Hybrid Educational Grading System Development

Project Overview:
I am looking for a developer or team to build a dual-mode educational grading system. The system consists of:

An iOS App: Capable of real-time scanning and grading of both standard OMR bubble sheets AND unique orientation-based cards (Plickers-style).

A PHP Web Backend: A tool to generate customized PDF test sheets and student cards using Chromium (via Spatie/Browsershot).

Privacy is paramount. All student scanning and grading must occur on-device to ensure data security.

Module 1: The iOS App (Swift/SwiftUI)
The app must feature a toggle or auto-detection to switch between two modes:

Mode A: OMR Bubble Sheets:

Detects standard multiple-choice grids.

Real-time detection of "filled" vs. "empty" bubbles using local image thresholding.

Mode B: Plickers-Style Cards:

Detects unique geometric shapes (markers) assigned to each student.

Grading is based on the orientation of the card (A, B, C, or D at the top).

Must support scanning multiple cards in a single camera frame (e.g., scanning a whole classroom).

Technical Requirements (iOS):

Engine: Use Apple’s Vision Framework and Core Image for high-speed, real-time processing.

Local Processing: No images should be sent to a server for grading. All logic must be local.

Database: Use CoreData or SQLite with encryption to store student rosters and scores.

Export: Generate CSV/Excel reports locally from the app.

Module 2: PDF Generation Engine (PHP/Chromium)
I need a system to generate the physical papers that the app will scan.

Technology: PHP 8.x with Spatie/Browsershot (Headless Chromium).

OMR Generator: Dynamically generate bubble sheets based on the number of questions (e.g., 10, 20, 50, 100 questions).

Plickers Card Generator: Generate a unique set of cards (40–60 unique patterns) with student names printed on the back/corners.

Layout: High-precision CSS layout to ensure that "anchor points" (the black squares in the corners) are perfectly placed for the iOS camera to find the grid.

Output: High-quality, print-ready PDFs.

Module 3: Privacy & Security
Zero-Cloud Grading: The server only generates the PDFs. It should never see the students' filled-in answers.

GDPR/FERPA Ready: The app must not include third-party trackers.

Local Encryption: Student data stored on the iPhone must be protected via the iOS Secure Enclave/Keychain.

Specific Deliverables:
iOS Source Code: Fully documented Swift code.

PHP Script/Backend: A web-based interface where I can input questions or student lists and download the generated PDFs.

PDF Samples: Set of 5 sample OMR templates and 1 set of 40 unique Plickers cards.

Hardware Calibration: The scanner must be optimized for different iPhone models (adjusting for focal length/distortions).

Developer Requirements:
Expertise in Computer Vision (Vision Framework, OpenCV, or AVFoundation).

Strong PHP/Laravel skills with experience in Puppeteer/Chromium/Browsershot.

Experience with Real-time Camera Overlays (drawing bounding boxes and scores over the live feed).

Ability to demonstrate previous OMR or QR-related scanning projects.

Application Instructions:
Please start your proposal with the word "HYBRID".
In your proposal, please answer:

How will you ensure the OMR grid detection remains accurate if the teacher holds the phone at an angle?

Have you used Browsershot/Chromium for high-precision print layouts before?