Delete ocr_processor.py

ocr_processor.py

@@ -1,118 +0,0 @@
-import cv2
-import numpy as np
-import pytesseract
-from PIL import Image
-import re
-
-class PrescriptionOCR:
-    def __init__(self):
-        self.medication_keywords = [
-            'tablet', 'capsule', 'mg', 'ml', 'injection', 'dose',
-            'twice', 'thrice', 'daily', 'weekly', 'monthly'
-        ]
-    
-    def preprocess_image(self, image):
-        """Enhanced image preprocessing for medical prescriptions"""
-        try:
-            # Convert to numpy array
-            img_array = np.array(image)
-            
-            # Convert to grayscale
-            if len(img_array.shape) == 3:
-                gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY)
-            else:
-                gray = img_array
-            
-            # Noise removal
-            denoised = cv2.medianBlur(gray, 3)
-            
-            # Thresholding
-            _, thresh = cv2.threshold(denoised, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-            
-            # Morphological operations
-            kernel = np.ones((2, 2), np.uint8)
-            processed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
-            
-            return processed
-            
-        except Exception as e:
-            print(f"Image preprocessing error: {e}")
-            return np.array(image)
-    
-    def extract_medication_info(self, text):
-        """Extract medication information from OCR text"""
-        medications = []
-        lines = text.split('\n')
-        
-        for line in lines:
-            line_clean = line.strip()
-            if any(keyword in line_clean.lower() for keyword in self.medication_keywords):
-                # Extract dosage information
-                dosage_pattern = r'(\d+\s*(?:mg|ml|tablet|cap)s?)'
-                dosages = re.findall(dosage_pattern, line_clean, re.IGNORECASE)
-                
-                # Extract frequency
-                freq_pattern = r'(?:once|twice|thrice|\d+\s*times)\s*(?:daily|a day|per day)'
-                frequency = re.findall(freq_pattern, line_clean, re.IGNORECASE)
-                
-                medication_info = {
-                    'text': line_clean,
-                    'dosages': dosages,
-                    'frequency': frequency[0] if frequency else 'Unknown',
-                    'confidence': 'High' if dosages else 'Medium'
-                }
-                medications.append(medication_info)
-        
-        return medications
-    
-    def process_prescription(self, image):
-        """Main method to process prescription and extract information"""
-        try:
-            # Preprocess image
-            processed_img = self.preprocess_image(image)
-            
-            # OCR with medical-specific configuration
-            custom_config = r'--oem 3 --psm 6 -l eng'
-            extracted_text = pytesseract.image_to_string(processed_img, config=custom_config)
-            
-            # Extract medication information
-            medications = self.extract_medication_info(extracted_text)
-            
-            # Calculate confidence score
-            confidence = self.calculate_confidence(extracted_text, medications)
-            
-            return {
-                'raw_text': extracted_text,
-                'medications': medications,
-                'confidence_score': confidence,
-                'medication_count': len(medications)
-            }
-            
-        except Exception as e:
-            return {
-                'raw_text': '',
-                'medications': [],
-                'confidence_score': 0,
-                'error': str(e)
-            }
-    
-    def calculate_confidence(self, text, medications):
-        """Calculate confidence score for OCR extraction"""
-        if not text.strip():
-            return 0
-        
-        # Base score based on text length and medication detection
-        base_score = min(100, len(text) / 10)
-        
-        # Bonus for medication detection
-        medication_bonus = len(medications) * 15
-        
-        # Penalty for likely errors
-        error_penalty = 0
-        if len(text) < 20:
-            error_penalty += 20
-        if len(re.findall(r'[^\w\s.,]', text)) > len(text) * 0.3:
-            error_penalty += 15
-        
-        final_score = base_score + medication_bonus - error_penalty
-        return max(0, min(100, final_score))