open(doc))
|
87 |
+
else:
|
88 |
+
reader = easyocr.Reader(['en'])
|
89 |
+
predictor = reader.readtext("./data/" + filename, detail = 0)
|
90 |
+
with st.spinner('Analyzing...'):
|
91 |
+
|
92 |
+
# Plot OCR output
|
93 |
+
if det_arch == 'pytesseract':
|
94 |
+
cols[1].text(predictor)
|
95 |
+
else:
|
96 |
+
cols[1].text(''.join(text))
|
97 |
+
|
98 |
+
|
99 |
+
if __name__ == '__main__':
|
100 |
+
main()
|