image-to-data

Image To Data

Overview

Based on DDC methodology (Chapter 2.4), this skill extracts structured data from construction images using computer vision, OCR, and AI models to analyze site photos, scanned documents, and drawings.

Book Reference: "Преобразование данных в структурированную форму" / "Data Transformation to Structured Form"

Quick Start

from dataclasses import dataclass, field
from enum import Enum
from typing import List, Dict, Optional, Any, Tuple
from datetime import datetime
import json
import base64

class ImageType(Enum):
    """Types of construction images"""
    SITE_PHOTO = "site_photo"
    SCANNED_DOCUMENT = "scanned_document"
    FLOOR_PLAN = "floor_plan"
    ELEVATION = "elevation"
    DETAIL_DRAWING = "detail_drawing"
    PROGRESS_PHOTO = "progress_photo"
    SAFETY_PHOTO = "safety_photo"
    DEFECT_PHOTO = "defect_photo"
    MATERIAL_PHOTO = "material_photo"
    EQUIPMENT_PHOTO = "equipment_photo"

class ExtractionType(Enum):
    """Types of data extraction"""
    OCR_TEXT = "ocr_text"
    TABLE = "table"
    OBJECT_DETECTION = "object_detection"
    MEASUREMENT = "measurement"
    CLASSIFICATION = "classification"
    PROGRESS = "progress"

@dataclass
class BoundingBox:
    """Bounding box for detected region"""
    x: int
    y: int
    width: int
    height: int
    confidence: float = 1.0

@dataclass
class TextRegion:
    """Extracted text region from image"""
    text: str
    bbox: BoundingBox
    confidence: float
    language: str = "en"

@dataclass
class DetectedObject:
    """Detected object in image"""
    label: str
    bbox: BoundingBox
    confidence: float
    attributes: Dict[str, Any] = field(default_factory=dict)

@dataclass
class ExtractedTable:
    """Extracted table from image"""
    headers: List[str]
    rows: List[List[str]]
    bbox: BoundingBox
    confidence: float

@dataclass
class ProgressMeasurement:
    """Progress measurement from image"""
    element_type: str
    total_count: int
    completed_count: int
    percent_complete: float
    area_sqft: Optional[float] = None
    volume_cuft: Optional[float] = None

@dataclass
class ImageAnalysisResult:
    """Complete image analysis result"""
    image_id: str
    image_type: ImageType
    text_regions: List[TextRegion]
    detected_objects: List[DetectedObject]
    tables: List[ExtractedTable]
    progress: Optional[ProgressMeasurement] = None
    metadata: Dict[str, Any] = field(default_factory=dict)
    processing_time: float = 0.0


class OCREngine:
    """OCR engine for text extraction"""

    def __init__(self, engine: str = "tesseract"):
        self.engine = engine
        self.supported_languages = ["en", "ru", "de", "fr", "es"]

    def extract_text(
        self,
        image_data: bytes,
        language: str = "en"
    ) -> List[TextRegion]:
        """Extract text from image"""
        # Simulated OCR extraction (use actual OCR library in production)
        # In production: pytesseract, EasyOCR, or cloud OCR services

        regions = []

        # Simulate detecting title block in drawing
        regions.append(TextRegion(
            text="PROJECT: OFFICE BUILDING",
            bbox=BoundingBox(x=100, y=50, width=300, height=30, confidence=0.95),
            confidence=0.95,
            language=language
        ))

        regions.append(TextRegion(
            text="DRAWING: A-101",
            bbox=BoundingBox(x=100, y=90, width=200, height=25, confidence=0.92),
            confidence=0.92,
            language=language
        ))

        regions.append(TextRegion(
            text="SCALE: 1:100",
            bbox=BoundingBox(x=100, y=120, width=150, height=20, confidence=0.88),
            confidence=0.88,
            language=language
        ))

        return regions

    def extract_structured_text(
        self,
        image_data: bytes,
        template: Optional[Dict] = None
    ) -> Dict[str, str]:
        """Extract structured text using template matching"""
        # Extract text regions
        regions = self.extract_text(image_data)

        # Match to template fields
        structured = {}

        if template:
            for field_name, field_config in template.items():
                # Find matching region
                for region in regions:
                    if field_config.get("keyword") in region.text.lower():
                        structured[field_name] = region.text
                        break
        else:
            # Default extraction
            for region in regions:
                if "PROJECT:" in region.text:
                    structured["project_name"] = region.text.split(":")[-1].strip()
                elif "DRAWING:" in region.text:
                    structured["drawing_number"] = region.text.split(":")[-1].strip()
                elif "SCALE:" in region.text:
                    structured["scale"] = region.text.split(":")[-1].strip()

        return structured


class ObjectDetector:
    """Object detection for construction images"""

    def __init__(self, model: str = "yolov8"):
        self.model = model
        self.construction_classes = self._load_construction_classes()

    def _load_construction_classes(self) -> Dict[str, Dict]:
        """Load construction-specific object classes"""
        return {
            # Equipment
            "excavator": {"category": "equipment", "safety_zone": 20},
            "crane": {"category": "equipment", "safety_zone": 30},
            "forklift": {"category": "equipment", "safety_zone": 10},
            "concrete_mixer": {"category": "equipment", "safety_zone": 5},
            "scaffolding": {"category": "equipment", "safety_zone": 5},

            # Safety
            "hard_hat": {"category": "ppe", "required": True},
            "safety_vest": {"category": "ppe", "required": True},
            "safety_glasses": {"category": "ppe", "required": False},
            "harness": {"category": "ppe", "required": False},

            # Materials
            "rebar_bundle": {"category": "material", "unit": "bundle"},
            "concrete_block": {"category": "material", "unit": "pallet"},
            "lumber_stack": {"category": "material", "unit": "bundle"},
            "pipe_stack": {"category": "material", "unit": "bundle"},

            # Workers
            "worker": {"category": "person", "track": True},

            # Building elements
            "column": {"category": "structure"},
            "beam": {"category": "structure"},
            "slab": {"category": "structure"},
            "wall": {"category": "structure"},
        }

    def detect(
        self,
        image_data: bytes,
        confidence_threshold: float = 0.5
    ) -> List[DetectedObject]:
        """Detect objects in image"""
        # Simulated detection (use actual model in production)
        # In production: YOLO, Faster R-CNN, etc.

        detected = []

        # Simulate detected objects
        sample_detections = [
            ("worker", 0.92, BoundingBox(200, 300, 80, 180, 0.92)),
            ("hard_hat", 0.88, BoundingBox(210, 300, 30, 25, 0.88)),
            ("safety_vest", 0.85, BoundingBox(210, 340, 60, 80, 0.85)),
            ("scaffolding", 0.78, BoundingBox(400, 100, 200, 400, 0.78)),
            ("concrete_block", 0.72, BoundingBox(50, 450, 100, 50, 0.72)),
        ]

        for label, conf, bbox in sample_detections:
            if conf >= confidence_threshold:
                class_info = self.construction_classes.get(label, {})
                detected.append(DetectedObject(
                    label=label,
                    bbox=bbox,
                    confidence=conf,
                    attributes=class_info
                ))

        return detected

    def detect_safety_compliance(
        self,
        image_data: bytes
    ) -> Dict:
        """Detect safety compliance in image"""
        objects = self.detect(image_data)

        workers = [o for o in objects if o.label == "worker"]
        hard_ha