import PIL.Image import gradio as gr import torch import numpy as np 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): """ A box happen to be a 4-pixel list in order 1 -- 2 4 -- 3 """ return box[2][0]<=dw and box[2][1]<= dh def is_ne(box): return box[3][0]>=1-dw and box[3][1]<= dh def is_se(box): return box[0][0]>=1-dw and box[0][1]>= 1-dh def is_sw(box): return box[1][0]<=dw and box[1][1]>= 1-dh def is_corner(box)->bool: """ @:returns true if the box is located in any corner """ return is_nw(box) or is_ne(box) or is_se(box) or is_sw(box) dhhf=0.2 # dh for header and footer def is_footer(box)->bool: """ true if for the 2 first points, y>0.8 """ return box[0][1]>=1-dhhf and box[1][1]>=1-dhhf 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: 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 gr.Interface( fn = process, 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'], ['data/photologo-3.jpg']], allow_flagging="never" ).launch(debug=True, enable_queue=True)