Update ocr_engine.py

ocr_engine.py

@@ -3,72 +3,145 @@ import numpy as np
 import cv2
 import re
 import logging
+from datetime import datetime
+import os
+from PIL import Image, ImageEnhance
 
-# Set up logging for debugging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+# Set up logging for detailed debugging
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
 
-# Initialize EasyOCR
+# Initialize EasyOCR with English and GPU disabled (enable if you have a compatible GPU)
 easyocr_reader = easyocr.Reader(['en'], gpu=False)
 
+# Directory for debug images
+DEBUG_DIR = "debug_images"
+os.makedirs(DEBUG_DIR, exist_ok=True)
+
+def save_debug_image(img, filename_suffix, prefix=""):
+    """Saves an image to the debug directory with a timestamp."""
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S_%f")
+    filename = os.path.join(DEBUG_DIR, f"{prefix}{timestamp}_{filename_suffix}.png")
+    if len(img.shape) == 3:  # Color image
+        cv2.imwrite(filename, img)
+    else:  # Grayscale image
+        cv2.imwrite(filename, img)
+    logging.debug(f"Saved debug image: {filename}")
+
 def estimate_brightness(img):
     """Estimate image brightness to detect illuminated displays"""
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-    return np.mean(gray)
+    brightness = np.mean(gray)
+    logging.debug(f"Estimated brightness: {brightness}")
+    return brightness
+
+def preprocess_image(img):
+    """Enhance contrast, brightness, and reduce noise for better digit detection"""
+    # Convert to PIL for initial enhancement
+    pil_img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
+    pil_img = ImageEnhance.Contrast(pil_img).enhance(2.0)  # Stronger contrast
+    pil_img = ImageEnhance.Brightness(pil_img).enhance(1.3)  # Moderate brightness boost
+    img = cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)
+    save_debug_image(img, "00_preprocessed_pil")
+
+    # Apply CLAHE to enhance local contrast
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+    enhanced = clahe.apply(gray)
+    save_debug_image(enhanced, "00_clahe_enhanced")
+
+    # Apply bilateral filter to reduce noise while preserving edges
+    filtered = cv2.bilateralFilter(enhanced, d=11, sigmaColor=100, sigmaSpace=100)
+    save_debug_image(filtered, "00_bilateral_filtered")
+    return filtered
 
 def detect_roi(img):
     """Detect and crop the region of interest (likely the digital display)"""
     try:
-        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+        save_debug_image(img, "01_original")
+        gray = preprocess_image(img)
+        save_debug_image(gray, "02_preprocessed_grayscale")
+
+        # Try multiple thresholding methods
         brightness = estimate_brightness(img)
-        thresh_value = 230 if brightness > 100 else 190
-        _, thresh = cv2.threshold(gray, thresh_value, 255, cv2.THRESH_BINARY)
-        kernel = np.ones((9, 9), np.uint8)
-        dilated = cv2.dilate(thresh, kernel, iterations=3)
+        if brightness > 150:
+            thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
+                                           cv2.THRESH_BINARY, 31, 5)
+            save_debug_image(thresh, "03_roi_adaptive_threshold_high")
+        else:
+            _, thresh = cv2.threshold(gray, 40, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+            save_debug_image(thresh, "03_roi_otsu_threshold_low")
+
+        # Morphological operations to clean up noise and connect digits
+        kernel = np.ones((5, 5), np.uint8)
+        thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=2)
+        save_debug_image(thresh, "03_roi_morph_cleaned")
+
+        kernel = np.ones((11, 11), np.uint8)
+        dilated = cv2.dilate(thresh, kernel, iterations=5)
+        save_debug_image(dilated, "04_roi_dilated")
+
         contours, _ = cv2.findContours(dilated, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+
         if contours:
-            valid_contours = [c for c in contours if cv2.contourArea(c) > 500]
+            img_area = img.shape[0] * img.shape[1]
+            valid_contours = []
+            for c in contours:
+                area = cv2.contourArea(c)
+                if 200 < area < (img_area * 0.99):  # Very relaxed area filter
+                    x, y, w, h = cv2.boundingRect(c)
+                    aspect_ratio = w / h if h > 0 else 0
+                    if 0.5 <= aspect_ratio <= 10.0 and w > 30 and h > 20:  # Very relaxed filters
+                        valid_contours.append(c)
+
             if valid_contours:
-                for contour in sorted(valid_contours, key=cv2.contourArea, reverse=True):
-                    x, y, w, h = cv2.boundingRect(contour)
-                    aspect_ratio = w / h
-                    if 1.5 <= aspect_ratio <= 4.0 and w > 50 and h > 30:
-                        x, y = max(0, x-40), max(0, y-40)
-                        w, h = min(w+80, img.shape[1]-x), min(h+80, img.shape[0]-y)
-                        return img[y:y+h, x:x+w], (x, y, w, h)
+                contour = max(valid_contours, key=cv2.contourArea)  # Largest contour
+                x, y, w, h = cv2.boundingRect(contour)
+                padding = 100  # Generous padding
+                x, y = max(0, x - padding), max(0, y - padding)
+                w, h = min(w + 2 * padding, img.shape[1] - x), min(h + 2 * padding, img.shape[0] - y)
+                roi_img = img[y:y+h, x:x+w]
+                save_debug_image(roi_img, "05_detected_roi")
+                logging.info(f"Detected ROI with dimensions: ({x}, {y}, {w}, {h})")
+                return roi_img, (x, y, w, h)
+
+        logging.info("No suitable ROI found, returning preprocessed image.")
+        save_debug_image(img, "05_no_roi_original_fallback")
         return img, None
     except Exception as e:
         logging.error(f"ROI detection failed: {str(e)}")
+        save_debug_image(img, "05_roi_detection_error_fallback")
         return img, None
 
 def detect_segments(digit_img):
     """Detect seven-segment patterns in a digit image"""
     h, w = digit_img.shape
-    if h < 10 or w < 10:
+    if h < 8 or w < 4:  # Very relaxed size constraints
+        logging.debug(f"Digit image too small: {w}x{h}")
         return None
 
-    # Define segment regions (top, middle, bottom, left-top, left-bottom, right-top, right-bottom)
     segments = {
-        'top': (0, w, 0, h//5),
-        'middle': (0, w, 2*h//5, 3*h//5),
-        'bottom': (0, w, 4*h//5, h),
-        'left_top': (0, w//5, 0, h//2),
-        'left_bottom': (0, w//5, h//2, h),
-        'right_top': (4*w//5, w, 0, h//2),
-        'right_bottom': (4*w//5, w, h//2, h)
+        'top': (int(w*0.1), int(w*0.9), 0, int(h*0.25)),
+        'middle': (int(w*0.1), int(w*0.9), int(h*0.35), int(h*0.65)),
+        'bottom': (int(w*0.1), int(w*0.9), int(h*0.75), h),
+        'left_top': (0, int(w*0.3), int(h*0.05), int(h*0.55)),
+        'left_bottom': (0, int(w*0.3), int(h*0.45), int(h*0.95)),
+        'right_top': (int(w*0.7), w, int(h*0.05), int(h*0.55)),
+        'right_bottom': (int(w*0.7), w, int(h*0.45), int(h*0.95))
     }
 
     segment_presence = {}
     for name, (x1, x2, y1, y2) in segments.items():
+        x1, y1 = max(0, x1), max(0, y1)
+        x2, y2 = min(w, x2), min(h, y2)
         region = digit_img[y1:y2, x1:x2]
         if region.size == 0:
-            return None
-        # Count white pixels in the region
+            segment_presence[name] = False
+            continue
         pixel_count = np.sum(region == 255)
         total_pixels = region.size
-        # Segment is present if more than 50% of the region is white
-        segment_presence[name] = pixel_count > total_pixels * 0.5
+        segment_presence[name] = pixel_count / total_pixels > 0.3  # Very low threshold
+        logging.debug(f"Segment {name}: {pixel_count}/{total_pixels} = {pixel_count/total_pixels:.2f}")
 
-    # Seven-segment digit patterns
     digit_patterns = {
         '0': ('top', 'bottom', 'left_top', 'left_bottom', 'right_top', 'right_bottom'),
         '1': ('right_top', 'right_bottom'),
@@ -83,140 +156,237 @@ def detect_segments(digit_img):
     }
 
     best_match = None
-    max_matches = 0
+    max_score = -1
     for digit, pattern in digit_patterns.items():
         matches = sum(1 for segment in pattern if segment_presence.get(segment, False))
-        non_matches = sum(1 for segment in segment_presence if segment not in pattern and segment_presence[segment])
-        score = matches - non_matches
-        if score > max_matches:
-            max_matches = score
+        non_matches_penalty = sum(1 for segment in segment_presence if segment not in pattern and segment_presence[segment])
+        current_score = matches - non_matches_penalty
+        if all(segment_presence.get(s, False) for s in pattern):
+            current_score += 0.5
+        if current_score > max_score:
+            max_score = current_score
             best_match = digit
-
+        elif current_score == max_score and best_match is not None:
+            current_digit_non_matches = sum(1 for segment in segment_presence if segment not in pattern and segment_presence[segment])
+            best_digit_pattern = digit_patterns[best_match]
+            best_digit_non_matches = sum(1 for segment in segment_presence if segment not in best_digit_pattern and segment_presence[segment])
+            if current_digit_non_matches < best_digit_non_matches:
+                best_match = digit
+    
+    logging.debug(f"Segment presence: {segment_presence}, Detected digit: {best_match}")
     return best_match
 
 def custom_seven_segment_ocr(img, roi_bbox):
     """Perform custom OCR for seven-segment displays"""
     try:
         gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-        _, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+        brightness = estimate_brightness(img)
+        # Try multiple thresholding approaches
+        if brightness > 150:
+            _, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+            save_debug_image(thresh, "06_roi_otsu_threshold")
+        else:
+            _, thresh = cv2.threshold(gray, 30, 255, cv2.THRESH_BINARY)
+            save_debug_image(thresh, "06_roi_simple_threshold")
+        
+        # Morphological cleaning
+        kernel = np.ones((3, 3), np.uint8)
+        thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
+        save_debug_image(thresh, "06_roi_morph_cleaned")
 
-        # Use EasyOCR to get bounding boxes for digits
         results = easyocr_reader.readtext(thresh, detail=1, paragraph=False, 
-                                        contrast_ths=0.1, adjust_contrast=0.7, 
-                                        text_threshold=0.9, mag_ratio=1.5, 
-                                        allowlist='0123456789.')
-
+                                         contrast_ths=0.1, adjust_contrast=1.0, 
+                                         text_threshold=0.3, mag_ratio=4.0, 
+                                         allowlist='0123456789.-', y_ths=0.6)
+        
+        logging.info(f"Custom OCR EasyOCR results: {results}")
         if not results:
+            logging.info("Custom OCR EasyOCR found no digits.")
             return None
 
-        # Sort bounding boxes left to right
-        digits = []
-        for (bbox, _, _) in results:
+        digits_info = []
+        for (bbox, text, conf) in results:
             (x1, y1), (x2, y2), (x3, y3), (x4, y4) = bbox
-            x_min, x_max = min(x1, x4), max(x2, x3)
-            y_min, y_max = min(y1, y2), max(y3, y4)
-            digits.append((x_min, x_max, y_min, y_max))
-
-        digits.sort(key=lambda x: x[0])  # Sort by x_min (left to right)
+            h_bbox = max(y1, y2, y3, y4) - min(y1, y2, y3, y4)
+            if len(text) == 1 and (text.isdigit() or text in '.-') and h_bbox > 4:
+                x_min, x_max = int(min(x1, x4)), int(max(x2, x3))
+                y_min, y_max = int(min(y1, y2)), int(max(y3, y4))
+                digits_info.append((x_min, x_max, y_min, y_max, text, conf))
 
-        # Extract and recognize each digit
+        digits_info.sort(key=lambda x: x[0])
         recognized_text = ""
-        for x_min, x_max, y_min, y_max in digits:
-            x_min, y_min = max(0, int(x_min)), max(0, int(y_min))
-            x_max, y_max = min(thresh.shape[1], int(x_max)), min(thresh.shape[0], int(y_max))
+        for idx, (x_min, x_max, y_min, y_max, easyocr_char, easyocr_conf) in enumerate(digits_info):
+            x_min, y_min = max(0, x_min), max(0, y_min)
+            x_max, y_max = min(thresh.shape[1], x_max), min(thresh.shape[0], y_max)
             if x_max <= x_min or y_max <= y_min:
                 continue
-            digit_img = thresh[y_min:y_max, x_min:x_max]
-            digit = detect_segments(digit_img)
-            if digit:
-                recognized_text += digit
-
-        # Validate the recognized text
-        text = recognized_text
-        text = re.sub(r"[^\d\.]", "", text)
-        if re.fullmatch(r"\d{1,4}(\.\d{0,3})?", text):
-            return text
+            digit_img_crop = thresh[y_min:y_max, x_min:x_max]
+            save_debug_image(digit_img_crop, f"07_digit_crop_{idx}_{easyocr_char}")
+            if easyocr_conf > 0.8 or easyocr_char in '.-' or digit_img_crop.shape[0] < 8 or digit_img_crop.shape[1] < 4:
+                recognized_text += easyocr_char
+            else:
+                digit_from_segments = detect_segments(digit_img_crop)
+                if digit_from_segments:
+                    recognized_text += digit_from_segments
+                else:
+                    recognized_text += easyocr_char
+        
+        logging.info(f"Custom OCR before validation, recognized_text: {recognized_text}")
+        # Relaxed validation for debugging
+        if recognized_text:
+            return recognized_text
+        logging.info(f"Custom OCR text '{recognized_text}' failed validation.")
         return None
     except Exception as e:
         logging.error(f"Custom seven-segment OCR failed: {str(e)}")
         return None
 
 def extract_weight_from_image(pil_img):
+    """Extract weight from a PIL image of a digital scale display"""
     try:
         img = np.array(pil_img)
         img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+        save_debug_image(img, "00_input_image")
 
         brightness = estimate_brightness(img)
-        conf_threshold = 0.9 if brightness > 100 else 0.7
+        conf_threshold = 0.3 if brightness > 150 else (0.2 if brightness > 80 else 0.1)
 
-        # Detect ROI
         roi_img, roi_bbox = detect_roi(img)
-
-        # Try custom seven-segment OCR first
         custom_result = custom_seven_segment_ocr(roi_img, roi_bbox)
         if custom_result:
-            # Format the custom result
-            if "." in custom_result:
-                int_part, dec_part = custom_result.split(".")
-                int_part = int_part.lstrip("0") or "0"
-                custom_result = f"{int_part}.{dec_part.rstrip('0')}"
-            else:
-                custom_result = custom_result.lstrip('0') or "0"
-            return custom_result, 100.0  # High confidence for custom OCR
+            # Basic cleaning
+            text = re.sub(r"[^\d\.\-]", "", custom_result)  # Allow negative signs
+            if text.count('.') > 1:
+                text = text.replace('.', '', text.count('.') - 1)
+            if text:
+                if text.startswith('.'):
+                    text = "0" + text
+                if text.endswith('.'):
+                    text = text.rstrip('.')
+                if text == '.' or text == '':
+                    logging.warning(f"Custom OCR result '{text}' is invalid after cleaning.")
+                else:
+                    try:
+                        float(text)
+                        logging.info(f"Custom OCR result: {text}, Confidence: 100.0%")
+                        return text, 100.0
+                    except ValueError:
+                        logging.warning(f"Custom OCR result '{text}' is not a valid number, falling back.")
+            logging.warning(f"Custom OCR result '{custom_result}' failed validation, falling back.")
 
-        # Fallback to EasyOCR if custom OCR fails
-        images_to_process = [
-            ("raw", roi_img, {'contrast_ths': 0.1, 'adjust_contrast': 0.7, 'text_threshold': 0.9, 'mag_ratio': 1.5, 'allowlist': '0123456789.'}),
-        ]
+        logging.info("Custom OCR failed or invalid, falling back to general EasyOCR.")
+        processed_roi_img = preprocess_image(roi_img)
+        
+        # Try multiple thresholding approaches
+        if brightness > 150:
+            thresh = cv2.adaptiveThreshold(processed_roi_img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
+                                           cv2.THRESH_BINARY, 41, 7)
+            save_debug_image(thresh, "09_fallback_adaptive_thresh")
+        else:
+            _, thresh = cv2.threshold(processed_roi_img, 30, 255, cv2.THRESH_BINARY)
+            save_debug_image(thresh, "09_fallback_simple_thresh")
+
+        # Morphological cleaning
+        kernel = np.ones((3, 3), np.uint8)
+        thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
+        save_debug_image(thresh, "09_fallback_morph_cleaned")
+
+        results = easyocr_reader.readtext(thresh, detail=1, paragraph=False, 
+                                         contrast_ths=0.1, adjust_contrast=1.0, 
+                                         text_threshold=0.2, mag_ratio=5.0, 
+                                         allowlist='0123456789.-', batch_size=4, y_ths=0.6)
 
         best_weight = None
         best_conf = 0.0
         best_score = 0.0
-
-        for mode, proc_img, ocr_params in images_to_process:
-            if mode == "raw":
-                proc_img = cv2.cvtColor(proc_img, cv2.COLOR_BGR2GRAY)
-            results = easyocr_reader.readtext(proc_img, detail=1, paragraph=False, **ocr_params)
-            
-            for (bbox, text, conf) in results:
-                text = text.lower().strip()
-                text = text.replace(",", ".").replace(";", ".")
-                text = text.replace("o", "0").replace("O", "0")
-                text = text.replace("s", "5").replace("S", "5")
-                text = text.replace("g", "9").replace("G", "6")
-                text = text.replace("l", "1").replace("I", "1")
-                text = text.replace("b", "8").replace("B", "8")
-                text = text.replace("z", "2").replace("Z", "2")
-                text = text.replace("q", "9").replace("Q", "9")
-                text = text.replace("kgs", "").replace("kg", "").replace("k", "")
-                text = re.sub(r"[^\d\.]", "", text)
-
-                if re.fullmatch(r"\d{1,4}(\.\d{0,3})?", text):
-                    try:
-                        weight = float(text)
-                        range_score = 1.0 if 0.1 <= weight <= 500 else 0.3
-                        digit_score = 1.5 if 10 <= weight < 100 else 1.0
-                        score = conf * range_score * digit_score
-                        if score > best_score and conf > conf_threshold:
-                            best_weight = text
-                            best_conf = conf
-                            best_score = score
-                    except ValueError:
-                        continue
+        for (bbox, text, conf) in results:
+            logging.info(f"Fallback EasyOCR raw text: {text}, Confidence: {conf}")
+            text = text.lower().strip()
+            text = text.replace(",", ".").replace(";", ".").replace(":", ".").replace(" ", "")
+            text = text.replace("o", "0").replace("O", "0").replace("q", "0").replace("Q", "0")
+            text = text.replace("s", "5").replace("S", "5")
+            text = text.replace("g", "9").replace("G", "6")
+            text = text.replace("l", "1").replace("I", "1").replace("|", "1")
+            text = text.replace("b", "8").replace("B", "8")
+            text = text.replace("z", "2").replace("Z", "2")
+            text = text.replace("a", "4").replace("A", "4")
+            text = text.replace("e", "3")
+            text = text.replace("t", "7")
+            text = text.replace("~", "").replace("`", "")
+            text = re.sub(r"(kgs|kg|k|lb|g|gr|pounds|lbs)\b", "", text)
+            text = re.sub(r"[^\d\.\-]", "", text)
+            if text.count('.') > 1:
+                parts = text.split('.')
+                text = parts[0] + '.' + ''.join(parts[1:])
+            text = text.strip('.')
+            if len(text.replace('.', '').replace('-', '')) > 0:  # Allow negative weights
+                try:
+                    weight = float(text)
+                    range_score = 1.0
+                    if 0.0 <= weight <= 250:
+                        range_score = 1.5
+                    elif weight > 250 and weight <= 500:
+                        range_score = 1.2
+                    elif weight > 500 and weight <= 1000:
+                        range_score = 1.0
+                    else:
+                        range_score = 0.5
+                    digit_count = len(text.replace('.', '').replace('-', ''))
+                    digit_score = 1.0
+                    if digit_count >= 2 and digit_count <= 5:
+                        digit_score = 1.3
+                    elif digit_count == 1:
+                        digit_score = 0.8
+                    score = conf * range_score * digit_score
+                    if roi_bbox:
+                        (x_roi, y_roi, w_roi, h_roi) = roi_bbox
+                        roi_area = w_roi * h_roi
+                        x_min, y_min = int(min(b[0] for b in bbox)), int(min(b[1] for b in bbox))
+                        x_max, y_max = int(max(b[0] for b in bbox)), int(max(b[1] for b in bbox))
+                        bbox_area = (x_max - x_min) * (y_max - y_min)
+                        if roi_area > 0 and bbox_area / roi_area < 0.02:
+                            score *= 0.5
+                        bbox_aspect_ratio = (x_max - x_min) / (y_max - y_min) if (y_max - y_min) > 0 else 0
+                        if bbox_aspect_ratio < 0.1:
+                            score *= 0.7
+                    if score > best_score and conf > conf_threshold:
+                        best_weight = text
+                        best_conf = conf
+                        best_score = score
+                        logging.info(f"Candidate EasyOCR weight: '{text}', Conf: {conf}, Score: {score}")
+                except ValueError:
+                    logging.warning(f"Could not convert '{text}' to float during EasyOCR fallback.")
+                    continue
 
         if not best_weight:
-            logging.info("No valid weight detected")
+            logging.info("No valid weight detected after all attempts.")
             return "Not detected", 0.0
 
         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.rstrip('0')}"
+            dec_part = dec_part.rstrip('0')
+            if not dec_part and int_part != "0":
+                best_weight = int_part
+            elif not dec_part and int_part == "0":
+                best_weight = "0"
+            else:
+                best_weight = f"{int_part}.{dec_part}"
         else:
             best_weight = best_weight.lstrip('0') or "0"
 
+        try:
+            final_float_weight = float(best_weight)
+            if final_float_weight < 0.0 or final_float_weight > 1000:
+                logging.warning(f"Detected weight {final_float_weight} is outside typical range, reducing confidence.")
+                best_conf *= 0.5
+        except ValueError:
+            logging.warning(f"Final weight '{best_weight}' is not a valid number.")
+            best_conf *= 0.5
+
+        logging.info(f"Final detected weight: {best_weight}, Confidence: {round(best_conf * 100, 2)}%")
         return best_weight, round(best_conf * 100, 2)
 
     except Exception as e:
-        logging.error(f"Weight extraction failed: {str(e)}")
+        logging.error(f"Weight extraction failed unexpectedly: {str(e)}")
         return "Not detected", 0.0