⚡ Optimize redundant image loading in crop_face

[LebToki]

💡 What: Changed FaceDetector.crop_face to accept either an image path string or a pre-loaded numpy array. Updated app.py to load the image into memory once, and then pass that numpy array directly into crop_face for each detected face in the loop.

🎯 Why: To solve the performance issue of reading the same image from disk repeatedly for every detected face during multi-face processing.

📊 Measured Improvement: Benchmarking an image with 100 faces taking 100 crops revealed a dramatic performance bump, going from a baseline of ~0.31s down to ~0.003s, which represents an approximate 100x speedup in the specific loop.

---

PR created automatically by Jules for task 15693430642243536256 started by @LebToki

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.