ALPR System

The Problem

Commercial license plate recognition systems cost between €5,000 and €10,000 per camera and are closed systems: proprietary hardware, proprietary software, no integration possible. For a 50-space parking lot or a condo with an automatic gate, the cost is prohibitive. The alternative was manual management or standard cameras with no automation.

The technical problem is more subtle than it seems: an Italian plate needs to be read in real conditions. Night with blinding headlights, rain, mud-covered plates, side angles, fast-moving vehicles. Generic models don't hold up under these conditions.

The Solution

I developed a custom system that works with normal IP cameras at €200-300. The core is YOLO11, trained on ~10,000 photos of Italian plates collected in every light, weather, and angle condition. The model locates the plate in the frame, crops it, and passes it to the OCR layer for text conversion.

The OCR has an automatic correction layer based on Italian plate patterns: two letters, three digits, two letters. When the system reads an O that should be a 0, or a B that looks like an 8, the plate format pattern guides the correction. This pushes accuracy to 98.5% even on degraded images.

The architecture is flexible: a central server for processing streams from multiple cameras, or edge computing directly on the camera for sub-100ms latency without network dependency. A web dashboard manages transit logs, subscriber whitelists, and hourly traffic statistics.

The Result

Parking lots with automatic barriers, condos with resident access, restricted traffic zones, warehouses tracking incoming and outgoing vans. The system brings full automation to contexts that previously couldn't afford it, at one-tenth the cost of commercial systems.