Update app.py

app.py

@@ -1,36 +1,128 @@
-import os
-os.system('pip install paddlepaddle')
-os.system('pip install paddleocr')
-from paddleocr import PaddleOCR, draw_ocr
+import pandas as pd
+import PIL
 from PIL import Image
+from PIL import ImageDraw
 import gradio as gr
 import torch
+import easyocr
 
-torch.hub.download_url_to_file('https://i.imgur.com/aqMBT0i.jpg', 'example.jpg')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/english.png', 'english.png')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/thai.jpg', 'thai.jpg')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/french.jpg', 'french.jpg')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/chinese.jpg', 'chinese.jpg')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/japanese.jpg', 'japanese.jpg')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/korean.png', 'korean.png')
+torch.hub.download_url_to_file('https://i.imgur.com/mwQFd7G.jpeg', 'Hindi.jpeg')
+
+def draw_boxes(image, bounds, color='yellow', width=2):
+    draw = ImageDraw.Draw(image)
+    for bound in bounds:
+        p0, p1, p2, p3 = bound[0]
+        draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
+    return image
 
 def inference(img, lang):
-    ocr = PaddleOCR(use_angle_cls=True, lang=lang,use_gpu=False)
-    img_path = img.name
-    result = ocr.ocr(img_path, cls=True)
-    image = Image.open(img_path).convert('RGB')
-    boxes = [line[0] for line in result]
-    txts = [line[1][0] for line in result]
-    scores = [line[1][1] for line in result]
-    im_show = draw_ocr(image, boxes, txts, scores,
-                       font_path='simfang.ttf')
-    im_show = Image.fromarray(im_show)
-    im_show.save('result.jpg')
-    return 'result.jpg'
+    reader = easyocr.Reader(lang)
+    bounds = reader.readtext(img.name)
+    im = PIL.Image.open(img.name)
+    draw_boxes(im, bounds)
+    im.save('result.jpg')
+    return ['result.jpg', pd.DataFrame(bounds).iloc[: , 1:]]
 
-title = 'PaddleOCR'
-description = 'Gradio demo for PaddleOCR. PaddleOCR demo supports Chinese, English, French, German, Korean and Japanese.To use it, simply upload your image and choose a language from the dropdown menu, or click one of the examples to load them. Read more at the links below.'
-article = "<p style='text-align: center'><a href='https://www.paddlepaddle.org.cn/hub/scene/ocr'>Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）</a> | <a href='https://github.com/PaddlePaddle/PaddleOCR'>Github Repo</a></p>"
-examples = [['example.jpg','en']]
+title = 'EasyOCR'
+description = 'Gradio demo for EasyOCR. EasyOCR demo supports 80+ languages.To use it, simply upload your image and choose a language from the dropdown menu, or click one of the examples to load them. Read more at the links below.'
+article = "<p style='text-align: center'><a href='https://www.jaided.ai/easyocr/'>Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.</a> | <a href='https://github.com/JaidedAI/EasyOCR'>Github Repo</a></p>"
+examples = [['english.png',['en']],['thai.jpg',['th']],['french.jpg',['fr', 'en']],['chinese.jpg',['ch_sim', 'en']],['japanese.jpg',['ja', 'en']],['korean.png',['ko', 'en']],['Hindi.jpeg',['hi', 'en']]]
 css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
+choices = [
+    "abq",
+    "ady",
+    "af",
+    "ang",
+    "ar",
+    "as",
+    "ava",
+    "az",
+    "be",
+    "bg",
+    "bh",
+    "bho",
+    "bn",
+    "bs",
+    "ch_sim",
+    "ch_tra",
+    "che",
+    "cs",
+    "cy",
+    "da",
+    "dar",
+    "de",
+    "en",
+    "es",
+    "et",
+    "fa",
+    "fr",
+    "ga",
+    "gom",
+    "hi",
+    "hr",
+    "hu",
+    "id",
+    "inh",
+    "is",
+    "it",
+    "ja",
+    "kbd",
+    "kn",
+    "ko",
+    "ku",
+    "la",
+    "lbe",
+    "lez",
+    "lt",
+    "lv",
+    "mah",
+    "mai",
+    "mi",
+    "mn",
+    "mr",
+    "ms",
+    "mt",
+    "ne",
+    "new",
+    "nl",
+    "no",
+    "oc",
+    "pi",
+    "pl",
+    "pt",
+    "ro",
+    "ru",
+    "rs_cyrillic",
+    "rs_latin",
+    "sck",
+    "sk",
+    "sl",
+    "sq",
+    "sv",
+    "sw",
+    "ta",
+    "tab",
+    "te",
+    "th",
+    "tjk",
+    "tl",
+    "tr",
+    "ug",
+    "uk",
+    "ur",
+    "uz",
+    "vi"
+]
 gr.Interface(
     inference,
-    [gr.inputs.Image(type='file', label='Input'),gr.inputs.Dropdown(choices=['ch', 'en', 'fr', 'german', 'korean', 'japan'], type="value", default='en', label='language')],
-    gr.outputs.Image(type='file', label='Output'),
+    [gr.inputs.Image(type='file', label='Input'),gr.inputs.CheckboxGroup(choices, type="value", default=['en'], label='language')],
+    [gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe(headers=['text', 'confidence'])],
     title=title,
     description=description,
     article=article,