app.py

import os
import streamlit as st
import paddlehub as hub
from PIL import Image
import io


from paddleocr import PaddleOCR,draw_ocr
def ocr(img,lang):
    # Paddleocr supports Chinese, English, French, German, Korean and Japanese.
    # You can set the parameter `lang` as `ch`, `en`, `french`, `german`, `korean`, `japan`
    # to switch the language model in order.
    ocr = PaddleOCR(use_angle_cls=True, lang=lang) # need to run only once to download and load model into memory
    img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
    result = ocr.ocr(img, cls=True)
    for idx in range(len(result)):
        res = result[idx]
        for line in res:
            print(line)

    # draw result
    from PIL import Image
    result = result[0]
    image = Image.open(img_path).convert('RGB')
    boxes = [line[0] for line in result]
    st.text(boxes)
    txts = [line[1][0] for line in result]
    st.text(txts)
    scores = [line[1][1] for line in result]
    st.text(scores)
    #im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
    #im_show = Image.fromarray(im_show)
    #st.image(im_show, caption='Sunrise by the mountains')
    #im_show.save('result.jpg')


uploaded_file = st.file_uploader("Choose a file")
if uploaded_file is not None:
    # To read file as bytes:
    bytes_data = uploaded_file.getvalue()
    st.write(bytes_data)
    image = Image.open(io.BytesIO(bytes_data))
    st.image(image, caption='Sunrise by the mountains')
    ocr(image,'ch')