Atulit23 commited on
Commit
2ea84fe
1 Parent(s): 6488435

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. app.py +3 -31
  2. g-ocr.py +30 -0
app.py CHANGED
@@ -3,37 +3,9 @@ import json
3
  import gradio as gr
4
  import easyocr
5
 
6
- reader = easyocr.Reader(['en'])
7
-
8
- # ocr = PaddleOCR(use_angle_cls=True, lang='en', use_pdserving=False, cls_batch_num=8, det_batch_num=8, rec_batch_num=8)
9
-
10
- # ocr = PaddleOCR(use_angle_cls=True, lang='en')
11
-
12
- # def index(url):
13
- # response = requests.get(url)
14
- # img = Image.open(BytesIO(response.content))
15
- # resize_factor = 1
16
- # new_size = tuple(int(dim * resize_factor) for dim in img.size)
17
- # img = img.resize(new_size, Image.Resampling.LANCZOS)
18
-
19
- # img_array = np.array(img.convert('RGB'))
20
-
21
- # result = ocr.ocr(img_array)
22
-
23
- # boxes = [line[0] for line in result]
24
- # txts = [line[1][0] for line in result]
25
- # scores = [line[1][1] for line in result]
26
-
27
- # print(boxes)
28
- # print(txts)
29
-
30
- # output_dict = {"texts": txts, "boxes": boxes, "scores": scores}
31
- # output_json = json.dumps(output_dict) # Convert to JSON string
32
-
33
- # return output_json
34
-
35
 
36
  def index(image_url):
 
37
  result = reader.readtext(image_url)
38
 
39
  texts = []
@@ -46,7 +18,7 @@ def index(image_url):
46
 
47
  output_dict = {"texts": texts, "boxes": probs}
48
  output_json = json.dumps(output_dict)
49
-
50
  return output_json
51
 
52
  inputs_image_url = [
@@ -63,4 +35,4 @@ interface_image_url = gr.Interface(
63
  outputs=outputs_result_json,
64
  title="Text Extraction",
65
  cache_examples=False,
66
- ).queue().launch()
 
3
  import gradio as gr
4
  import easyocr
5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
 
7
  def index(image_url):
8
+ reader = easyocr.Reader(['en'])
9
  result = reader.readtext(image_url)
10
 
11
  texts = []
 
18
 
19
  output_dict = {"texts": texts, "boxes": probs}
20
  output_json = json.dumps(output_dict)
21
+
22
  return output_json
23
 
24
  inputs_image_url = [
 
35
  outputs=outputs_result_json,
36
  title="Text Extraction",
37
  cache_examples=False,
38
+ ).queue().launch()
g-ocr.py CHANGED
@@ -52,6 +52,36 @@
52
  # opening = opening(gray)
53
  # canny = canny(gray)
54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  import easyocr
56
 
57
  image_url = 'https://res.cloudinary.com/ddvajyjou/image/upload/v1706960876/rzse0mcqxbgs8z2pf6lr.png'
 
52
  # opening = opening(gray)
53
  # canny = canny(gray)
54
 
55
+
56
+ # ocr = PaddleOCR(use_angle_cls=True, lang='en', use_pdserving=False, cls_batch_num=8, det_batch_num=8, rec_batch_num=8)
57
+
58
+ # ocr = PaddleOCR(use_angle_cls=True, lang='en')
59
+
60
+ # def index(url):
61
+ # response = requests.get(url)
62
+ # img = Image.open(BytesIO(response.content))
63
+ # resize_factor = 1
64
+ # new_size = tuple(int(dim * resize_factor) for dim in img.size)
65
+ # img = img.resize(new_size, Image.Resampling.LANCZOS)
66
+
67
+ # img_array = np.array(img.convert('RGB'))
68
+
69
+ # result = ocr.ocr(img_array)
70
+
71
+ # boxes = [line[0] for line in result]
72
+ # txts = [line[1][0] for line in result]
73
+ # scores = [line[1][1] for line in result]
74
+
75
+ # print(boxes)
76
+ # print(txts)
77
+
78
+ # output_dict = {"texts": txts, "boxes": boxes, "scores": scores}
79
+ # output_json = json.dumps(output_dict) # Convert to JSON string
80
+
81
+ # return output_json
82
+
83
+
84
+
85
  import easyocr
86
 
87
  image_url = 'https://res.cloudinary.com/ddvajyjou/image/upload/v1706960876/rzse0mcqxbgs8z2pf6lr.png'