🚀 Added advanced Hindi OCR with preprocessing

app.py

@@ -0,0 +1,30 @@
+import gradio as gr
+import pytesseract
+from PIL import Image, ImageEnhance, ImageFilter
+import os
+
+def ocr_image(img):
+    # Image pre-processing
+    img = img.convert("L")  # Grayscale
+    img = img.filter(ImageFilter.SHARPEN)  # Sharpen
+    enhancer = ImageEnhance.Contrast(img)
+    img = enhancer.enhance(2.0)  # Increase contrast
+
+    # OCR with better PSM mode
+    custom_config = r'--oem 3 --psm 6'  # PSM 6: Assume a single uniform block of text
+
+    try:
+        text = pytesseract.image_to_string(img, lang="hin+eng", config=custom_config)
+        return text.strip()
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+demo = gr.Interface(
+    fn=ocr_image,
+    inputs=gr.Image(type="pil", label="📷 Upload Hindi Image (High Quality)"),
+    outputs=gr.Textbox(label="📝 OCR Result"),
+    title="🧠 Hindi OCR - High Accuracy",
+    description="Upload sharp, clear Hindi text image. This OCR boosts contrast & sharpness before scanning. Powered by Tesseract!"
+)
+
+demo.launch()

packages.txt

@@ -0,0 +1,6 @@
+tesseract-ocr
+tesseract-ocr-hin
+libglib2.0-0
+libsm6
+libxrender1
+libxext6

requirements.txt

@@ -0,0 +1,2 @@
+pytesseract
+Pillow