Spaces:
Runtime error
Runtime error
| # from flair.data import Sentence | |
| # from flair.models import SequenceTagger | |
| # import streamlit as st | |
| # # load tagger | |
| # tagger = SequenceTagger.load("flair/ner-english-large") | |
| # # make example sentence | |
| # text=st.text_area("Enter the text to detect it's named entities") | |
| # sentence = Sentence(text) | |
| # # predict NER tags | |
| # tagger.predict(sentence) | |
| # # print sentence | |
| # print(sentence) | |
| # # print predicted NER spans | |
| # print('The following NER tags are found:') | |
| # # iterate over entities and printx | |
| # for entity in sentence.get_spans('ner'): | |
| # print(entity) | |
| import easyocr | |
| import cv2 | |
| import requests | |
| import re | |
| from PIL import Image | |
| import streamlit as st | |
| # import os | |
| # Load the EasyOCR reader | |
| reader = easyocr.Reader(['en']) | |
| # key=os.environ.getattribute("api_key") | |
| # print(key) | |
| API_URL = "https://api-inference.huggingface.co/models/flair/ner-english-large" | |
| headers = {"Authorization": st.secrets["api_key"]} | |
| ## Image uploading function ## | |
| def image_upload_and_ocr(reader): | |
| uploaded_file=st.file_uploader(label=':red[**please upload a busines card** :sunglasses:]',type=['jpeg','jpg','png','webp']) | |
| if uploaded_file is not None: | |
| image=Image.open(uploaded_file) | |
| image=image.resize((640,480)) | |
| result2 = reader.readtext(image) | |
| # result2=result | |
| texts = [item[1] for item in result2] | |
| result=' '.join(texts) | |
| return result2,result | |
| def query(payload): | |
| response = requests.post(API_URL, headers=headers, json=payload) | |
| return response.json() | |
| def get_ner_from_transformer(output): | |
| data = output | |
| named_entities = {} | |
| for entity in data: | |
| entity_type = entity['entity_group'] | |
| entity_text = entity['word'] | |
| if entity_type not in named_entities: | |
| named_entities[entity_type] = [] | |
| named_entities[entity_type].append(entity_text) | |
| # for entity_type, entities in named_entities.items(): | |
| # print(f"{entity_type}: {', '.join(entities)}") | |
| return entity_type,named_entities | |
| ### DRAWING DETECTION FUNCTION ### | |
| def drawing_detection(image): | |
| # Draw bounding boxes around the detected text regions | |
| for detection in image: | |
| # Extract the bounding box coordinates | |
| points = detection[0] # List of points defining the bounding box | |
| x1, y1 = int(points[0][0]), int(points[0][1]) # Top-left corner | |
| x2, y2 = int(points[2][0]), int(points[2][1]) # Bottom-right corner | |
| # Draw the bounding box | |
| cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2) | |
| # Add the detected text | |
| text = detection[1] | |
| cv2.putText(image, text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2) | |
| st.image(image,caption='Detected text on the card ',width=710) | |
| return image | |
| st.title("_Business_ card data extractor using opencv and streamlit :sunglasses:") | |
| res2,res=image_upload_and_ocr(reader) | |
| darwing_image=drawing_detection(res2) | |
| output = query({ | |
| "inputs": res, | |
| }) | |
| entity_type,named_entities= get_ner_from_transformer(output) | |
| st.write(entity_type) | |
| st.write(named_entities) |