ocr_engine.py

import easyocr
import numpy as np
import cv2
import re
import logging
from datetime import datetime
import os

# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Initialize EasyOCR
try:
    easyocr_reader = easyocr.Reader(['en'], gpu=False)
    logging.info("EasyOCR initialized successfully")
except Exception as e:
    logging.error(f"Failed to initialize EasyOCR: {str(e)}")
    easyocr_reader = None

# Directory for debug images
DEBUG_DIR = "debug_images"
os.makedirs(DEBUG_DIR, exist_ok=True)

def save_debug_image(img, filename_suffix, prefix=""):
    """Save image to debug directory with 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:
        cv2.imwrite(filename, cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
    else:
        cv2.imwrite(filename, img)
    logging.info(f"Saved debug image: {filename}")

def estimate_brightness(img):
    """Estimate image brightness."""
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    return np.mean(gray)

def preprocess_image(img):
    """Preprocess image for OCR with enhanced contrast and noise reduction."""
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    brightness = estimate_brightness(img)
    # Dynamic CLAHE based on brightness
    clahe_clip = 4.0 if brightness < 80 else 2.0
    clahe = cv2.createCLAHE(clipLimit=clahe_clip, tileGridSize=(8, 8))
    enhanced = clahe.apply(gray)
    save_debug_image(enhanced, "01_preprocess_clahe")
    # Gaussian blur to reduce noise
    blurred = cv2.GaussianBlur(enhanced, (3, 3), 0)
    save_debug_image(blurred, "02_preprocess_blur")
    # Adaptive thresholding with dynamic block size
    block_size = max(11, min(31, int(img.shape[0] / 15) * 2 + 1))
    thresh = cv2.adaptiveThreshold(blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
                                   cv2.THRESH_BINARY_INV, block_size, 5)
    # Morphological operations to enhance digits
    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
    thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
    thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=2)
    save_debug_image(thresh, "03_preprocess_morph")
    return thresh, enhanced

def correct_rotation(img):
    """Correct image rotation using edge detection."""
    try:
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        edges = cv2.Canny(gray, 50, 150, apertureSize=3)
        lines = cv2.HoughLinesP(edges, 1, np.pi / 180, threshold=50, minLineLength=30, maxLineGap=10)
        if lines is not None:
            angles = [np.arctan2(line[0][3] - line[0][1], line[0][2] - line[0][0]) * 180 / np.pi for line in lines]
            angle = np.median(angles)
            if abs(angle) > 1.0:
                h, w = img.shape[:2]
                center = (w // 2, h // 2)
                M = cv2.getRotationMatrix2D(center, angle, 1.0)
                img = cv2.warpAffine(img, M, (w, h))
                save_debug_image(img, "00_rotated_image")
                logging.info(f"Applied rotation: {angle:.2f} degrees")
        return img
    except Exception as e:
        logging.error(f"Rotation correction failed: {str(e)}")
        return img

def detect_roi(img):
    """Detect region of interest (display) with multi-scale contour filtering."""
    try:
        save_debug_image(img, "04_original")
        thresh, enhanced = preprocess_image(img)
        brightness_map = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        # Try multiple block sizes for robust ROI detection
        block_sizes = [max(11, min(31, int(img.shape[0] / s) * 2 + 1)) for s in [15, 20, 25]]
        valid_contours = []
        img_area = img.shape[0] * img.shape[1]
        
        for block_size in block_sizes:
            temp_thresh = cv2.adaptiveThreshold(enhanced, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
                                                cv2.THRESH_BINARY_INV, block_size, 5)
            kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
            temp_thresh = cv2.morphologyEx(temp_thresh, cv2.MORPH_CLOSE, kernel, iterations=2)
            save_debug_image(temp_thresh, f"05_roi_threshold_block{block_size}")
            contours, _ = cv2.findContours(temp_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
            
            for c in contours:
                area = cv2.contourArea(c)
                x, y, w, h = cv2.boundingRect(c)
                roi_brightness = np.mean(brightness_map[y:y+h, x:x+w])
                aspect_ratio = w / h
                if (300 < area < (img_area * 0.7) and 
                    0.5 <= aspect_ratio <= 10.0 and w > 60 and h > 25 and roi_brightness > 40):
                    valid_contours.append((c, area * roi_brightness))
                    logging.debug(f"Contour (block {block_size}): Area={area}, Aspect={aspect_ratio:.2f}, Brightness={roi_brightness:.2f}")
        
        if valid_contours:
            contour, _ = max(valid_contours, key=lambda x: x[1])
            x, y, w, h = cv2.boundingRect(contour)
            padding = max(20, min(60, int(min(w, h) * 0.3)))
            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, "06_detected_roi")
            logging.info(f"Detected ROI: ({x}, {y}, {w}, {h})")
            return roi_img, (x, y, w, h)
        
        logging.info("No ROI found, using full image.")
        save_debug_image(img, "06_no_roi_fallback")
        return img, None
    except Exception as e:
        logging.error(f"ROI detection failed: {str(e)}")
        save_debug_image(img, "06_roi_error_fallback")
        return img, None

def detect_segments(digit_img, brightness):
    """Detect seven-segment digits with adaptive thresholds."""
    try:
        h, w = digit_img.shape
        if h < 10 or w < 5:
            logging.debug("Digit image too small for segment detection.")
            return None

        # Dynamic segment threshold based on brightness
        segment_threshold = 0.2 if brightness < 80 else 0.3
        segments = {
            '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*0.45), int(h*0.55)),
            'bottom': (int(w*0.1), int(w*0.9), int(h*0.75), h),
            'left_top': (0, int(w*0.3), int(h*0.1), int(h*0.5)),
            'left_bottom': (0, int(w*0.3), int(h*0.5), int(h*0.9)),
            'right_top': (int(w*0.7), w, int(h*0.1), int(h*0.5)),
            'right_bottom': (int(w*0.7), w, int(h*0.5), int(h*0.9))
        }

        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:
                segment_presence[name] = False
                continue
            pixel_count = np.sum(region == 255)
            total_pixels = region.size
            segment_presence[name] = pixel_count / total_pixels > segment_threshold
            logging.debug(f"Segment {name}: {pixel_count}/{total_pixels} = {pixel_count/total_pixels:.2f}")

        digit_patterns = {
            '0': ('top', 'bottom', 'left_top', 'left_bottom', 'right_top', 'right_bottom'),
            '1': ('right_top', 'right_bottom'),
            '2': ('top', 'middle', 'bottom', 'left_bottom', 'right_top'),
            '3': ('top', 'middle', 'bottom', 'right_top', 'right_bottom'),
            '4': ('middle', 'left_top', 'right_top', 'right_bottom'),
            '5': ('top', 'middle', 'bottom', 'left_top', 'right_bottom'),
            '6': ('top', 'middle', 'bottom', 'left_top', 'left_bottom', 'right_bottom'),
            '7': ('top', 'right_top', 'right_bottom'),
            '8': ('top', 'middle', 'bottom', 'left_top', 'left_bottom', 'right_top', 'right_bottom'),
            '9': ('top', 'middle', 'bottom', 'left_top', 'right_top', 'right_bottom')
        }

        best_match, best_score = None, -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 - 0.2 * non_matches
            if matches >= len(pattern) * 0.6:
                score += 1.0
            if score > best_score:
                best_score = score
                best_match = digit
        logging.debug(f"Segment detection: {segment_presence}, Digit: {best_match}, Score: {best_score:.2f}")
        return best_match
    except Exception as e:
        logging.error(f"Segment detection failed: {str(e)}")
        return None

def perform_ocr(img, roi_bbox):
    """Perform OCR with EasyOCR and seven-segment fallback."""
    if easyocr_reader is None:
        logging.error("EasyOCR not initialized, cannot perform OCR.")
        return None, 0.0
    try:
        thresh, enhanced = preprocess_image(img)
        brightness = estimate_brightness(img)
        # Dynamic EasyOCR parameters
        results = easyocr_reader.readtext(thresh, detail=1, paragraph=False, 
                                          contrast_ths=0.1, adjust_contrast=1.5, 
                                          text_threshold=0.3, mag_ratio=3.0, 
                                          allowlist='0123456789.', batch_size=1, y_ths=0.2)
        save_debug_image(thresh, "07_ocr_threshold")
        logging.info(f"EasyOCR results: {results}")

        if not results:
            logging.info("EasyOCR failed, trying fallback parameters.")
            results = easyocr_reader.readtext(thresh, detail=1, paragraph=False, 
                                              contrast_ths=0.05, adjust_contrast=2.0, 
                                              text_threshold=0.2, mag_ratio=4.0, 
                                              allowlist='0123456789.', batch_size=1, y_ths=0.2)
            save_debug_image(thresh, "07_fallback_threshold")

        digits_info = []
        for (bbox, text, conf) in results:
            (x1, y1), (x2, y2), (x3, y3), (x4, y4) = bbox
            h_bbox = max(y1, y2, y3, y4) - min(y1, y2, y3, y4)
            if (text.isdigit() or text == '.') and h_bbox > 10 and conf > 0.2:
                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))

        if digits_info:
            digits_info.sort(key=lambda x: x[0])
            recognized_text = ""
            total_conf = 0.0
            conf_count = 0
            for idx, (x_min, x_max, y_min, y_max, char, 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
                if conf < 0.7 and char != '.':
                    digit_crop = thresh[y_min:y_max, x_min:x_max]
                    save_debug_image(digit_crop, f"08_digit_crop_{idx}_{char}")
                    segment_digit = detect_segments(digit_crop, brightness)
                    if segment_digit:
                        recognized_text += segment_digit
                        total_conf += 0.85
                        logging.debug(f"Used segment detection for char {char}: {segment_digit}")
                    else:
                        recognized_text += char
                        total_conf += conf
                    conf_count += 1
                else:
                    recognized_text += char
                    total_conf += conf
                    conf_count += 1
            
            avg_conf = total_conf / conf_count if conf_count > 0 else 0.0
            text = re.sub(r"[^\d\.]", "", recognized_text)
            if text.count('.') > 1:
                text = text.replace('.', '', text.count('.') - 1)
            text = text.strip('.')
            if text and re.fullmatch(r"^\d*\.?\d*$", text):
                text = text.lstrip('0') or '0'
                logging.info(f"Validated text: {text}, Confidence: {avg_conf:.2f}")
                return text, avg_conf * 100
        logging.info("No valid digits detected.")
        return None, 0.0
    except Exception as e:
        logging.error(f"OCR failed: {str(e)}")
        return None, 0.0

def extract_weight_from_image(pil_img):
    """Extract weight from a digital scale image."""
    try:
        img = np.array(pil_img)
        img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
        save_debug_image(img, "00_input_image")
        img = correct_rotation(img)
        brightness = estimate_brightness(img)
        conf_threshold = 0.7 if brightness > 100 else 0.5

        roi_img, roi_bbox = detect_roi(img)
        if roi_bbox:
            conf_threshold *= 1.1 if (roi_bbox[2] * roi_bbox[3]) > (img.shape[0] * img.shape[1] * 0.3) else 1.0

        result, confidence = perform_ocr(roi_img, roi_bbox)
        if result and confidence >= conf_threshold * 100:
            try:
                weight = float(result)
                if 0.01 <= weight <= 1000:
                    logging.info(f"Detected weight: {result} kg, Confidence: {confidence:.2f}%")
                    return result, confidence
                logging.warning(f"Weight {result} out of range.")
            except ValueError:
                logging.warning(f"Invalid weight format: {result}")

        logging.info("Primary OCR failed, using full image fallback.")
        result, confidence = perform_ocr(img, None)
        if result and confidence >= conf_threshold * 0.9 * 100:
            try:
                weight = float(result)
                if 0.01 <= weight <= 1000:
                    logging.info(f"Full image weight: {result} kg, Confidence: {confidence:.2f}%")
                    return result, confidence
                logging.warning(f"Full image weight {result} out of range.")
            except ValueError:
                logging.warning(f"Invalid full image weight format: {result}")

        logging.info("No valid weight detected.")
        return "Not detected", 0.0
    except Exception as e:
        logging.error(f"Weight extraction failed: {str(e)}")
        return "Not detected", 0.0