Update app.py

app.py

@@ -1,17 +1,15 @@
-import cv2
-import numpy as np
 import torch
-import pytesseract
-import easyocr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
 import gradio as gr
-from yolov5 import YOLOv5
 import re
+import cv2
+import numpy as np
 
-# Load YOLOv5 model (pre-trained)
-model = YOLOv5('yolov5s.pt', device='cpu')
-
-# Load EasyOCR
-ocr_reader = easyocr.Reader(['en'])
+# Load BLIP model
+device = "cuda" if torch.cuda.is_available() else "cpu"
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
 
 # Image Preprocessing (Sharpen & Deblur)
 def enhance_image(image):
@@ -20,15 +18,12 @@ def enhance_image(image):
     sharpened = cv2.filter2D(image, -1, kernel)
     return sharpened
 
-# Detect Digits Using YOLOv5
-def detect_digits(image):
-    results = model(image)
-    digits = [det.xyxy.tolist()[0] for det in results.pred[0] if det.conf > 0.5]
-    return digits
-
-# Extract Text Using OCR
+# Extract Text Using BLIP
 def extract_text(image):
-    text = pytesseract.image_to_string(image, config='--psm 6')
+    image = Image.fromarray(image)
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    generated_ids = model.generate(**inputs)
+    text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
     return text
 
 # Extract Weight Using Regex
@@ -39,7 +34,6 @@ def extract_weight(text):
 # Full Processing Pipeline
 def process_image(image):
     enhanced = enhance_image(image)
-    digits = detect_digits(image)
     text = extract_text(enhanced)
     weight = extract_weight(text)
     return weight or "No weight detected"