File size: 2,504 Bytes
b9e018b e651999 03b6d75 b9e018b e651999 03b6d75 e651999 03b6d75 e651999 03b6d75 b9e018b e651999 03b6d75 2d2df69 e651999 03b6d75 e651999 03b6d75 e651999 2d2df69 03b6d75 2d2df69 03b6d75 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 |
import os
import gradio as gr
from Plan.AiLLM import llm_recognition
from Plan.pytesseractOCR import ocr_recognition
from Preprocess.preprocessImg import preprocess_image001, preprocess_image002
# 取得所有語言清單
languages = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
def preprocess_and_ocr(image, valid_type, language):
# 方案一
pre_img_001 = preprocess_image001(image)
ocr_result_001 = ocr_recognition(pre_img_001, valid_type, language)
# 方案二
pre_img_002 = preprocess_image002(image)
ocr_result_002 = ocr_recognition(pre_img_002, valid_type, language)
return pre_img_001, pre_img_002, ocr_result_001, ocr_result_002
def preprocess_and_llm(image, valid_type, language):
# 方案一
pre_img_001 = preprocess_image001(image)
llm_result_001 = llm_recognition(pre_img_001, valid_type, language)
# 方案二
pre_img_002 = preprocess_image002(image)
llm_result_002 = llm_recognition(pre_img_002, valid_type, language)
return pre_img_001, pre_img_002, llm_result_001, llm_result_002
with gr.Blocks() as demo:
with gr.Row():
image_input = gr.Image(type="pil", label="上傳圖片")
preprocess_output_001 = gr.Image(type="pil", label="預處理後的圖片-方案一")
preprocess_output_002 = gr.Image(type="pil", label="預處理後的圖片-方案二")
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")
# preprocessed_type = gr.Radio(["001", "002"], label="解析方案")
with gr.Row():
ocr_button = gr.Button("使用 OCR")
llm_button = gr.Button("使用 AI LLM")
with gr.Row():
ocr_output_001 = gr.JSON(label="OCR-001-解析結果")
ocr_output_002 = gr.JSON(label="OCR-002-解析結果")
llm_output_001 = gr.JSON(label="AiLLM-001 解析結果")
llm_output_002 = gr.JSON(label="AiLLM-002 解析結果")
ocr_button.click(preprocess_and_ocr, inputs=[image_input, validation_type, language_dropdown],
outputs=[preprocess_output_001, preprocess_output_002, ocr_output_001, ocr_output_002])
llm_button.click(preprocess_and_llm, inputs=[image_input, validation_type, language_dropdown],
outputs=[preprocess_output_001, preprocess_output_002, llm_output_001, llm_output_002])
demo.launch(share=False)
|