Spaces:
Sleeping
Sleeping
File size: 8,145 Bytes
c02c6ce | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 | """
OCR (Optical Character Recognition) module for extracting text from images.
Uses EasyOCR for reliable text detection and recognition.
"""
import logging
from typing import List, Dict, Optional
import easyocr
logger = logging.getLogger(__name__)
class OCREngine:
"""Handle OCR for food labels and expiry dates."""
def __init__(self, languages: List[str] = None, use_gpu: bool = False):
"""
Initialize OCR engine.
Args:
languages: List of language codes (e.g., ['en', 'es'])
use_gpu: Whether to use GPU for OCR
"""
self.languages = languages or ['en']
self.use_gpu = use_gpu
self.reader = None
self._init_reader()
def _init_reader(self):
"""Initialize EasyOCR reader."""
try:
logger.info(f"Initializing OCR reader for languages: {self.languages}")
self.reader = easyocr.Reader(
self.languages,
gpu=self.use_gpu,
model_storage_directory=None
)
logger.info("OCR reader initialized successfully")
except Exception as e:
logger.error(f"Failed to initialize OCR reader: {e}")
raise RuntimeError(f"OCR initialization failed: {e}")
def extract_text(self, image_path: str, confidence_threshold: float = 0.3) -> Dict:
"""
Extract text from image file.
Args:
image_path: Path to image file
confidence_threshold: Minimum confidence for text detection
Returns:
Dictionary with extracted text and metadata
"""
if self.reader is None:
raise RuntimeError("OCR reader not initialized")
logger.info(f"Extracting text from {image_path}")
try:
results = self.reader.readtext(image_path)
extracted_texts = []
for (bbox, text, confidence) in results:
if confidence >= confidence_threshold:
extracted_texts.append({
"text": text.strip(),
"confidence": float(confidence),
"bbox": {
"x": float(bbox[0][0]),
"y": float(bbox[0][1]),
"width": float(bbox[2][0] - bbox[0][0]),
"height": float(bbox[2][1] - bbox[0][1])
}
})
logger.info(f"Extracted {len(extracted_texts)} text regions")
return {
"status": "success",
"texts": extracted_texts,
"full_text": " ".join([t["text"] for t in extracted_texts]),
"num_texts": len(extracted_texts)
}
except Exception as e:
logger.error(f"OCR extraction failed: {e}")
return {
"status": "error",
"error": str(e),
"texts": [],
"full_text": ""
}
def extract_text_from_bytes(
self,
image_bytes: bytes,
confidence_threshold: float = 0.3
) -> Dict:
"""
Extract text from image bytes.
Args:
image_bytes: Image data as bytes
confidence_threshold: Minimum confidence for text detection
Returns:
Dictionary with extracted text and metadata
"""
if self.reader is None:
raise RuntimeError("OCR reader not initialized")
import cv2
import numpy as np
logger.info("Extracting text from image bytes")
try:
# Convert bytes to image
nparr = np.frombuffer(image_bytes, np.uint8)
image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
if image is None:
raise ValueError("Failed to decode image")
# Convert BGR to RGB for EasyOCR
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
results = self.reader.readtext(image)
extracted_texts = []
for (bbox, text, confidence) in results:
if confidence >= confidence_threshold:
extracted_texts.append({
"text": text.strip(),
"confidence": float(confidence),
"bbox": {
"x": float(bbox[0][0]),
"y": float(bbox[0][1]),
"width": float(bbox[2][0] - bbox[0][0]),
"height": float(bbox[2][1] - bbox[0][1])
}
})
logger.info(f"Extracted {len(extracted_texts)} text regions from bytes")
return {
"status": "success",
"texts": extracted_texts,
"full_text": " ".join([t["text"] for t in extracted_texts]),
"num_texts": len(extracted_texts)
}
except Exception as e:
logger.error(f"OCR extraction from bytes failed: {e}")
return {
"status": "error",
"error": str(e),
"texts": [],
"full_text": ""
}
def parse_ingredients_from_text(self, text: str) -> List[str]:
"""
Parse ingredient names from extracted text.
Uses simple heuristics to identify likely ingredient names.
Args:
text: Extracted text from OCR
Returns:
List of potential ingredient names
"""
# Common ingredient keywords
ingredient_keywords = {
"contains", "ingredients", "product", "made from",
"of", "and", "with", "including", "mix"
}
# Split text and filter potential ingredients
words = text.lower().split()
potential_ingredients = []
for word in words:
# Remove common non-ingredient words and punctuation
cleaned = word.strip('.,;:!?()[]{}"\'-').strip()
if (len(cleaned) > 2 and
cleaned not in ingredient_keywords and
not cleaned.isdigit() and
'%' not in cleaned):
potential_ingredients.append(cleaned)
# Remove duplicates and sort
unique_ingredients = list(set(potential_ingredients))
logger.info(f"Parsed {len(unique_ingredients)} potential ingredients from text")
return sorted(unique_ingredients)
def detect_expiry_date(self, text: str) -> Optional[str]:
"""
Attempt to detect expiry date from extracted text.
Looks for common date patterns.
Args:
text: Extracted text from OCR
Returns:
Detected expiry date string or None
"""
import re
# Common expiry date patterns
patterns = [
r'\b(?:exp|expiry|best before|use by)[:\s]*(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b',
r'\b(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b', # General date pattern
r'\b(?:jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)[a-z]*\.?\s+\d{4}\b'
]
text_lower = text.lower()
for pattern in patterns:
matches = re.finditer(pattern, text_lower, re.IGNORECASE)
for match in matches:
return match.group(0) if match.lastindex is None else match.group(1)
return None
# Global OCR instance
_ocr_instance = None
def get_ocr_engine(languages: List[str] = None, use_gpu: bool = False) -> OCREngine:
"""Get or create singleton OCR engine."""
global _ocr_instance
if _ocr_instance is None:
_ocr_instance = OCREngine(languages=languages, use_gpu=use_gpu)
return _ocr_instance
|