add file

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,14 +1,15 @@
----
-title: Ocr Got Proj
-emoji: 📊
-colorFrom: indigo
-colorTo: blue
-sdk: streamlit
-sdk_version: 1.38.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: 'Optical Character Recognition (OCR) on an uploaded image '
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# OCR with General OCR Theory (GOT) Model
+
+This is a web-based Optical Character Recognition (OCR) application using the General OCR Theory (GOT) model to extract text from images.
+
+## How to Run the Project
+
+1. Clone the repository.
+2. Install dependencies: `pip install -r requirements.txt`.
+3. Run the Flask app: `python app.py`.
+4. Open your browser and go to `http://localhost:5000`.
+
+## Features
+- Supports image uploads.
+- Extracts text from images using the GOT model.
+- Displays the extracted text on the web interface.

app.py

@@ -0,0 +1,60 @@
+from flask import Flask, render_template, request
+from model.got_model import perform_ocr  # Import the OCR function
+import os
+import re
+
+app = Flask(__name__)
+app.config['UPLOAD_FOLDER'] = 'uploads/'
+
+# Create the uploads folder if it doesn't exist
+if not os.path.exists(app.config['UPLOAD_FOLDER']):
+    os.makedirs(app.config['UPLOAD_FOLDER'])
+
+# Global variable to store extracted text
+extracted_text_global = ""
+
+@app.route("/", methods=["GET", "POST"])
+def upload_image():
+    global extracted_text_global
+    if request.method == "POST":
+        file = request.files.get("file")  # Get the uploaded file
+        
+        if file:
+            file_path = os.path.join(app.config["UPLOAD_FOLDER"], file.filename)
+            file.save(file_path)  # Save the file to the uploads folder
+
+            # Run the OCR model on the uploaded image
+            extracted_text_global = perform_ocr(file_path)
+
+            # Render the result template, passing the extracted text
+            return render_template("result.html", extracted_text=extracted_text_global)
+        else:
+            # If no file was uploaded, display an error message
+            return render_template("upload.html", error="Please upload a valid image file.")
+    
+    return render_template("upload.html")
+
+@app.route("/search", methods=["POST"])
+def search_text():
+    global extracted_text_global
+    keyword = request.form.get("keyword")
+    
+    if keyword:
+        # Escape special characters in the keyword to avoid conflicts in HTML
+        keyword = keyword.strip()
+
+        # Check if the keyword is found in the extracted text
+        if re.search(keyword, extracted_text_global, re.IGNORECASE):
+            # Use re.sub to replace the keyword with <mark> for case-insensitive highlighting
+            highlighted_text = re.sub(f"({re.escape(keyword)})", r"<mark>\1</mark>", extracted_text_global, flags=re.IGNORECASE)
+            result_message = f"The keyword '{keyword}' was found and highlighted in the text."
+        else:
+            highlighted_text = extracted_text_global
+            result_message = f"The keyword '{keyword}' was not found in the extracted text."
+        
+        # Render the result page with the highlighted text and search result message
+        return render_template("result.html", extracted_text=highlighted_text, search_result=result_message)
+    
+    return render_template("result.html", extracted_text=extracted_text_global, search_result="Please enter a keyword.")
+if __name__ == "__main__":
+    app.run(debug=True)

requirements.txt

@@ -0,0 +1,4 @@
+Flask
+torch
+transformers
+Pillow