Mycha / app.py
Youssouf Traore
Update app.py
94affbe
raw
history blame
949 Bytes
import gradio as gr
import pytesseract
from PIL import Image
import cv2
def extract_text(image):
img_cv = cv2.imread(image)
# By default OpenCV stores images in BGR format and since pytesseract assumes RGB format,
# we need to convert from BGR to RGB format/mode:
img_rgb = cv2.cvtColor(img_cv, cv2.COLOR_BGR2RGB)
print(pytesseract.image_to_string(img_rgb))
# OR
img_rgb = Image.frombytes('RGB', img_cv.shape[:2], img_cv, 'raw', 'BGR', 0, 0)
print(pytesseract.image_to_string(img_rgb))
# Définir l'interface utilisateur Gradio
inputs = gr.inputs.Image()
outputs = gr.outputs.Textbox()
interface = gr.Interface(fn=extract_text, inputs=inputs, outputs=outputs,
title="Extraction de texte à partir d'une image",
description="Téléchargez une image contenant du texte et cliquez sur 'Predict' pour extraire le texte.")
interface.launch()