check signature with craft_hw_ocr as an option to craft_text_detection

app.py

@@ -3,7 +3,30 @@ import gradio as gr
 import torch
 import numpy as np
 
-dw=0.3
+def detect_with_craft_text_detector(image: np.ndarray):
+    from craft_text_detector import Craft
+    craft = Craft(output_dir='output', crop_type="box", cuda=torch.cuda.is_available(), export_extra=True)
+    result = craft.detect_text( image)
+    annotated = PIL.Image.open('output/image_text_detection.png')  # image with boxes displayed
+    return annotated, result['boxes'], is_signature(result['boxes_as_ratios'])
+
+def detect_with_craft_hw_ocr(image: np.ndarray):
+    from craft_hw_ocr import OCR
+    ocr = OCR.load_models()
+    image, results = OCR.detection(image, ocr[2])
+    bboxes, _ = OCR.recoginition(image, results, ocr[0], ocr[1])
+    h,w,_=np.shape(image) # third dimension is color channel
+    annotated = OCR.visualize(image, results)
+    m=(np.asarray([w,h]))[np.newaxis,np.newaxis,:]
+    return annotated, bboxes, is_signature(bboxes/m)
+
+def process(image:np.ndarray, lib:str):
+    if image is None:
+        return None,'',''
+    annotated, boxes, signed = detect_with_craft_text_detector(image) if lib=='craft_text_detector' else detect_with_craft_hw_ocr( image)
+    return annotated, len(boxes), signed
+
+dw=0.3 # width ratio
 dh=0.25
 def is_nw(box):
     """
@@ -35,41 +58,22 @@ def is_header(box)->bool:
     """ true if for the 2 last points, y<0.2 """
     return box[2][1]<=dhhf and box[3][1]<=dhhf
 
-def is_signature(prediction_result) -> bool:
-    """ true if any of the boxes is at any corner """
-    for box in prediction_result['boxes_as_ratios']:
+# def is_signature(prediction_result) -> bool:
+def is_signature(boxes) -> bool:
+    """ true if any of the boxes is at any corner, or header or footer """
+    for box in boxes:
+        if box[1][0]-box[0][0]<0.05: # not large enough
+            continue
         if is_corner(box) or is_header(box) or is_footer(box):
             return True
     return False
 
-def detect_with_craft_text_detector(image: PIL.Image.Image):
-    from craft_text_detector import Craft
-    craft = Craft(output_dir='output', crop_type="box", cuda=torch.cuda.is_available(), export_extra=True)
-    result = craft.detect_text( np.asarray(image))
-    annotated = PIL.Image.open('output/image_text_detection.png')  # image with boxes displayed
-    return annotated, result['boxes'], is_signature(result)
-
-def detect_with_craft_hw_ocr(image: PIL.Image.Image):
-    image = np.asarray(image)
-    from craft_hw_ocr import OCR
-    ocr = OCR.load_models()
-    image, results = OCR.detection(image, ocr[2])
-    bboxes, _ = OCR.recoginition(image, results, ocr[0], ocr[1])
-    annotated = OCR.visualize(image, results)
-    return annotated, bboxes, False
-
-def process(image:PIL.Image.Image, lib:str):
-    if image is None:
-        return None,0,False
-    annotated, boxes, signed = detect_with_craft_text_detector(image) if lib=='craft_text_detector' else detect_with_craft_hw_ocr( image)
-    return annotated, len(boxes), signed
-
 gr.Interface(
     fn = process,
-    inputs = [ gr.Image(type="pil", label="Input"), gr.inputs.Radio(label='Model', choices=["craft_text_detector", "craft_hw_ocr"], default='craft_text_detector') ],
-    outputs = [ gr.Image(type="pil", label="Output"), gr.Label(label="nb of text detections"), gr.Label(label="Has signature") ],
+    inputs = [ gr.Image(label="Input"), gr.inputs.Radio(label='Model', choices=["craft_text_detector", "craft_hw_ocr"], default='craft_text_detector') ],
+    outputs = [ gr.Image(label="Output"), gr.Label(label="nb of text detections"), gr.Label(label="Has signature") ],
     title="Detect signature in image",
     description="Is the photo or image watermarked by a signature?",
-    examples=[['data/photologo-1-1.jpg'], ['data/times-square.jpg']],
+    examples=[['data/photologo-1-1.jpg'], ['data/times-square.jpg'], ['data/photologo-3.jpg']],
     allow_flagging="never"
 ).launch(debug=True, enable_queue=True)