Spaces:
Running
Running
import easyocr | |
import numpy as np | |
import cv2 | |
import re | |
reader = easyocr.Reader(['en'], gpu=False) | |
def extract_weight_from_image(pil_img): | |
try: | |
img = np.array(pil_img) | |
# Resize if too large | |
max_dim = 1000 | |
height, width = img.shape[:2] | |
if max(height, width) > max_dim: | |
scale = max_dim / max(height, width) | |
img = cv2.resize(img, None, fx=scale, fy=scale, interpolation=cv2.INTER_AREA) | |
results = reader.readtext(img) | |
best_weight = None | |
best_conf = 0.0 | |
for item in results: | |
if len(item) != 2 or not isinstance(item[1], tuple): | |
continue | |
text, conf = item[1] | |
cleaned = text.lower().strip() | |
# Fix misread characters | |
cleaned = cleaned.replace(",", ".") | |
cleaned = cleaned.replace("o", "0").replace("O", "0") | |
cleaned = cleaned.replace("s", "5").replace("S", "5") | |
cleaned = cleaned.replace("g", "9").replace("G", "6") | |
cleaned = cleaned.replace("kg", "").replace("kgs", "") | |
cleaned = re.sub(r"[^\d\.]", "", cleaned) | |
# Check for number format like 75.5, 102.3 | |
if re.fullmatch(r"\d{2,4}(\.\d{1,3})?", cleaned): | |
if conf > best_conf: | |
best_weight = cleaned | |
best_conf = conf | |
# If nothing matched, return first numeric string found | |
if not best_weight: | |
for item in results: | |
if len(item) != 2 or not isinstance(item[1], tuple): | |
continue | |
text, conf = item[1] | |
fallback = re.sub(r"[^\d\.]", "", text) | |
if fallback and fallback.replace(".", "").isdigit(): | |
best_weight = fallback | |
best_conf = conf | |
break | |
if not best_weight: | |
return "Not detected", 0.0 | |
# Strip leading zeros | |
if "." in best_weight: | |
int_part, dec_part = best_weight.split(".") | |
int_part = int_part.lstrip("0") or "0" | |
best_weight = f"{int_part}.{dec_part}" | |
else: | |
best_weight = best_weight.lstrip("0") or "0" | |
return best_weight, round(best_conf * 100, 2) | |
except Exception as e: | |
return f"Error: {str(e)}", 0.0 | |