File size: 3,175 Bytes
b9e018b e651999 2d7bdf0 e651999 b9e018b e871a21 b9e018b e871a21 b9e018b e651999 93d3635 c8fd47b c6f1797 e651999 c6f1797 e651999 b9e018b e651999 2d2df69 e651999 2d2df69 e651999 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import os
import gradio as gr
import pytesseract
from Plan.AiLLM import llm_recognition
from Plan.pytesseractOCR import ocr_recognition
from Preprocess.preprocessImg import preprocess_image001
langs = []
choices = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
# If you don't have tesseract executable in your PATH, include the following:
# pytesseract.pytesseract.tesseract_cmd = r'<full_path_to_your_tesseract_executable>'
# Example tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract'
# Simple image to string
# print(pytesseract.image_to_string(Image.open('eurotext.png')))
# # French text image to string
# print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='fra'))
# # Get bounding box estimates
# print(pytesseract.image_to_boxes(Image.open('test.png')))
# # Get verbose data including boxes, confidences, line and page numbers
# print(pytesseract.image_to_data(Image.open('test.png')))
# # Get information about orientation and script detection
# print(pytesseract.image_to_osd(Image.open('test.png'))
# 取得所有語言清單
languages = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
print(' ======================================================== ')
# print(' ###### choices:' + choices)
# print(' ###### GET ENV - TESSDATA_PREFIX:' + os.getenv('TESSDATA_PREFIX'))
# print(' ###### OS - TESSDATA_PREFIX:' + os.environ['TESSDATA_PREFIX'])
# os.environ['TESSDATA_PREFIX'] = os.getenv('TESSDATA_PREFIX')
# print(' ###### Tesseract_Cmd:' + pytesseract.pytesseract.tesseract_cmd)
# pytesseract.pytesseract.tesseract_cmd = os.getenv('TESSDATA_PREFIX')
print(' ======================================================== ')
def preprocess_and_ocr(image, validation_type, language):
preprocessed_image = preprocess_image001(image)
ocr_result = ocr_recognition(preprocessed_image, validation_type, language)
return preprocessed_image, ocr_result
def preprocess_and_llm(image, validation_type, language):
preprocessed_image = preprocess_image001(image)
llm_result = llm_recognition(preprocessed_image, validation_type, language)
return preprocessed_image, llm_result
with gr.Blocks() as demo:
with gr.Row():
image_input = gr.Image(type="pil", label="上傳圖片")
preprocess_output = gr.Image(type="pil", label="預處理後的圖片")
with gr.Row():
validation_type = gr.Dropdown(choices=["身分證正面", "身分證反面"], label="驗證類別")
language_dropdown = gr.Dropdown(choices=languages, value="chi_tra", label="語言")
with gr.Row():
ocr_button = gr.Button("使用 OCR")
llm_button = gr.Button("使用 AI LLM")
with gr.Row():
ocr_output = gr.JSON(label="OCR 解析結果")
llm_output = gr.JSON(label="AI LLM 解析結果")
ocr_button.click(preprocess_and_ocr, inputs=[image_input, validation_type, language_dropdown],
outputs=[preprocess_output, ocr_output])
llm_button.click(preprocess_and_llm, inputs=[image_input, validation_type, language_dropdown],
outputs=[preprocess_output, llm_output])
demo.launch(share=False)
|