Computer Vision

Hi, I run a swiss AI consulting firm. One of my clients, an electrical planning office, marks up floor plans by hand — I want to automate this. THE TASK The client receives floor plans as PDFs (CAD exports). The tool should read such a PDF and return the same PDF with markings added on a separate layer: - an X in the center of every room (drill/anchor point) - a power outlet symbol in every room corner I have a Python prototype (PyMuPDF + OpenCV) that shows the approach, but it does not work reliably yet. You can use it as a reference or start fresh — your call. What matters is a solution that works correctly on real plans. REQUIREMENTS - Runs locally or on cloud - Handles typical variations (different CAD exports, multi-page PDFs) - Simple to use for a non-technical client (command line is fine to start; a small upload UI could be phase 2) I will provide the prototype code and several real sample plans (after NDA). Interested? Send me a short note with your relevant experience, a rough estimate (effort and price) and timeline, plus any open questions. Best regards, Niven