Update app.py

app.py

@@ -1,37 +1,80 @@
-<?php
-defined('BASEPATH') or exit('No direct script access allowed');
-
-class OcrClient extends CI_Controller
-{
-    public function process_image()
-    {
-        $url = 'http://<your-streamlit-app-url>/'; // Update with your Streamlit app URL
-        $imagePath = '/path/to/image.jpg'; // Path to the image file on the server
-
-        $curl = curl_init();
-        curl_setopt($curl, CURLOPT_URL, $url);
-        curl_setopt($curl, CURLOPT_POST, 1);
-        curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
-
-        // Attach the image file
-        $cfile = curl_file_create($imagePath, 'image/jpeg', 'image.jpg');
-        curl_setopt($curl, CURLOPT_POSTFIELDS, ['file' => $cfile]);
-
-        // Execute the cURL request
-        $response = curl_exec($curl);
-        $httpCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
-        curl_close($curl);
-
-        // Handle the response
-        if ($httpCode === 200) {
-            $result = json_decode($response, true);
-            if (isset($result['extracted_text'])) {
-                echo "Extracted Text: " . $result['extracted_text'];
-            } else {
-                echo "Error: Unexpected response from the API.";
-            }
-        } else {
-            echo "Error: Unable to connect to the OCR service.";
-        }
-    }
-}
+import streamlit as st
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+from PIL import Image
+import cv2
+import numpy as np
+
+# Load the model and processor
+@st.cache_resource
+def load_model():
+    processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+    model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
+    return processor, model
+
+processor, model = load_model()
+
+# Helper function to preprocess the image and detect lines
+def detect_lines(image, min_height=20, min_width=100):
+    # Convert the PIL image to a NumPy array
+    image_np = np.array(image)
+
+    # Convert to grayscale
+    gray = cv2.cvtColor(image_np, cv2.COLOR_RGB2GRAY)
+
+    # Apply binary thresholding
+    _, binary = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
+
+    # Dilate to merge nearby text
+    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
+    dilated = cv2.dilate(binary, kernel, iterations=1)
+
+    # Find contours
+    contours, _ = cv2.findContours(dilated, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+
+    # Sort contours top-to-bottom
+    bounding_boxes = [cv2.boundingRect(c) for c in contours]
+    bounding_boxes = sorted(bounding_boxes, key=lambda b: b[1])  # Sort by y-coordinate
+
+    # Filter out small contours and merge nearby ones
+    filtered_boxes = []
+    for x, y, w, h in bounding_boxes:
+        if h >= min_height and w >= min_width:  # Filter small boxes
+            filtered_boxes.append((x, y, w, h))
+
+    # Extract individual lines as images
+    line_images = []
+    for (x, y, w, h) in filtered_boxes:
+        line = image_np[y:y+h, x:x+w]
+        line_images.append(line)
+
+    return line_images
+
+# Streamlit app
+st.title("OCR API Service with Multiline Support")
+
+# Handle image upload
+uploaded_file = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    try:
+        # Load and process the uploaded image
+        image = Image.open(uploaded_file).convert("RGB")
+        line_images = detect_lines(image, min_height=30, min_width=100)
+
+        # Perform OCR on each detected line
+        extracted_text = ""
+        for line_img in line_images:
+            line_pil = Image.fromarray(line_img)
+            pixel_values = processor(images=line_pil, return_tensors="pt").pixel_values
+            generated_ids = model.generate(pixel_values)
+            generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+            extracted_text += f"{generated_text}\n"
+
+        # Simulate API-like JSON response
+        json_response = {"extracted_text": extracted_text}
+
+        # Return JSON response
+        st.write(json_response)  # This is the response to your CodeIgniter client
+    except Exception as e:
+        # Return an error response
+        st.write({"error": str(e)})