Spaces:
Running
Running
| # -*- encoding: utf-8 -*- | |
| import math | |
| import random | |
| import time | |
| from pathlib import Path | |
| import cv2 | |
| import gradio as gr | |
| import numpy as np | |
| from PIL import Image, ImageDraw, ImageFont | |
| from rapidocr_onnxruntime import RapidOCR | |
| def draw_ocr_box_txt(image, boxes, txts, font_path, | |
| scores=None, text_score=0.5): | |
| h, w = image.height, image.width | |
| img_left = image.copy() | |
| img_right = Image.new('RGB', (w, h), (255, 255, 255)) | |
| random.seed(0) | |
| draw_left = ImageDraw.Draw(img_left) | |
| draw_right = ImageDraw.Draw(img_right) | |
| for idx, (box, txt) in enumerate(zip(boxes, txts)): | |
| if scores is not None and float(scores[idx]) < text_score: | |
| continue | |
| color = (random.randint(0, 255), | |
| random.randint(0, 255), | |
| random.randint(0, 255)) | |
| box = [tuple(v) for v in box] | |
| draw_left.polygon(box, fill=color) | |
| draw_right.polygon([box[0][0], box[0][1], | |
| box[1][0], box[1][1], | |
| box[2][0], box[2][1], | |
| box[3][0], box[3][1]], | |
| outline=color) | |
| box_height = math.sqrt((box[0][0] - box[3][0])**2 | |
| + (box[0][1] - box[3][1])**2) | |
| box_width = math.sqrt((box[0][0] - box[1][0])**2 | |
| + (box[0][1] - box[1][1])**2) | |
| if box_height > 2 * box_width: | |
| font_size = max(int(box_width * 0.9), 10) | |
| font = ImageFont.truetype(font_path, font_size, | |
| encoding="utf-8") | |
| cur_y = box[0][1] | |
| for c in txt: | |
| char_size = font.getsize(c) | |
| draw_right.text((box[0][0] + 3, cur_y), c, | |
| fill=(0, 0, 0), font=font) | |
| cur_y += char_size[1] | |
| else: | |
| font_size = max(int(box_height * 0.8), 10) | |
| font = ImageFont.truetype(font_path, font_size, encoding="utf-8") | |
| draw_right.text([box[0][0], box[0][1]], txt, | |
| fill=(0, 0, 0), font=font) | |
| img_left = Image.blend(image, img_left, 0.5) | |
| img_show = Image.new('RGB', (w * 2, h), (255, 255, 255)) | |
| img_show.paste(img_left, (0, 0, w, h)) | |
| img_show.paste(img_right, (w, 0, w * 2, h)) | |
| return np.array(img_show) | |
| def visualize(image_path, boxes, txts, scores, | |
| font_path="./FZYTK.TTF"): | |
| image = Image.open(image_path) | |
| draw_img = draw_ocr_box_txt(image, boxes, | |
| txts, font_path, | |
| scores, | |
| text_score=0.5) | |
| draw_img_save = Path("./inference_results/") | |
| if not draw_img_save.exists(): | |
| draw_img_save.mkdir(parents=True, exist_ok=True) | |
| time_stamp = time.strftime('%Y-%m-%d-%H-%M-%S', time.localtime(time.time())) | |
| image_save = str(draw_img_save / f'{time_stamp}_{Path(image_path).name}') | |
| cv2.imwrite(image_save, draw_img[:, :, ::-1]) | |
| return image_save | |
| def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5): | |
| img = cv2.imread(img_path) | |
| ocr_result, _ = rapid_ocr(img, box_thresh=box_thresh, | |
| unclip_ratio=unclip_ratio, | |
| text_score=text_score) | |
| if not ocr_result: | |
| return img_path, '未识别到有效文本' | |
| dt_boxes, rec_res, scores = list(zip(*ocr_result)) | |
| img_save_path = visualize(img_path, dt_boxes, rec_res, scores) | |
| output_text = [f'{one_rec} {float(score):.4f}' | |
| for one_rec, score in zip(rec_res, scores)] | |
| return img_save_path, output_text | |
| rapid_ocr = RapidOCR() | |
| examples = [['images/1.jpg']] | |
| with gr.Blocks(title='RapidOCR') as demo: | |
| gr.Markdown(""" | |
| <h1><center><a href="https://github.com/RapidAI/RapidOCR" target="_blank">Rapid⚡OCR</a></center></h1> | |
| ### Docs: [Docs](https://rapidocr.rtfd.io/) | |
| ### Parameters docs: [link](https://github.com/RapidAI/RapidOCR/tree/main/python#configyaml%E4%B8%AD%E5%B8%B8%E7%94%A8%E5%8F%82%E6%95%B0%E4%BB%8B%E7%BB%8D) | |
| - **box_thresh**: 检测到的框是文本的概率，值越大，框中是文本的概率就越大。存在漏检时，调低该值。取值范围：[0, 1.0] | |
| - **unclip_ratio**: 控制文本检测框的大小，值越大，检测框整体越大。在出现框截断文字的情况，调大该值。取值范围：[1.5, 2.0] | |
| - **text_score**: 文本识别结果是正确的置信度，值越大，显示出的识别结果更准确。存在漏检时，调低该值。取值范围：[0, 1.0] | |
| ### 运行环境： | |
| - Python: 3.8 | |
| - onnxruntime: 1.14.1 | |
| - rapidocr_onnxruntime: 1.2.5""") | |
| with gr.Box(): | |
| with gr.Row(): | |
| box_thresh = gr.Slider(minimum=0, maximum=1.0, value=0.5, | |
| label='box_thresh', step=0.1, | |
| interactive=True, | |
| info='[0, 1.0]') | |
| unclip_ratio = gr.Slider(minimum=1.5, maximum=2.0, value=1.6, | |
| label='unclip_ratio', step=0.1, | |
| interactive=True, | |
| info='[1.5, 2.0]') | |
| text_score = gr.Slider(minimum=0, maximum=1.0, value=0.5, | |
| label='text_score', step=0.1, | |
| interactive=True, | |
| info='[0, 1.0]') | |
| with gr.Row(): | |
| input_img = gr.Image(type='filepath', label='Input') | |
| with gr.Column(scale=2): | |
| out_img = gr.Image(type='filepath', label='Output_image') | |
| out_txt = gr.outputs.Textbox(type='text', label='Output_text') | |
| button = gr.Button('Submit') | |
| button.click(fn=inference, | |
| inputs=[input_img, box_thresh, unclip_ratio, text_score], | |
| outputs=[out_img, out_txt]) | |
| gr.Examples(examples=examples, | |
| inputs=[input_img, box_thresh, unclip_ratio, text_score], | |
| outputs=[out_img, out_txt], fn=inference) | |
| demo.launch(debug=True, enable_queue=True) | |