Project Description
I have a growing library of MP4 recordings of casino-grade slot machines and I need a reliable way to turn each session into structured data. For every spin I want the script to capture the start time, end time, bet size, win amount, any bonus triggers, and jackpots, then tally an overall spin count. The videos cover many different games, so the screen layout shifts from title to title; your solution therefore has to locate each region of interest on its own instead of relying on hard-coded coordinates.
Because bonuses and jackpots are marked with visually distinct graphics, you can leverage that cue when classifying events. Accuracy matters more than raw speed, but I still expect processing to run unattended once configured.
Please build a computer-vision / OCR pipeline that:
• Automatically detects and tracks the changing ROI zones for bet, win, credit, and any bonus or jackpot indicators
• Parses the text or numerical values frame-by-frame to create a chronological log of every spin
• Outputs clean CSV or JSON per session, plus a summary of total spins, total wagered, total won, and jackpots for tax reporting
• Includes a brief README and example command that reproduces your results on my sample MP4s
Acceptance criteria
• Works on at least three different game layouts without manual retuning
• ≥99.95 % accuracy on spin count, bet size and win amount when compared with my hand-labeled ground truth
• Correctly flags 100 % of visually distinct bonus/jackpot events in the provided test set
Feel free to use OpenCV, Tesseract, YOLO, or any modern deep-learning framework—whatever achieves dependable results.